TypeWhisper v1.0.8

TypeWhisper 1.0.8 is a stable Windows feature and reliability release focused on more flexible workflows, safer authenticated provider integrations, and stronger state preservation across recording, updates, and clipboard use.

Highlights

• Added a first-party integration for authenticated provider CLI sessions used by LLM workflow processing, with executable discovery, authentication status, structured input and output, timeouts, cancellation, and process cleanup.
• Added configurable App or website and App and website matching for automatic workflow triggers while preserving the behavior of existing combined workflows.
• Added \s support for inserting literal spaces in dictionary replacements, with updated guidance in every supported app language.

Reliability Improvements

• Preserved explicitly disabled term packs, vocabulary boosting preferences, and pending industry presets across updates, catalog refreshes, licensing, and user-data migration.
• Fixed recorder overlays so finalizing is no longer shown as an active recording, with more reliable placement across monitors and DPI scales.
• Improved bitmap clipboard capture and restoration for delayed, unavailable, and OLE bitmap representations during temporary paste operations.
• Kept missing or unavailable provider selections visible and actionable instead of silently routing workflow processing to another provider.

Security and Compatibility

• Restricted provider processes to fixed arguments, a controlled environment and working directory, bounded output, disabled tools and project context, and process-tree termination on cancellation or timeout.
• Kept unsupported provider paths unavailable until equivalent per-invocation safety controls can be verified.
• Added stable UI Automation identifiers and clearer recorder overlay status descriptions for accessibility and runtime validation.

Validation Notes

• Verify stable Velopack channels win-x64 and win-arm64.
• Confirm x64 and ARM64 installers, portable ZIPs, full nupkg packages, RELEASES files, and JSON manifests are present without -daily suffixes.
• Validate both published portable ZIPs and record the Authenticode status of the published installers.
• Publish Microsoft Store package 1.0.8.0 and WinGet package 1.0.8 separately from the GitHub release.

Other Changes

• Fix MCP tool catalog refresh (#1094)
• Add Obsidian live sync and Markdown templates (#1089)
• Add Streamable HTTP to MCP client (#1088)
• Add MCP client action add-on (#1087)
• Add bulk plugin updates and automatic restart (#1073)
• Fix calendar access entitlement (#1072)
• release Speechmatics plugin 1.0.8 (#1070)
• Fix Speechmatics US batch routing and language packs (#1069)
• Fix calendar access request flow (#1066)
• Bump Soniox plugin to 1.2.6 (#1065)
• Clean up Soniox async resources and surface quota errors (#1064)
• Fix WhisperKit restore for workflow model overrides (#1062)
• Fix readiness for restorable transcription models (#1061)
• Add premium calendar meeting automation (#1050)
• Fix WhisperKit auto-reload after model unload (#1060)
• Add recovery audio retention controls (#1056)
• Add Simplified Chinese localization (#1041)
• Bump OpenAI Compatible plugin to 1.1.7 (#1054)
• Add realtime transcription support to OpenAI Compatible plugin (#1052)
• Add optional API version to OpenAI-compatible profiles (#1051)

Other Changes

• Harden authenticated CLI process isolation
• Add authenticated provider CLI prompt processing
• Fix recorder overlay finalizing state

Other Changes

• Cover vocabulary boosting state
• Preserve pending preset activation
• Preserve disabled term packs across updates
• Support space escape in dictionary replacements
• Add configurable workflow context matching
• Assert unavailable OLE bitmap alias
• Preserve bitmap clipboard representations

Other Changes

• Add Obsidian live sync and Markdown templates (#1089)
• Add Streamable HTTP to MCP client (#1088)
• Add MCP client action add-on (#1087)
• Add bulk plugin updates and automatic restart (#1073)
• Fix calendar access entitlement (#1072)
• release Speechmatics plugin 1.0.8 (#1070)
• Fix Speechmatics US batch routing and language packs (#1069)
• Fix calendar access request flow (#1066)
• Bump Soniox plugin to 1.2.6 (#1065)
• Clean up Soniox async resources and surface quota errors (#1064)
• Fix WhisperKit restore for workflow model overrides (#1062)
• Fix readiness for restorable transcription models (#1061)
• Add premium calendar meeting automation (#1050)
• Fix WhisperKit auto-reload after model unload (#1060)
• Add recovery audio retention controls (#1056)
• Add Simplified Chinese localization (#1041)
• Bump OpenAI Compatible plugin to 1.1.7 (#1054)
• Add realtime transcription support to OpenAI Compatible plugin (#1052)
• Add optional API version to OpenAI-compatible profiles (#1051)

Other Changes

• Add 1.0.7 release notes
• Harden local model lifecycle and plugin state
• Restrict model UI exception handling
• Serialize recorder lifecycle transitions
• Harden recorder scope and plugin paths
• Address triage review findings
• Address triage review findings
• Harden local model plugin lifecycle (#193)
• Add local model retry and removal controls (#193)
• Research browser microphone integration (#304)
• Document Parakeet Realtime EOU Windows status (#155)
• Update OpenAI catalog version expectations (#54)
• Improve AMD acceleration diagnostics (#234)
• Document Windows platform parity (#58)
• Add transcription dictionary term budgets (#54)
• Add recorder transcription overrides (#196)
• Redesign integrations catalog sources (#189)
• Add community plugin registry feed support (#190)
• Add registry artifact trust validation (#191)
• Add plugin repair diagnostics (#192)
• Add configurable LLM request timeout (#199)
• Fix workflow prompt input framing (#342)

TypeWhisper v1.0.7

TypeWhisper 1.0.7 is a stable Windows feature and reliability release focused on better transcription output, faster recovery, safer local models, and more capable integrations.

Highlights

• Added Smart Formatting, regular-expression dictionary rules, short-utterance punctuation, spoken-number normalization, and regional German output for Germany, Austria, Switzerland, and neutral written German.
• Added interactive usage statistics with daily activity, language and app breakdowns, keyboard-accessible details, and retention-independent totals.
• Improved immediate dictation startup, automatic recovery after interrupted sessions, and clipboard restoration when text insertion fails.
• Added unified local-model download requirements, retry and removal controls, optional Hugging Face authentication, and revision-aware license acceptance.

Integrations and Models

• Added local Cohere Transcribe support and hardened the packaged Sherpa ONNX, cuDNN, Whisper.cpp, Granite Speech, and Supertonic TTS runtimes.
• Added recorder-specific transcription engine and model overrides for long recordings without changing the main dictation model.
• Added configurable request timeouts per OpenAI Compatible profile and safer Unicode, reasoning, and thinking-content handling.
• Redesigned Integrations around Installed, Discover, and Manual sources with trusted registry artifacts, community feeds, compatibility diagnostics, update-state details, and repair actions.
• Added provider-aware dictionary budgets and stronger workflow input and output boundaries for plugin integrations.

Windows Experience

• Added Simplified Chinese localization and expanded localized model, integration, and recorder controls.
• Added an About section with project, support, documentation, and license links.
• Displayed History timestamps in local time while preserving UTC storage.
• Reworked Script Runner editing and made mouse-based dictation hotkeys safer.
• Improved onboarding model update state and local-model acceleration details.

Reliability Improvements

• Serialized recorder start and stop transitions so concurrent API requests cannot overwrite active sessions or leak model scopes.
• Made local-model progress, cancellation, removal, selection persistence, and service disposal safe across concurrent operations.
• Hardened plugin discovery, compatibility checks, package verification, rollback, path validation, and broken-install reporting.
• Preserved existing text and selection state across workflow processing and insertion recovery paths.

Validation Notes

• Verify stable Velopack channels win-x64 and win-arm64.
• Confirm x64 and ARM64 installers, portable ZIPs, full nupkg packages, RELEASES files, and JSON manifests are present without -rc or -daily suffixes.
• Validate both published portable ZIPs and record the Authenticode status of the published installers.
• Publish Microsoft Store package 1.0.7.0 and WinGet package 1.0.7 separately from the GitHub release.

Maintenance release v1.0.7-daily.20260810

Other Changes

• Add bulk plugin updates and automatic restart (#1073)
• Fix calendar access entitlement (#1072)
• release Speechmatics plugin 1.0.8 (#1070)
• Fix Speechmatics US batch routing and language packs (#1069)
• Fix calendar access request flow (#1066)
• Bump Soniox plugin to 1.2.6 (#1065)
• Clean up Soniox async resources and surface quota errors (#1064)
• Fix WhisperKit restore for workflow model overrides (#1062)
• Fix readiness for restorable transcription models (#1061)
• Add premium calendar meeting automation (#1050)
• Fix WhisperKit auto-reload after model unload (#1060)
• Add recovery audio retention controls (#1056)
• Add Simplified Chinese localization (#1041)
• Bump OpenAI Compatible plugin to 1.1.7 (#1054)
• Add realtime transcription support to OpenAI Compatible plugin (#1052)
• Add optional API version to OpenAI-compatible profiles (#1051)

Other Changes

• Harden short utterance punctuation handling
• Add short utterance punctuation control
• Address statistics review feedback
• Show friendly model names in statistics
• Add interactive usage statistics
• Avoid duplicate German variant settings saves
• Address German output review feedback
• Add regional German output variants
• Add opt-in regex dictionary corrections
• Cover unsupported language fallback
• Normalize spoken numbers without language metadata
• Display history timestamps in local time
• Expose project links in About

Other Changes

• release Speechmatics plugin 1.0.8 (#1070)
• Fix Speechmatics US batch routing and language packs (#1069)
• Fix calendar access request flow (#1066)
• Bump Soniox plugin to 1.2.6 (#1065)
• Clean up Soniox async resources and surface quota errors (#1064)
• Fix WhisperKit restore for workflow model overrides (#1062)
• Fix readiness for restorable transcription models (#1061)
• Add premium calendar meeting automation (#1050)
• Fix WhisperKit auto-reload after model unload (#1060)
• Add recovery audio retention controls (#1056)
• Add Simplified Chinese localization (#1041)
• Bump OpenAI Compatible plugin to 1.1.7 (#1054)
• Add realtime transcription support to OpenAI Compatible plugin (#1052)
• Add optional API version to OpenAI-compatible profiles (#1051)

Maintenance release v1.0.7-daily.20260808

Other Changes

• Bump Soniox plugin to 1.2.6 (#1065)
• Clean up Soniox async resources and surface quota errors (#1064)
• Fix WhisperKit restore for workflow model overrides (#1062)
• Fix readiness for restorable transcription models (#1061)
• Add premium calendar meeting automation (#1050)
• Fix WhisperKit auto-reload after model unload (#1060)
• Add recovery audio retention controls (#1056)
• Add Simplified Chinese localization (#1041)
• Bump OpenAI Compatible plugin to 1.1.7 (#1054)
• Add realtime transcription support to OpenAI Compatible plugin (#1052)
• Add optional API version to OpenAI-compatible profiles (#1051)

Other Changes

• Handle Windows clipboard protection metadata
• Harden clipboard transaction edge cases
• Fix clipboard restoration after auto paste
• Address recovery review feedback
• Add dictation recovery and request resilience

Other Changes

• Fix readiness for restorable transcription models (#1061)
• Add premium calendar meeting automation (#1050)
• Fix WhisperKit auto-reload after model unload (#1060)
• Add recovery audio retention controls (#1056)
• Add Simplified Chinese localization (#1041)
• Bump OpenAI Compatible plugin to 1.1.7 (#1054)
• Add realtime transcription support to OpenAI Compatible plugin (#1052)
• Add optional API version to OpenAI-compatible profiles (#1051)

Other Changes

• Tighten dictation lifecycle safeguards
• Harden dictation cancellation and API failures
• Pin delayed dictation preparation state
• Harden delayed dictation lifecycle handling
• Enable instant dictation recording startup
• Handle ASR commas around structural commands
• Refine spoken formatting defaults and settings
• Address Script Runner review feedback
• Rewrite Script Runner configuration and execution
• Fix remaining spoken formatting test path
• Address spoken formatting review feedback
• Fix spoken formatting test dialog binding
• Add spoken and smart formatting support
• Handle model update review edge cases
• Refresh model state after plugin updates
• Prevent unsafe mouse hotkeys

Other Changes

• Add recovery audio retention controls (#1056)
• Add Simplified Chinese localization (#1041)
• Bump OpenAI Compatible plugin to 1.1.7 (#1054)
• Add realtime transcription support to OpenAI Compatible plugin (#1052)
• Add optional API version to OpenAI-compatible profiles (#1051)

Maintenance release v1.0.7-daily.20260805

Other Changes

• Bump OpenAI Compatible plugin to 1.1.7 (#1054)
• Add realtime transcription support to OpenAI Compatible plugin (#1052)
• Add optional API version to OpenAI-compatible profiles (#1051)

Other Changes

• Harden audio capture failure recovery
• Restore immediate microphone capture startup

Other Changes

• Add optional API version to OpenAI-compatible profiles (#1051)

Other Changes

• Preserve Unicode in OpenAI-compatible requests
• Use DeepInfra reasoning effort control
• Fix DeepInfra reasoning control

TypeWhisper 1.6.0-rc1 opens the 1.6 release-candidate line with a more productive settings experience, new statistics and backup tools, and a broad reliability pass across dictation, audio routing, workflows, integrations, and local models.

Highlights

• Unified the visual language across Settings, including dashboards, forms, collections, workspaces, and advanced tool pages.
• Added a Statistics view for privacy-friendly aggregate usage insights.
• Added Backup & Restore for portable workflows, dictionary entries, snippets, profiles, prompt actions, hotkeys, installed community plugins, transcription history text, update-channel selection, and supported preferences.
• Regrouped the menu bar for faster access and now shows the active transcription provider alongside the selected model.

Dictation Reliability

• Added an ordered microphone priority list and improved recovery for AirPods, Bluetooth system-default input, clamshell changes, and FaceTime built-in microphone capture.
• Reduced startup and dictation latency while keeping recording and model preparation responsive.
• Fixed indicator placement, dismissal, fullscreen visibility, feedback interaction, countdown progress, and optional screen-capture visibility.
• Improved contextual insertion for Firefox, CJK text, trailing spaces, secure-input situations, and target-app correction learning.

Dictionary & Workflows

• Added dictionary search, safe reset actions, grouped correction variants, clearer learned-correction visibility, and a guided microphone correction trainer.
• Applied dictionary corrections to file transcription and connected per-term CTC tuning to Parakeet.
• Added ordered global LLM provider and model fallbacks while keeping explicit workflow providers strict.
• Added explicit workflow dictation through the local API and improved webhook and Obsidian workflow configuration.

Models & Integrations

• Added a live-preview engine override so preview can stay local while final transcription uses the configured dictation engine.
• Added Soniox live WebSocket transcription and the local Cohere Transcribe integration.
• Added context-aware OpenAI transcription and dynamic ChatGPT model discovery.
• Improved MLX model storage, lazy restore, stalled-download recovery, and lifecycle handling across Qwen3, Gemma 4, Granite, Voxtral, Parakeet, and WhisperKit.

Known Limitation

• Automatic private iCloud sync is disabled in this build while the production container and Developer ID provisioning profile remain unavailable.
• Cloud Folder Sync through a user-selected iCloud Drive, Dropbox, OneDrive, Syncthing, or custom folder remains available.

Testing Focus

• Verify both an upgrade from 1.5.1 and a clean installation, including permissions, first dictation, and preservation of user data and update-channel selection.
• Exercise AirPods, Bluetooth, clamshell, virtual-input, and built-in microphone routes across dictation and Recorder sessions.
• Smoke-test dictation, text insertion, file transcription and export, workflows, History, the local HTTP API, and the CLI.
• Verify that the tagged RC1 build hides automatic private iCloud sync while preserving user-selected Cloud Folder Sync.
• Verify Dictionary search, correction training, per-term CTC, Backup & Restore, Statistics, indicators, models, bundled integrations, community plugins, and the Release Candidate update channel.

Other Changes

• Add macOS project icon (#1045)
• Fix duplicate MLX model storage
• Fix indicator feedback interaction and countdown (#1034)

Other Changes

• Add project icon assets
• Report missing final chat content
• Simplify thinking mode checkbox handling
• Fix OpenAI-compatible thinking output and model selection

Other Changes

• Fix AssemblyAI Universal 3.5 Pro support (#1043)

Other Changes

• Ensure welcome localization test cleanup
• Refresh localized welcome state
• Fix Chinese fallback and localized error refresh
• Fix localization state refresh edge cases
• Address localization review feedback
• Add Simplified Chinese localization

Maintenance release v1.0.7-daily.20260731

Other Changes

• Complete Cohere German localization (#1035)
• Add local Cohere Transcribe plugin (#1032)
• Fix OpenAI file transcription finalization (#1030)

Other Changes

• Restart Cohere sidecar after unexpected exit
• Harden Cohere benchmark validation
• Document optional benchmark retries
• Benchmark quantizations with persistent CrispASR
• Add reproducible Cohere quantization benchmark
• Add selectable Cohere quantizations
• Reference Windows SDK without changing plugin output
• Use managed Store data path resolution
• Fix Cohere runtime loading in Store package
• Address Cohere review findings
• Harden Cohere resource cleanup
• Add local Cohere transcription plugin
• Cap GitHub release pagination
• Use safe portable marker path join
• Fix portable update checks and release filtering
• Fix cuDNN loading in packaged app
• Release Sherpa ONNX plugin 1.0.4

Other Changes

• Sync per-term CTC to Parakeet (#1017)
• Add context-aware transcription and dynamic ChatGPT models (#1016)
• Attach existing Polar activations to Premium accounts (#1015)
• Add live preview engine override (preview locally, transcribe finally on the dictation engine) (#943)
• Bump Soniox plugin to 1.2.5 (#1013)
• Retry Soniox async jobs with WAV (#1012)

Other Changes

• Prepare 1.0.6 release notes
• Handle sparse OpenAI model catalogs
• Refine model refresh credential handling
• Harden model catalog refresh handling
• Ship OpenAI transcription and dynamic model catalogs
• Match Individual device count exactly
• Increase Individual license device limit
• Rollback cancelled plugin initialization
• Harden startup and capture fallback paths
• Improve startup and recording performance
• Move Soniox compression off the caller thread
• Prefer compressed Soniox uploads with WAV fallback

TypeWhisper v1.0.6

TypeWhisper 1.0.6 is a stable Windows performance and reliability release focused on faster startup, responsive settings, dependable microphone capture, and safer local transcription.

Highlights

• Rendered the tray, recording overlay, and settings shell before slower plugin, model, and audio-device initialization work.
• Replaced periodic audio-device polling with event-driven notifications and cached enumeration.
• Restored low-latency WASAPI recording with automatic WaveIn fallback while continuing to release capture resources between dictations.
• Added isolated CUDA runtime safety checks with automatic CPU fallback for local transcription.
• Increased the Individual license tier from two to three devices.

Integration Updates

• OpenAI plugin 1.1.1 adds gpt-transcribe and gpt-live-transcribe, dynamic account-specific model catalogs, ordered language hints, dictionary terms, and safer cached fallbacks.
• Soniox plugin 1.1.0 uses compressed M4A uploads when available and retries with the original WAV when compression is unavailable or rejected.
• Both integration updates are available through the TypeWhisper plugin marketplace and remain optional.

Reliability Improvements

• Deferred local model loading until first use to reduce startup work.
• Rolled back cancelled plugin initialization cleanly.
• Hardened microphone device changes, capture startup, and fallback paths.
• Preserved valid OpenAI model selections when remote catalogs are sparse or temporarily unavailable.
• Matched the three-device Individual entitlement exactly without misclassifying larger device counts.

Validation Notes

• Verify stable Velopack channels win-x64 and win-arm64.
• Confirm x64 and ARM64 installers, portable ZIPs, full nupkg packages, RELEASES files, and JSON manifests are present without -rc or -daily suffixes.
• Validate both published portable ZIPs and record the Authenticode status of the published installers.
• Publish Microsoft Store package 1.0.6.0 and WinGet package 1.0.6 separately from the GitHub release.

Other Changes

• Fix Safari maximized window indicator suppression (#1010)
• Add indicator screen capture visibility setting (#1009)

Other Changes

• Prepare 1.0.5 release notes
• Clarify prompt streaming contract and UI selector tests
• Add configurable ElevenLabs transcription options
• Bump actions/setup-python from 6 to 7 in the github-actions group

TypeWhisper v1.0.5

TypeWhisper 1.0.5 is a stable Windows maintenance release focused on reliable dictation sessions, safer portable upgrades, clearer plugin configuration, and better local integrations.

Highlights

• Released microphone capture between dictations so consecutive recordings use a fresh capture session.
• Added safe cross-volume migration for legacy portable user data.
• Added workflow-specific dictation through the local API while preserving existing bodyless start requests.
• Added configurable ElevenLabs transcription modes, audio-event handling, speaker options, and TypeWhisper dictionary support.

Improvements

• Moved plugin settings into accessible, resizable modal windows that open after installation and from installed plugin cards.
• Added staged Save and Cancel behavior to the Script Runner editor.
• Exposed active workflow details and workflow dictation capability through API status responses.
• Added x64 and ARM64 portable archive validation to package dry runs and release builds.

Fixes

• Fixed side-specific bare-modifier main dictation hotkeys such as Right Alt and Right Ctrl.
• Fixed microphone resources remaining open between recording sessions.
• Fixed portable startup when legacy user data resolves to another volume.
• Fixed Script Runner edits collapsing the selected script after each input.

Validation Notes

• Verify stable Velopack channels win-x64 and win-arm64.
• Confirm x64 and ARM64 installers, portable ZIPs, full nupkg packages, RELEASES files, and JSON manifests are present without -rc or -daily suffixes.
• Validate both published portable ZIPs and record the Authenticode status of the published installers.

Maintenance release v1.0.5-daily.20260727

Other Changes

• Fix CJK contextual insertion spacing (#1002)

Maintenance release v1.0.5-daily.20260726

Other Changes

• Optimize startup and dictation responsiveness (#1000)

Maintenance release v1.0.5-daily.20260725

Other Changes

• Polish settings UI: dashboard animations, hover effects, and layout consistency (#995)
• Fix AirPods dictation microphone readiness (#994)
• Streamline release validation checklist
• Harden CI: pin action, scope token permissions, drop unused imports (#988)
• Add subtle motion to About logo and settings sidebar icons (#990)
• Bump Deepgram plugin to 1.0.13 (#993)
• Fix Mistral transcribing non-English speech in English (#992)
• Fix Deepgram crash on malformed custom base URL (#989)
• Bump temperature-aware plugin versions (#991)
• Mistral AI plugin: add Voxtral Small and temperature control (#986)
• Fix per-workflow temperature override on LLM provider plugins (#987)

Maintenance release v1.0.5-daily.20260724

Other Changes

• Fix clamshell system-default microphone fallback (#984)

Other Changes

• Bound portable validator test process
• Test portable package validation behavior
• Fix portable user data migration across volumes
• Strengthen microphone lifecycle regression test
• Release microphone capture between dictations

New Features

• fetch model list from /v1/models with 24h cache (#970)

Other Changes

• Stabilize Gemma preparation timeout test (#982)
• Support explicit workflow dictation in the local API (#981)
• Fix Bluetooth system-default recording startup (#964)
• Fix duplicate Firefox text insertion (#979)

Other Changes

• Support explicit workflow dictation in the local API (#319)

Other Changes

• Remove legacy dev training capture (#971)
• Add Improve TypeWhisper contribution plugin (#969)
• Use bundle-aware notarization verification (#967)
• Notarize plugin releases (#966)

Maintenance release v1.0.5-daily.20260721

Maintenance release v1.0.5-daily.20260720

Bug Fixes

• Replaces the unavailable native Sign in with Apple entitlement with browser-based Apple authentication.
• Uses target-specific Developer ID signing so the widget no longer inherits the main app's entitlements.
• Temporarily disables automatic iCloud sync while Apple restores the production App ID. Cloud Folder sync remains available, and existing iCloud data is not deleted.

Other Changes

• Address Script Runner review feedback
• Fix Script Runner editor persistence
• Bump actions/setup-dotnet from 5 to 6 in the github-actions group

Other Changes

• Release AssemblyAIPlugin v1.0.14 (#941)
• Fix AssemblyAI file-transcription diarization routing (#939)
• Fix scroll lag elsewhere in the app while a Recorder session is active (#934)

Maintenance release v1.0.5-daily.20260718

Other Changes

• Add missing description to Filler Words plugin manifest (#931)
• Bump ElevenLabs plugin to 1.0.9 (#930)
• Add ElevenLabs REST-only transcription mode (#928)
• Fix glitchy sidebar collapse animation in Settings (#918)
• Manage stale external plugin bundles (#922)
• Fix Apple Speech regional model selection (#921)
• Show canonical release tags in About (#917)
• Add close button to History detail panel (#915)
• Fix recorder Stop freeze with bounded streaming finalization (#914)
• Feat: Added Statistics tab (#909)

Other Changes

• Fix bare modifier main hotkeys
• Simplify plugin window lifetime test
• Move plugin settings into modal windows

New Features

• select data-residency region (US/EU/JP) with auto-detect

Bug Fixes

• disable API key box during region auto-detect probe
• bound region auto-detect probes and lock region UI during test

Other Changes

• Preserve chat helper binary compatibility
• Hide Groq Qwen reasoning output
• Update GraniteSpeech PyTorch dependency
• Enable autostart for new installations
• Harden file transcription test isolation
• Add file transcription regression coverage
• Bump Live Transcript plugin to 1.0.3
• Prevent duplicate transcript entrance animation
• Address correction trainer review feedback
• Stabilize live transcript and recording overlays
• Add guided correction trainer
• Address settings automation review feedback
• Fix dictionary pack state notifications
• Refine recording overlays and live transcript
• Add settings UI automation coverage
• Simplify dictionary reset actions
• Persist correction provenance and add safe dictionary resets
• Retry restored code quality service
• Retry transient code quality check
• Improve correction group accessibility
• Refine correction group layout
• Group dictionary corrections by replacement
• Handle invalid diagnostics roots consistently
• Recover missing correction learning target window
• Refresh localization resources on build
• Improve correction learning visibility
• Preserve external HTTP timeout behavior
• Handle stalled plugin downloads
• Add privacy-friendly purchase attribution (#287)
• Strengthen hybrid modifier regression test
• Fix hybrid modifier hold behavior
• Require double Escape to cancel dictation
• Address review feedback
• Add ordered language hints
• Address review feedback
• Preserve hotkey recorder clear action
• Preserve workflow provider during refresh
• Protect user data across release channels
• Refine Windows hotkey handling
• Allow workflows without post-processing
• Serve plugins from registry origin
• Publish plugin package hashes
• Unsubscribe wizard close handler
• Clarify Parakeet plugin updates
• Fix wizard lifetime when settings close
• Address Store packaging review feedback
• Add Microsoft Store packaging workflow
• Address microphone priority review feedback
• Stabilize microphone device priority selection
• Keep uninstall audio recovery non-interactive
• Address recording protection review feedback
• Protect user recordings during uninstall
• Address review: follow default-endpoint changes and honor explicit preview device
• Follow the system default capture device in automatic microphone mode
• await background cleanup in the two auto-language tests
• run best-effort cleanup off the transcription critical path
• use current stt-async-v5 model
• poll async status with adaptive backoff

Other Changes

• Rename Recording settings tab to Dictation (#910)
• Preserve file transcription language selection (#913)
• Fix managed window restoration after login (#908)
• Make recording cancel confirmation optional
• Add direct Recorder retranscription (#903)
• Apply dictionary corrections to file transcriptions (#901)
• Bump Obsidian plugin to 1.0.7 (#900)
• Add configurable Obsidian daily note append format (#898)

Other Changes

• Preserve chat helper binary compatibility
• Hide Groq Qwen reasoning output
• Update GraniteSpeech PyTorch dependency
• Enable autostart for new installations

Other Changes

• Omit app-specific metadata from generic daily Obsidian notes (#892)
• Fix clamshell microphone failover (#890)
• Verify public appcast publication (#896)
• Update Sparkle to 2.9.4 (#894)
• Keep login launches windowless (#883)
• Keep unavailable webhook workflows visible (#889)
• Improve webhook settings layout (#886)
• Fix webhook editor presentation (#882)

Other Changes

• Harden file transcription test isolation
• Add file transcription regression coverage

Other Changes

• Fix WhisperKit slow model compilation handling (#880) (#881)
• Add a guided microphone correction trainer (#879)
• Improve correction learning reliability and visibility (#878)
• Group dictionary correction variants (#876)
• Add safe dictionary reset actions (#875)
• Improve search field visibility (#874)
• Add dictionary search (#873)

Other Changes

• Bump Live Transcript plugin to 1.0.3
• Prevent duplicate transcript entrance animation
• Address correction trainer review feedback
• Stabilize live transcript and recording overlays
• Add guided correction trainer
• Address settings automation review feedback
• Fix dictionary pack state notifications
• Refine recording overlays and live transcript
• Add settings UI automation coverage
• Simplify dictionary reset actions
• Persist correction provenance and add safe dictionary resets
• Retry restored code quality service
• Retry transient code quality check
• Improve correction group accessibility
• Refine correction group layout
• Group dictionary corrections by replacement
• Handle invalid diagnostics roots consistently
• Recover missing correction learning target window
• Refresh localization resources on build
• Improve correction learning visibility
• Preserve external HTTP timeout behavior
• Handle stalled plugin downloads

Other Changes

• Fix webhook creation flow (#872)
• Add privacy-friendly purchase attribution (#864)

New Features

• select data-residency region (US/EU/JP) with auto-detect

Bug Fixes

• disable API key box during region auto-detect probe
• bound region auto-detect probes and lock region UI during test

Other Changes

• Add privacy-friendly purchase attribution (#287)
• Strengthen hybrid modifier regression test
• Fix hybrid modifier hold behavior
• Require double Escape to cancel dictation
• Address review feedback
• Add ordered language hints
• Address review feedback
• Preserve hotkey recorder clear action
• Preserve workflow provider during refresh
• Protect user data across release channels
• Refine Windows hotkey handling
• Allow workflows without post-processing
• await background cleanup in the two auto-language tests
• run best-effort cleanup off the transcription critical path
• use current stt-async-v5 model
• poll async status with adaptive backoff

Other Changes

• Serve plugins from registry origin
• Publish plugin package hashes

Bug Fixes

• resolve active-screen indicator coordinate spaces (#854) (#858)

Other Changes

• Fix trailing space after dictation (#863)
• Fix CoreAudio HAL teardown race (#860)
• Fix notch indicator dismissal race (#861)
• Add global LLM fallback priority list (#859)

Other Changes

• Unsubscribe wizard close handler
• Clarify Parakeet plugin updates
• Fix wizard lifetime when settings close

Bug Fixes

• restore filler dictionary corrections (#855)

Other Changes

• Address Store packaging review feedback
• Add Microsoft Store packaging workflow

New Features

• add microphone priority list (#845)

Other Changes

• Require restart after loaded plugin updates (#849)
• Fix recorder Apple Speech model restore (#851)
• Fix Gemma 4 4-bit MLX loading (#852)
• Fix Gemma 4 model loading

Other Changes

• Address microphone priority review feedback
• Stabilize microphone device priority selection
• Keep uninstall audio recovery non-interactive
• Address recording protection review feedback
• Protect user recordings during uninstall
• Address review: follow default-endpoint changes and honor explicit preview device
• Follow the system default capture device in automatic microphone mode

Other Changes

• Prepare 1.0.1 release notes
• Fix sherpa-onnx CUDA runtime aliasing
• Address sherpa-onnx runtime review feedback
• Fix sherpa-onnx native runtime loading
• Stop installing plugins by default

TypeWhisper v1.0.1

TypeWhisper 1.0.1 is a stable Windows maintenance release. It focuses on local speech-engine reliability, cleaner plugin startup behavior, and development dashboard tooling for support and QA workflows.

Highlights

• Promoted the latest 1.0.1 maintenance fixes to the stable Velopack channel.
• Improved Sherpa-ONNX native runtime loading for local transcription setups.
• Kept optional plugins opt-in so a fresh app install starts with only bundled capabilities active.

Improvements

• Added development dashboard seed controls to make support, QA, and demo data scenarios easier to reproduce.
• Refined development seed busy-state handling and test cleanup.
• Stopped installing marketplace plugins by default during first-run setup.

Fixes

• Fixed Sherpa-ONNX native runtime probing so required runtime DLLs are resolved from the plugin package.
• Fixed Sherpa-ONNX CUDA runtime aliasing for systems that use accelerated local transcription.
• Addressed review feedback around Sherpa-ONNX runtime loading behavior.

Validation Notes

• Verify stable Velopack channels win-x64 and win-arm64.
• Confirm x64 and ARM64 installers, portable ZIPs, full nupkg packages, RELEASES files, and JSON manifests are present without -rc or -daily suffixes.
• Check installer Authenticode status explicitly before announcing release quality.

Maintenance release v1.0.1-daily.20260707

New Features

• persist aggregate usage statistics

Bug Fixes

• make correction learning conservative (#842)
• remove incorrect fullscreen suppression for notch indicator

Other Changes

• Fix WhisperKit restore without loaded model marker
• Fix WhisperKit restore wait for long model loads

Other Changes

• Refine development seed busy state
• Address development seed status feedback
• Tighten development seed test cleanup
• Address development seed review feedback
• Add development dashboard seed controls

Other Changes

• Add iOS platform fields to issue templates (#838)
• Fix Qwen3 downloaded model restore (#828)

Maintenance release v1.0.1-daily.20260705

Other Changes

• Fix WhisperKit restore wait for long model loads

Other Changes

• support localized screenshot automation (#824)

Other Changes

• Add 1.0 stable release notes
• Add Windows screenshot assets (#257)
• Fix bundled plugin uninstall

TypeWhisper v1.0.0

TypeWhisper 1.0.0 is the stable Windows 1.0 release. It brings the 1.0 release candidate work to the stable update channel with update reliability, plugin lifecycle fixes, target-app learning improvements, and the Windows 1.0 screenshot set.

Highlights

• Promoted the Windows 1.0 release line from release candidate to the stable Velopack channel.
• Kept the stable release focused on reliability, update behavior, plugin lifecycle, and release polish.
• Added the Windows 1.0 screenshot set for the current app surfaces.

Improvements

• Improved update-channel behavior for explicit stable, release candidate, and daily channel selections.
• Improved bundled plugin uninstall handling so app-bundled plugin directories are removed consistently.
• Improved target-app autocorrection learning for Electron-based apps.
• Included plugin script files in release packages and refreshed bundled plugin compatibility for the 1.0 line.

Fixes

• Fixed bundled plugins returning after restart after uninstall.
• Fixed daily release version-base resolution after RC/stable tags.
• Fixed Groq recorder transcription on systems without Media Foundation AAC by falling back to WAV upload.
• Resolved Granite Speech package audit issues for release packaging.

Validation Notes

• Verify stable Velopack channels win-x64 and win-arm64.
• Confirm x64 and ARM64 installers, portable ZIPs, full nupkg packages, RELEASES files, and JSON manifests are present without -rc or -daily suffixes.
• Check installer Authenticode status explicitly before announcing release quality.

Bug Fixes

• macOS Secure Input hotkey handling (#816)
• lazy-load local models when auto-unload is active (#817)

Other Changes

• Add Soniox live WebSocket transcription (#818)
• prepare 1.6 release line
• refresh README screenshots for 1.5 (#822)
• prepare 1.5.0 stable release (#821)
• Fix Parakeet vocabulary download repair (#820)
• Fix fullscreen top overlay menu bar strip (#814)
• Restore non-Control hybrid modifier taps (#813)
• Fix compressed M4A upload finalization (#812)
• Surface recorder final transcription failures (#810)
• Fix fullscreen indicator menu bar strip (#809)
• Fix delayed Hybrid hotkey toggle behavior (#806)

Other Changes

• Fix bundled plugin uninstall

Other Changes

• Allow preview channel update downgrades
• Address release workflow review feedback
• Fix daily release version base
• Verify plugin uninstall marker cleanup
• Fail closed on stale plugin uninstall markers
• Make plugin uninstall cleanup fail closed
• Clear stale plugin uninstall markers
• Fix plugin uninstall pending restart
• Address review findings for target-app learning
• Fix Electron target-app correction learning
• Include plugin scripts in release packages
• Resolve Granite Speech PyTorch alert

TypeWhisper 1.5.0 is the stable 1.5 macOS release. It brings app-aware dictation insertion, virtual audio input support, broader number normalization, expanded bundled speech providers, local-model memory controls, dictionary-learning improvements, and a focused reliability pass across hotkeys, workflows, plugins, model handling, and release metadata.

Highlights

• Added app-aware smart insertion so dictated text better respects surrounding text, sentence position, trailing spaces, terminal paste behavior, and target-app context.
• Added virtual audio input device support and hardened media pause/resume behavior, recording start feedback, mouse-button shortcuts, and fullscreen indicator handling.
• Expanded number normalization across generic transcription output, multilingual number words, Dutch number words, English ordinals, English digit sequences, and French decimal phrases.
• Added and refreshed bundled speech and AI providers, including Gemini speech transcription, Cartesia speech transcription, Sber SaluteSpeech, OpenRouter speech-to-text, Reson8, Mistral AI, OpenAI-compatible profiles, Soniox regions and TTS, and updated cloud ASR providers.
• Added Japanese localization and dictation support, ordered language hints, recent transcriptions in the workflow palette, source progress for file transcription, recorder-specific engine overrides, and a short-dictation workflow AI-skip setting.
• Added local MLX memory-footprint controls, idle local-model auto-unload behavior, and recovery for stalled Gemma 4 model downloads.
• Added pro transcription fallback, auto-learned dictionary corrections, per-term dictionary CTC tuning plumbing, and tighter target-app correction learning.

Reliability and Fixes

• Fixed delayed Hybrid hotkey behavior, restored non-Control hybrid modifier taps, improved global push-to-talk capture, aligned Pages workflow hotkeys with palette behavior, added menu-based dictation pause, and required confirmation before Esc cancels dictation.
• Fixed fullscreen indicator menu-bar strip issues and the top overlay menu-bar strip.
• Fixed Groq and cloud ASR compressed M4A upload handling, including a WAV fallback for incomplete M4A finalization.
• Fixed Soniox async file transcription routing, region persistence, and realtime model selection.
• Fixed OpenAI Compatible GPT-5 token parameter handling, host SDK compatibility, and configurable request-timeout behavior.
• Fixed plugin host compatibility metadata, raised cloud ASR plugin host floors to TypeWhisper 1.5 where required, and prevented plugin releases from taking over the repository-level GitHub Latest marker.
• Fixed TaskForge preserve-clipboard insertion fallback, dictionary scroll crashes, event tap teardown, FaceTime built-in microphone capture, plugin uninstall keychain cleanup, and development build cleanup scope.
• Fixed Parakeet v2/v3 model setup by repairing missing vocabulary downloads before model loading.
• Improved Japanese dictation post-processing and settings localization, Latin word replacement boundaries, terminal clipboard restore verification, and recorder final transcription failure surfacing.

Developer and Distribution Notes

• Stable 1.5.0 builds use the default Sparkle channel and require macOS 14.0 or later.
• Release candidates and daily builds remain on their dedicated Sparkle channels and do not update Homebrew.
• The final stable tag publishes DMG and ZIP assets, updates the stable Sparkle appcast entry, triggers the website release dispatch, and updates the Homebrew cask.
• The 1.5 plugin line uses the community-capable registry feed and keeps host compatibility metadata aligned with the bundled plugin SDK.

Other Changes

• Address release workflow review feedback
• Fix daily release version base
• Verify plugin uninstall marker cleanup
• Fail closed on stale plugin uninstall markers
• Make plugin uninstall cleanup fail closed
• Clear stale plugin uninstall markers
• Fix plugin uninstall pending restart
• Address review findings for target-app learning
• Fix Electron target-app correction learning
• Include plugin scripts in release packages
• Resolve Granite Speech PyTorch alert

Bug Fixes

• lazy-load local models when auto-unload is active (#817)

Other Changes

• Fix fullscreen top overlay menu bar strip (#814)
• Restore non-Control hybrid modifier taps (#813)
• Fix compressed M4A upload finalization (#812)
• Surface recorder final transcription failures (#810)
• Fix fullscreen indicator menu bar strip (#809)
• Fix delayed Hybrid hotkey toggle behavior (#806)

Other Changes

• Address review findings for target-app learning
• Fix Electron target-app correction learning
• Include plugin scripts in release packages
• Resolve Granite Speech PyTorch alert

Other Changes

• Fix fullscreen top overlay menu bar strip (#814)
• Restore non-Control hybrid modifier taps (#813)
• Fix compressed M4A upload finalization (#812)
• Surface recorder final transcription failures (#810)
• Fix fullscreen indicator menu bar strip (#809)
• Fix delayed Hybrid hotkey toggle behavior (#806)

Maintenance release v0.8.5-daily.20260630

Other Changes

• Fix compressed M4A upload finalization (#812)
• Surface recorder final transcription failures (#810)
• Fix fullscreen indicator menu bar strip (#809)
• Fix delayed Hybrid hotkey toggle behavior (#806)

Maintenance release v0.8.5-daily.20260629

TypeWhisper v1.0.0-rc1

TypeWhisper 1.0.0-rc1 is the first release candidate for the Windows 1.0 release. It focuses on release quality, update reliability, plugin compatibility, and the stability fixes needed before the stable 1.0 tag.

Release Candidate Focus

• Prepared the Windows app for the 1.0.0-rc1 release-candidate channel.
• Kept the RC scope focused on blocker fixes, compatibility, documentation, and QA rather than new workflow surfaces.
• Preserved the stable 1.0 path for a short RC soak before publishing v1.0.0.

Improvements

• Loaded bundled app plugins from the installed application directory alongside marketplace and user-installed plugins.
• Preferred marketplace or user-installed plugin copies when they share an id with a bundled plugin.
• Aligned OpenAI and Supertonic TTS plugin host compatibility with the Windows 1.0 release line.
• Documented the RC validation focus for Windows 10 startup, plugin loading, update channels, and local acceleration diagnostics.

Fixes

• Fixed Groq recorder transcription on Windows systems where Media Foundation AAC encoding is unavailable by falling back to WAV upload.
• Preserved cancellation behavior for Groq transcription while avoiding hard failures for AAC encoder availability issues.

Known RC Packaging Note

• The v1.0.0-rc1 Windows Setup.exe assets are currently unsigned. Windows may show SmartScreen or publisher warnings during installation.
• Code signing remains a stable v1.0.0 release gate unless the release communication is updated again.

RC Validation Notes

• Check startup responsiveness on Windows 10 22H2 systems with virtual audio devices such as Voicemeeter.
• Confirm upgrade behavior from v0.8.4 to the RC channel and fresh portable RC launches.
• Verify OpenAI and Supertonic TTS visibility in the plugin marketplace on a 1.0.0-rc1 host.
• Verify Velopack RC-channel assets and x64/ARM64 package completeness.

TypeWhisper v1.5.0-rc2 refreshes the 1.5 release-candidate line after rc1 with tighter local-model memory controls, broader provider reliability fixes, dictionary-learning improvements, and another pass over hotkeys, workflows, plugins, and release infrastructure.

Highlights

• Added local MLX memory-footprint controls and improved recovery for stalled Gemma 4 model downloads.
• Added the pro transcription fallback and surfaced auto-learned dictionary corrections so app-specific cleanup can be inspected and reused.
• Added per-term dictionary CTC tuning plumbing and tightened when target-app corrections are learned.
• Refined push-to-talk, Hybrid modifier hold activation, Pages workflow hotkeys, menu-based dictation pause, and automatic workflow output format resolution.
• Added and updated provider paths across Mistral AI, MemPalace, Soniox regions and TTS, OpenAI-compatible thinking and token behavior, cloud ASR providers, and bundled marketplace metadata.

Reliability and Fixes

• Fixed Groq M4A upload fallback handling and compressed cloud ASR uploads.
• Raised cloud ASR plugin host floors to TypeWhisper 1.5 and restored plugin host compatibility for older release lines where needed.
• Fixed TaskForge preserve-clipboard insertion fallback, dictionary scroll crashes, idle local-model auto-unload, event tap teardown, and FaceTime built-in microphone capture.
• Fixed OpenAI Compatible GPT-5 token parameter handling and host SDK compatibility.
• Fixed Soniox region persistence, async file transcription routing, and realtime model selection.
• Improved Japanese dictation post-processing and settings localization, Latin word replacement boundaries, and French decimal normalization.
• Cleaned up plugin keychain data on uninstall and kept development build cleanup scoped to the TypeWhisper-Dev build.

Testing Focus

• Verify local MLX memory controls, idle unload behavior, and Gemma 4 stalled-download recovery.
• Verify pro transcription fallback, dictionary correction learning, per-term CTC tuning, and dictionary scroll behavior.
• Verify global push-to-talk, Hybrid modifier hold, menu pause, Pages workflow hotkeys, workflow output resolution, and Esc confirmation behavior.
• Smoke-test Groq, cloud ASR providers, Mistral AI, MemPalace, Soniox STT/TTS, and OpenAI-compatible profile paths.
• Verify TaskForge preserve-clipboard insertion fallback, FaceTime mic capture, event tap teardown, and plugin uninstall cleanup.
• Confirm v1.5.0-rc2 publishes on the release-candidate Sparkle channel, remains a GitHub prerelease, and does not update Homebrew or the stable website release path.

New Features

• surface auto-learned dictionary corrections (#795)
• pause dictation hotkeys from menu (#775)
• add Soniox regions and TTS (#748)
• clarify recorder transcription settings (#731)

Bug Fixes

• recover stalled Gemma 4 model downloads (#799)
• persist Soniox region selection (#791)
• invalidate event tap Mach port and run loop source on teardown (#779)
• improve global push-to-talk hotkey capture (#778)
• learn target-app corrections only after commit (#770)
• restore plugin host compatibility (#768)
• align Pages workflow hotkeys with palette behavior (#759)
• export text-only file subtitles (#758)
• cleanup plugin keychain data on uninstall (#756)
• restore built-in mic capture during FaceTime (#755)
• localize Mistral plugin settings (#746)
• normalize French point decimals (#728)

Other Changes

• Fix Groq M4A upload fallback (#802)
• Delay Hybrid modifier hold activation (#793)
• Add PR preflight and cancel stale CI runs (#798)
• Keep dev build cleanup scoped to TypeWhisper-Dev (#797)
• Fix preserve-clipboard insertion fallback for TaskForge (#792)
• Set cloud ASR plugin host floor (#796)
• Compress cloud ASR uploads (#794)
• Add pro transcription fallback (#790)
• Fix idle local model auto-unload (#789)
• Fix dictionary scroll crash
• bump actions/checkout from 6 to 7 (#781)
• Make OpenAI compatible token parameter fallback generic (#777)
• Fix OpenAI compatible GPT-5 token parameter (#776)
• Add per-term dictionary CTC tuning plumbing (#642)
• cover Latin word replacement boundaries (#771)
• Fix dictation language visibility and release guard (#769)
• codebase audit fixes and optimizations (#765)
• Fix OpenAI compatible plugin host SDK compatibility (#764)
• Add OpenAI-compatible thinking mode toggle (#763)
• Fix Qwen3 French trailing oui cleanup (#753)
• wire MemPalace community release (#754)
• Add MemPalace memory plugin (community submission) (#588)
• Learn target-app correction edits (#752)
• Improve Japanese dictation post-processing (#749)
• Improve Japanese settings localization (#750)
• Allow trusted contributors through PR Guard (#751)
• update Mistral AI plugin details URL and version
• add Mistral Xcode release target (#745)
• wire Mistral plugin release (#744)
• Add native Mistral AI plugin (#742)
• Route Soniox file transcription through async model (#739)
• Update Soniox realtime model to v5 (#736)
• Add automatic workflow output format resolution (#733)
• Require confirmation before Esc cancels dictation (#722)

Other Changes

• Fix live preview toggle handling
• Stabilize correction learning cleanup
• Address remaining review feedback
• Tighten correction learning review fixes
• Consolidate nonfatal exception filters
• Address target app learning review feedback
• Fix startup audio warmup performance
• Add premium target app autocorrection learning
• Bump actions/checkout from 6 to 7 in the github-actions group

New Features

• pause dictation hotkeys from menu (#775)
• add Soniox regions and TTS (#748)
• clarify recorder transcription settings (#731)

Bug Fixes

• invalidate event tap Mach port and run loop source on teardown (#779)
• improve global push-to-talk hotkey capture (#778)
• learn target-app corrections only after commit (#770)
• restore plugin host compatibility (#768)
• align Pages workflow hotkeys with palette behavior (#759)
• export text-only file subtitles (#758)
• cleanup plugin keychain data on uninstall (#756)
• restore built-in mic capture during FaceTime (#755)
• localize Mistral plugin settings (#746)
• normalize French point decimals (#728)

Other Changes

• Add pro transcription fallback (#790)
• Fix idle local model auto-unload (#789)
• Fix dictionary scroll crash
• bump actions/checkout from 6 to 7 (#781)
• Make OpenAI compatible token parameter fallback generic (#777)
• Fix OpenAI compatible GPT-5 token parameter (#776)
• Add per-term dictionary CTC tuning plumbing (#642)
• cover Latin word replacement boundaries (#771)
• Fix dictation language visibility and release guard (#769)
• codebase audit fixes and optimizations (#765)
• Fix OpenAI compatible plugin host SDK compatibility (#764)
• Add OpenAI-compatible thinking mode toggle (#763)
• Fix Qwen3 French trailing oui cleanup (#753)
• wire MemPalace community release (#754)
• Add MemPalace memory plugin (community submission) (#588)
• Learn target-app correction edits (#752)
• Improve Japanese dictation post-processing (#749)
• Improve Japanese settings localization (#750)
• Allow trusted contributors through PR Guard (#751)
• update Mistral AI plugin details URL and version
• add Mistral Xcode release target (#745)
• wire Mistral plugin release (#744)
• Add native Mistral AI plugin (#742)
• Route Soniox file transcription through async model (#739)
• Update Soniox realtime model to v5 (#736)
• Add automatic workflow output format resolution (#733)
• Require confirmation before Esc cancels dictation (#722)

Maintenance release v0.8.5-daily.20260627

New Features

• pause dictation hotkeys from menu (#775)
• add Soniox regions and TTS (#748)
• clarify recorder transcription settings (#731)

Bug Fixes

• invalidate event tap Mach port and run loop source on teardown (#779)
• improve global push-to-talk hotkey capture (#778)
• learn target-app corrections only after commit (#770)
• restore plugin host compatibility (#768)
• align Pages workflow hotkeys with palette behavior (#759)
• export text-only file subtitles (#758)
• cleanup plugin keychain data on uninstall (#756)
• restore built-in mic capture during FaceTime (#755)
• localize Mistral plugin settings (#746)
• normalize French point decimals (#728)

Other Changes

• bump actions/checkout from 6 to 7 (#781)
• Make OpenAI compatible token parameter fallback generic (#777)
• Fix OpenAI compatible GPT-5 token parameter (#776)
• Add per-term dictionary CTC tuning plumbing (#642)
• cover Latin word replacement boundaries (#771)
• Fix dictation language visibility and release guard (#769)
• codebase audit fixes and optimizations (#765)
• Fix OpenAI compatible plugin host SDK compatibility (#764)
• Add OpenAI-compatible thinking mode toggle (#763)
• Fix Qwen3 French trailing oui cleanup (#753)
• wire MemPalace community release (#754)
• Add MemPalace memory plugin (community submission) (#588)
• Learn target-app correction edits (#752)
• Improve Japanese dictation post-processing (#749)
• Improve Japanese settings localization (#750)
• Allow trusted contributors through PR Guard (#751)
• update Mistral AI plugin details URL and version
• add Mistral Xcode release target (#745)
• wire Mistral plugin release (#744)
• Add native Mistral AI plugin (#742)
• Route Soniox file transcription through async model (#739)
• Update Soniox realtime model to v5 (#736)
• Add automatic workflow output format resolution (#733)
• Require confirmation before Esc cancels dictation (#722)

Maintenance release v0.8.5-daily.20260626

Maintenance release v0.8.5-daily.20260625

New Features

• pause dictation hotkeys from menu (#775)
• add Soniox regions and TTS (#748)
• clarify recorder transcription settings (#731)

Bug Fixes

• improve global push-to-talk hotkey capture (#778)
• learn target-app corrections only after commit (#770)
• restore plugin host compatibility (#768)
• align Pages workflow hotkeys with palette behavior (#759)
• export text-only file subtitles (#758)
• cleanup plugin keychain data on uninstall (#756)
• restore built-in mic capture during FaceTime (#755)
• localize Mistral plugin settings (#746)
• normalize French point decimals (#728)

Other Changes

• bump actions/checkout from 6 to 7 (#781)
• Make OpenAI compatible token parameter fallback generic (#777)
• Fix OpenAI compatible GPT-5 token parameter (#776)
• Add per-term dictionary CTC tuning plumbing (#642)
• cover Latin word replacement boundaries (#771)
• Fix dictation language visibility and release guard (#769)
• codebase audit fixes and optimizations (#765)
• Fix OpenAI compatible plugin host SDK compatibility (#764)
• Add OpenAI-compatible thinking mode toggle (#763)
• Fix Qwen3 French trailing oui cleanup (#753)
• wire MemPalace community release (#754)
• Add MemPalace memory plugin (community submission) (#588)
• Learn target-app correction edits (#752)
• Improve Japanese dictation post-processing (#749)
• Improve Japanese settings localization (#750)
• Allow trusted contributors through PR Guard (#751)
• update Mistral AI plugin details URL and version
• add Mistral Xcode release target (#745)
• wire Mistral plugin release (#744)
• Add native Mistral AI plugin (#742)
• Route Soniox file transcription through async model (#739)
• Update Soniox realtime model to v5 (#736)
• Add automatic workflow output format resolution (#733)
• Require confirmation before Esc cancels dictation (#722)

New Features

• add Soniox regions and TTS (#748)
• clarify recorder transcription settings (#731)

Bug Fixes

• learn target-app corrections only after commit (#770)
• restore plugin host compatibility (#768)
• align Pages workflow hotkeys with palette behavior (#759)
• export text-only file subtitles (#758)
• cleanup plugin keychain data on uninstall (#756)
• restore built-in mic capture during FaceTime (#755)
• localize Mistral plugin settings (#746)
• normalize French point decimals (#728)

Other Changes

• Add per-term dictionary CTC tuning plumbing (#642)
• cover Latin word replacement boundaries (#771)
• Fix dictation language visibility and release guard (#769)
• codebase audit fixes and optimizations (#765)
• Fix OpenAI compatible plugin host SDK compatibility (#764)
• Add OpenAI-compatible thinking mode toggle (#763)
• Fix Qwen3 French trailing oui cleanup (#753)
• wire MemPalace community release (#754)
• Add MemPalace memory plugin (community submission) (#588)
• Learn target-app correction edits (#752)
• Improve Japanese dictation post-processing (#749)
• Improve Japanese settings localization (#750)
• Allow trusted contributors through PR Guard (#751)
• update Mistral AI plugin details URL and version
• add Mistral Xcode release target (#745)
• wire Mistral plugin release (#744)
• Add native Mistral AI plugin (#742)
• Route Soniox file transcription through async model (#739)
• Update Soniox realtime model to v5 (#736)
• Add automatic workflow output format resolution (#733)
• Require confirmation before Esc cancels dictation (#722)

Maintenance release v0.8.5-daily.20260624

New Features

• add Soniox regions and TTS (#748)
• clarify recorder transcription settings (#731)

Bug Fixes

• learn target-app corrections only after commit (#770)
• restore plugin host compatibility (#768)
• align Pages workflow hotkeys with palette behavior (#759)
• export text-only file subtitles (#758)
• cleanup plugin keychain data on uninstall (#756)
• restore built-in mic capture during FaceTime (#755)
• localize Mistral plugin settings (#746)
• normalize French point decimals (#728)

Other Changes

• Fix dictation language visibility and release guard (#769)
• codebase audit fixes and optimizations (#765)
• Fix OpenAI compatible plugin host SDK compatibility (#764)
• Add OpenAI-compatible thinking mode toggle (#763)
• Fix Qwen3 French trailing oui cleanup (#753)
• wire MemPalace community release (#754)
• Add MemPalace memory plugin (community submission) (#588)
• Learn target-app correction edits (#752)
• Improve Japanese dictation post-processing (#749)
• Improve Japanese settings localization (#750)
• Allow trusted contributors through PR Guard (#751)
• update Mistral AI plugin details URL and version
• add Mistral Xcode release target (#745)
• wire Mistral plugin release (#744)
• Add native Mistral AI plugin (#742)
• Route Soniox file transcription through async model (#739)
• Update Soniox realtime model to v5 (#736)
• Add automatic workflow output format resolution (#733)
• Require confirmation before Esc cancels dictation (#722)

Maintenance release v0.8.5-daily.20260623

New Features

• add Soniox regions and TTS (#748)
• clarify recorder transcription settings (#731)

Bug Fixes

• restore plugin host compatibility (#768)
• align Pages workflow hotkeys with palette behavior (#759)
• export text-only file subtitles (#758)
• cleanup plugin keychain data on uninstall (#756)
• restore built-in mic capture during FaceTime (#755)
• localize Mistral plugin settings (#746)
• normalize French point decimals (#728)

Other Changes

• codebase audit fixes and optimizations (#765)
• Fix OpenAI compatible plugin host SDK compatibility (#764)
• Add OpenAI-compatible thinking mode toggle (#763)
• Fix Qwen3 French trailing oui cleanup (#753)
• wire MemPalace community release (#754)
• Add MemPalace memory plugin (community submission) (#588)
• Learn target-app correction edits (#752)
• Improve Japanese dictation post-processing (#749)
• Improve Japanese settings localization (#750)
• Allow trusted contributors through PR Guard (#751)
• update Mistral AI plugin details URL and version
• add Mistral Xcode release target (#745)
• wire Mistral plugin release (#744)
• Add native Mistral AI plugin (#742)
• Route Soniox file transcription through async model (#739)
• Update Soniox realtime model to v5 (#736)
• Add automatic workflow output format resolution (#733)
• Require confirmation before Esc cancels dictation (#722)

Maintenance release v0.8.5-daily.20260622

New Features

• add Soniox regions and TTS (#748)
• clarify recorder transcription settings (#731)

Bug Fixes

• align Pages workflow hotkeys with palette behavior (#759)
• export text-only file subtitles (#758)
• cleanup plugin keychain data on uninstall (#756)
• restore built-in mic capture during FaceTime (#755)
• localize Mistral plugin settings (#746)
• normalize French point decimals (#728)

Other Changes

• Fix Qwen3 French trailing oui cleanup (#753)
• wire MemPalace community release (#754)
• Add MemPalace memory plugin (community submission) (#588)
• Learn target-app correction edits (#752)
• Improve Japanese dictation post-processing (#749)
• Improve Japanese settings localization (#750)
• Allow trusted contributors through PR Guard (#751)
• update Mistral AI plugin details URL and version
• add Mistral Xcode release target (#745)
• wire Mistral plugin release (#744)
• Add native Mistral AI plugin (#742)
• Route Soniox file transcription through async model (#739)
• Update Soniox realtime model to v5 (#736)
• Add automatic workflow output format resolution (#733)
• Require confirmation before Esc cancels dictation (#722)

Maintenance release v0.8.5-daily.20260621

New Features

• add Soniox regions and TTS (#748)
• clarify recorder transcription settings (#731)

Bug Fixes

• cleanup plugin keychain data on uninstall (#756)
• restore built-in mic capture during FaceTime (#755)
• localize Mistral plugin settings (#746)
• normalize French point decimals (#728)

Other Changes

• Fix Qwen3 French trailing oui cleanup (#753)
• wire MemPalace community release (#754)
• Add MemPalace memory plugin (community submission) (#588)
• Learn target-app correction edits (#752)
• Improve Japanese dictation post-processing (#749)
• Improve Japanese settings localization (#750)
• Allow trusted contributors through PR Guard (#751)
• update Mistral AI plugin details URL and version
• add Mistral Xcode release target (#745)
• wire Mistral plugin release (#744)
• Add native Mistral AI plugin (#742)
• Route Soniox file transcription through async model (#739)
• Update Soniox realtime model to v5 (#736)
• Add automatic workflow output format resolution (#733)
• Require confirmation before Esc cancels dictation (#722)

Maintenance release v0.8.5-daily.20260620

New Features

• add Soniox regions and TTS (#748)
• clarify recorder transcription settings (#731)

Bug Fixes

• localize Mistral plugin settings (#746)
• normalize French point decimals (#728)

Other Changes

• update Mistral AI plugin details URL and version
• add Mistral Xcode release target (#745)
• wire Mistral plugin release (#744)
• Add native Mistral AI plugin (#742)
• Route Soniox file transcription through async model (#739)
• Update Soniox realtime model to v5 (#736)
• Add automatic workflow output format resolution (#733)
• Require confirmation before Esc cancels dictation (#722)

Maintenance release v0.8.5-daily.20260619

New Features

• clarify recorder transcription settings (#731)

Bug Fixes

• normalize French point decimals (#728)

Other Changes

• Route Soniox file transcription through async model (#739)
• Update Soniox realtime model to v5 (#736)
• Add automatic workflow output format resolution (#733)
• Require confirmation before Esc cancels dictation (#722)

Maintenance release v0.8.5-daily.20260618

New Features

• clarify recorder transcription settings (#731)

Bug Fixes

• normalize French point decimals (#728)

Other Changes

• Add automatic workflow output format resolution (#733)
• Require confirmation before Esc cancels dictation (#722)

Maintenance release v0.8.5-daily.20260617

New Features

• clarify recorder transcription settings (#731)

Bug Fixes

• normalize French point decimals (#728)

Other Changes

• Require confirmation before Esc cancels dictation (#722)

Maintenance release v0.8.5-daily.20260616

Other Changes

• Add recorder system audio parity (#233)
• Fix Groq recorder long transcription
• Address plugin update review feedback
• Fix plugin update state handling
• Add Chinese spoken language option
• Fix CJK dictionary corrections
• Fix Python package audit for unresolved Torch advisory
• Fix overlay recovery after display changes
• Release Live Transcript plugin 1.0.2
• Handle stale provider profile selections
• Add OpenAI-compatible provider profiles
• Add number normalization parity
• Address static analysis review findings
• Address review feedback for translation storage flow
• Address review feedback for storage paths
• Address review feedback for asset paths
• Add quick translation mode and model storage controls
• Add file transcription queue clearing
• Document public production APIs
• Add multiple workflow hotkeys
• Release Soniox plugin 1.0.3
• Rework license management flows
• Group Soniox transcript tokens for subtitles
• Add Premium Cloud Folder Sync
• Add AMD acceleration for whisper.cpp
• Require restart after CUDA runtime installation

Bug Fixes

• normalize French point decimals (#728)

Other Changes

• Require confirmation before Esc cancels dictation (#722)

Other Changes

• Add recorder system audio parity (#233)

TypeWhisper 1.5.0-rc1 opens the 1.5 release-candidate line with app-aware dictation insertion, virtual audio input support, broader number normalization, new speech providers, and a focused reliability pass across plugins, model handling, workflows, and release metadata.

Highlights

• Added app-aware smart insertion so dictation output better respects the surrounding text, sentence position, trailing spaces, terminal paste behavior, and target-app context.
• Added virtual audio input device support and hardened media pause/resume handling, recording start feedback, mouse-button shortcuts, and Safari/fullscreen indicator behavior.
• Expanded number normalization across generic transcription output, multilingual number words, Dutch number words, English ordinals, and English digit sequences.
• Added new bundled speech providers and plugin releases, including Gemini speech transcription, Cartesia speech transcription, Sber SaluteSpeech, OpenRouter speech-to-text, Reson8, OpenAI-compatible profiles, and the experimental SenseVoice line before its removal from the bundled set.
• Added Japanese localization and dictation support, ordered language hints, recent transcriptions in the workflow palette, source progress for file transcription, recorder-specific engine overrides, and a short-dictation workflow AI-skip setting.
• Added commercial Cloud Folder Sync, the standalone setup wizard, README screenshot automation, plugin update-state diagnostics, repair actions, and clearer issue-template diagnostics guidance.

Reliability and Fixes

• Fixed smart insertion mid-sentence edge cases, terminal clipboard restore races, trailing-space insertion, middle-mouse pass-through, indicator visibility over fullscreen apps, and overlay live transcript preview expansion.
• Improved long file transcription progress, Groq uploads, Apple Speech first-use model selection, selected Apple Speech model restoration, custom workflow fine-tuning prompts, and workflow prompt casing diagnostics.
• Hardened cloud LLM behavior by honoring plugin model selection, parsing Gemini array errors, and avoiding legacy global model poisoning.
• Updated Soniox async transcription to model v5 and disabled dictionary-term prompts for Qwen3 ASR where they do not apply.
• Treated Reson8 as a single-language engine, added configurable LLM request timeout support to the OpenAI Compatible plugin, and required TypeWhisper 1.5 for the Gemini plugin.
• Fixed Cartesia plugin settings and prevented plugin releases from taking over the repository-level GitHub "latest" marker.

Testing Focus

• Verify app-aware insertion in plain text, mid-sentence, terminal, and rich-text targets.
• Verify virtual audio input recording, media pause/resume, mouse-button shortcuts, and indicator behavior in Safari fullscreen and other fullscreen apps.
• Verify number normalization for multilingual number words, Dutch, English ordinals, English digit sequences, and API/CLI dictionary corrections.
• Smoke-test Gemini, Cartesia, Sber SaluteSpeech, OpenRouter STT, Reson8, and OpenAI-compatible profile setup paths.
• Verify file transcription progress, recent-transcription workflow palette behavior, ordered language hints, Japanese dictation, and short-dictation AI-skip workflows.
• Confirm v1.5.0-rc1 publishes on the release-candidate Sparkle channel, remains a GitHub prerelease, and does not update Homebrew or the stable website release path.

Other Changes

• Require TypeWhisper 1.5 for Gemini plugin
• Add Gemini speech transcription
• Prevent plugin releases from becoming latest
• Fix Cartesia plugin settings
• Add virtual audio input device support (#712)

Other Changes

• Fix Groq recorder long transcription
• Address plugin update review feedback
• Fix plugin update state handling
• Add Chinese spoken language option

Other Changes

• Add Cartesia speech plugin (#713)
• Add Sber SaluteSpeech transcription plugin

Other Changes

• Fix CJK dictionary corrections
• Fix Python package audit for unresolved Torch advisory

Other Changes

• Update Soniox async model to v5 (#703)
• Fix cloud LLM 404: honor plugin model selection, parse Gemini array errors, stop poisoning legacy global (#696)
• Localize plugin settings and dev sync (#692)
• Add English digit-sequence number normalization (#693)
• Add source progress for file transcription (#702)

Maintenance release v0.8.4-daily.20260612

Other Changes

• Fix smart insertion mid-sentence edge cases (#698)

Maintenance release v0.8.4-daily.20260611

Other Changes

• Add app-aware smart insertion (#691)
• Add Japanese localization and dictation support (#684)
• Harden media pause and resume confirmation (#687)

Maintenance release v0.8.4-daily.20260610

Other Changes

• Disable dictionary term prompts for Qwen3 ASR (#683)

Maintenance release v0.8.4-daily.20260609

Other Changes

• Fix overlay recovery after display changes
• Release Live Transcript plugin 1.0.2

Bug Fixes

• improve long file transcription progress and Groq uploads (#676)

Other Changes

• Fix Safari fullscreen indicator suppression fallback (#680)
• Fix terminal clipboard restore race after verified paste (#678)

Maintenance release v0.8.4-daily.20260607

Other Changes

• Add diagnostics guidance to issue templates (#675)
• Add short dictation workflow AI skip setting (#674)
• Fix Safari fullscreen indicator suppression (#671)
• Add recent transcriptions to the workflow palette (#670)
• Add Dutch number word normalization (#669)

Other Changes

• Handle stale provider profile selections
• Add OpenAI-compatible provider profiles
• Add number normalization parity

Other Changes

• Add OpenRouter speech-to-text support (#664)

Other Changes

• Address static analysis review findings
• Address review feedback for translation storage flow
• Address review feedback for storage paths
• Address review feedback for asset paths
• Add quick translation mode and model storage controls
• Add file transcription queue clearing
• Document public production APIs
• Add multiple workflow hotkeys
• Release Soniox plugin 1.0.3

Other Changes

• Add English ordinal number normalization (#655)
• Apply Dictionary Corrections to API and CLI transcriptions (#657)

Other Changes

• Rework license management flows
• Group Soniox transcript tokens for subtitles
• Add Premium Cloud Folder Sync
• Add AMD acceleration for whisper.cpp

New Features

• add commercial Cloud Folder Sync (#653)

Other Changes

• Fix Apple Speech first-use model selection (#654)

Maintenance release v0.8.4-daily.20260603

Other Changes

• Add multilingual number word normalization (#648)
• Remove SenseVoice plugin (#651)
• Add generic transcription number normalization (#647)

Maintenance release v0.8.4-daily.20260602

Other Changes

• add SenseVoice plugin release target (#646)

Maintenance release v0.8.4-daily.20260601

Other Changes

• Add experimental SenseVoice transcription plugin (#644)

Maintenance release v0.8.4-daily.20260531

Bug Fixes

• treat Reson8 as single-language engine

Other Changes

• Require restart after CUDA runtime installation

Other Changes

• Fix CUDA runtime delivery for local plugins
• Fix Soniox API key review issues
• Address Soniox review feedback
• Fix Soniox async transcription
• Add smart trailing space after dictation
• Add Reson8 to plugin release workflow (#178)
• Add Reson8 transcription plugin (#177)
• Marshal workflow fallback feedback to UI thread
• Fix workflow post-processing fallbacks
• Guard dictation audio history filenames
• Harden dictation persistence follow-ups
• Address dictation output persistence review
• Preserve preview fallback for long dictation
• Address writing focus review feedback
• Add acceleration restart prompt (#172)
• Fix writing focus localization
• Harden localization and live transcript tests
• Fix live transcript appearance settings
• Harden Live Transcript terminal event matching
• Fix Live Transcript no-speech cleanup
• Fix Windows-key hotkey focus handling
• Add SignPath application documentation
• Avoid blocking streaming audio callbacks
• Serialize streaming audio sends
• Fix online live transcription behavior
• Stabilize Granite Speech dependency audit
• Handle dispatcher shutdown safely
• Harden dispatcher fallback during tests
• Stabilize plugin system test run
• Address acceleration reload review feedback
• Address remaining review nits
• Tighten review follow-up handling
• Fix CUDA acceleration reload
• Stabilize review check follow-ups
• Address HTTP API review findings
• Stabilize settings dispatcher events
• Stabilize HTTP API parity checks
• Align Windows HTTP API with Mac contract
• Harden workflow prompt tests
• Frame workflow LLM input as data
• Remove issue Discord relay workflow (#153)
• Add Smallest AI plugin release mapping
• Add Smallest AI Pulse transcription plugin
• Fix onboarding completion for unready transcription engines (#148)
• Fix Groq API key setup in onboarding (#147)
• Add OpenAI model parity and default provider clarity

Other Changes

• Add configurable LLM request timeout to OpenAI Compatible plugin (#629)
• Add Reson8 plugin

Other Changes

• Add smart trailing space after dictation
• Add Reson8 to plugin release workflow (#178)
• Add Reson8 transcription plugin (#177)

New Features

• order language hints (#637)

Bug Fixes

• verify terminal paste outcomes (#635)

Other Changes

• Add macOS Whisper Mode AGC (#636)

Maintenance release v0.8.2-daily.20260528

New Features

• add standalone setup wizard (#600)
• add dictionary HTTP API endpoints (#575)

Bug Fixes

• preserve Apple Speech model status (#609)

Other Changes

• Add OpenAI-compatible profiles (#626)
• Fix middle mouse pass-through for hotkeys (#624)
• Fix overlay live transcript preview expansion (#622)
• Fix Script Runner add dialog (#621)
• Fix indicator panels invisible over fullscreen apps
• Fix workflow prompt casing diagnostics
• Fix start sound ducking order (#617)
• Fix repair installation action visibility (#615)
• Redesign integrations plugin catalog
• Fix custom workflow fine-tuning prompt (#610)
• Add recorder-specific transcription engine overrides (#606)
• Fix recording start sound playback (#605)
• Use standard pasteboard types for generated pasteboard payloads
• Enforce TypeWhisper-built community plugin artifacts
• Fix dictation trailing space insertion (#597)
• Add plugin update-state diagnostics and repair action (#598)
• Automate README screenshot gallery
• Prepare TypeWhisper 1.4.0 stable release notes
• Show indicators for active recorder sessions
• Add recorder HTTP API
• Hide indicators from supported screen captures (#585)
• Fix workflow LLM input boundaries (#580)
• Fix Apple Intelligence scaffold echoes in workflows (#577)

Other Changes

• Marshal workflow fallback feedback to UI thread
• Fix workflow post-processing fallbacks

New Features

• add standalone setup wizard (#600)
• add dictionary HTTP API endpoints (#575)

Bug Fixes

• preserve Apple Speech model status (#609)

Other Changes

• Fix overlay live transcript preview expansion (#622)
• Fix Script Runner add dialog (#621)
• Fix indicator panels invisible over fullscreen apps
• Fix workflow prompt casing diagnostics
• Fix start sound ducking order (#617)
• Fix repair installation action visibility (#615)
• Redesign integrations plugin catalog
• Fix custom workflow fine-tuning prompt (#610)
• Add recorder-specific transcription engine overrides (#606)
• Fix recording start sound playback (#605)
• Use standard pasteboard types for generated pasteboard payloads
• Enforce TypeWhisper-built community plugin artifacts
• Fix dictation trailing space insertion (#597)
• Add plugin update-state diagnostics and repair action (#598)
• Automate README screenshot gallery
• Prepare TypeWhisper 1.4.0 stable release notes
• Show indicators for active recorder sessions
• Add recorder HTTP API
• Hide indicators from supported screen captures (#585)
• Fix workflow LLM input boundaries (#580)
• Fix Apple Intelligence scaffold echoes in workflows (#577)

Maintenance release v0.8.2-daily.20260526

Other Changes

• Guard dictation audio history filenames
• Harden dictation persistence follow-ups
• Address dictation output persistence review
• Preserve preview fallback for long dictation
• Address writing focus review feedback
• Add acceleration restart prompt (#172)
• Fix writing focus localization

New Features

• add standalone setup wizard (#600)
• add dictionary HTTP API endpoints (#575)

Bug Fixes

• preserve Apple Speech model status (#609)

Other Changes

• Fix Script Runner add dialog (#621)
• Fix indicator panels invisible over fullscreen apps
• Fix workflow prompt casing diagnostics
• Fix start sound ducking order (#617)
• Fix repair installation action visibility (#615)
• Redesign integrations plugin catalog
• Fix custom workflow fine-tuning prompt (#610)
• Add recorder-specific transcription engine overrides (#606)
• Fix recording start sound playback (#605)
• Use standard pasteboard types for generated pasteboard payloads
• Enforce TypeWhisper-built community plugin artifacts
• Fix dictation trailing space insertion (#597)
• Add plugin update-state diagnostics and repair action (#598)
• Automate README screenshot gallery
• Prepare TypeWhisper 1.4.0 stable release notes
• Show indicators for active recorder sessions
• Add recorder HTTP API
• Hide indicators from supported screen captures (#585)
• Fix workflow LLM input boundaries (#580)
• Fix Apple Intelligence scaffold echoes in workflows (#577)

Maintenance release v0.8.2-daily.20260524

New Features

• add standalone setup wizard (#600)
• add dictionary HTTP API endpoints (#575)

Bug Fixes

• preserve Apple Speech model status (#609)

Other Changes

• Redesign integrations plugin catalog
• Fix custom workflow fine-tuning prompt (#610)
• Add recorder-specific transcription engine overrides (#606)
• Fix recording start sound playback (#605)
• Use standard pasteboard types for generated pasteboard payloads
• Enforce TypeWhisper-built community plugin artifacts
• Fix dictation trailing space insertion (#597)
• Add plugin update-state diagnostics and repair action (#598)
• Automate README screenshot gallery
• Prepare TypeWhisper 1.4.0 stable release notes
• Show indicators for active recorder sessions
• Add recorder HTTP API
• Hide indicators from supported screen captures (#585)
• Fix workflow LLM input boundaries (#580)
• Fix Apple Intelligence scaffold echoes in workflows (#577)

Other Changes

• Harden localization and live transcript tests

New Features

• add standalone setup wizard (#600)
• add dictionary HTTP API endpoints (#575)

Other Changes

• Use standard pasteboard types for generated pasteboard payloads
• Enforce TypeWhisper-built community plugin artifacts
• Fix dictation trailing space insertion (#597)
• Add plugin update-state diagnostics and repair action (#598)
• Automate README screenshot gallery
• Prepare TypeWhisper 1.4.0 stable release notes
• Show indicators for active recorder sessions
• Add recorder HTTP API
• Hide indicators from supported screen captures (#585)
• Fix workflow LLM input boundaries (#580)
• Fix Apple Intelligence scaffold echoes in workflows (#577)

Other Changes

• Fix live transcript appearance settings
• Harden Live Transcript terminal event matching
• Fix Live Transcript no-speech cleanup
• Fix Windows-key hotkey focus handling

TypeWhisper 1.4.0 is the stable release for the new Integrations and community-plugin foundation. It brings the redesigned plugin hub, the 1.4 community registry feed, downloaded model management, new local automation APIs, and a broad reliability pass across workflows, live transcript, indicators, audio capture, and first-party plugins.

Highlights

• Added the plugins-community-v1.json registry feed for 1.4 builds while keeping the 1.3.x line on the existing official marketplace feed.
• Redesigned Integrations with Installed, Discover, and Manual tabs, grouped plugin lists, source and hosting metadata, and capability filtering for local, cloud, transcription, LLM, action, and memory plugins.
• Added support for community plugin registry publishing and mirrored first-party plugin releases into the community registry feed.
• Added downloaded model management for local model plugins, including host-version gating for the Qwen3, Granite, Voxtral, Gemma 4, WhisperKit, and Supertonic release line.
• Added the Smallest AI Pulse transcription plugin, the xAI Grok plugin, the experimental Supertonic TTS plugin, and refreshed OpenAI voice and Qwen3 ASR integrations for 1.4.
• Added local Recorder and Dictionary HTTP API endpoints so trusted local clients can inspect recorder state, start transcriptions, and manage dictionary terms through the app API.
• Added watch-folder file job automation, per-dictation STT engine/model overrides, workflow drag reordering, and multiple global hotkeys per action.
• Added Parakeet live transcription support and the WhisperKit Distil Large v3 Turbo model.
• Added licensed industry term packs and localized built-in term pack metadata.

Reliability and Fixes

• Tightened workflow input boundaries so dictated text and Apple Intelligence scaffold output are treated as source content instead of executable instructions.
• Improved live transcript stability, sentence accumulation, correction handling, preview latency, and maximized-window behavior.
• Kept recording indicators visible for active recorder sessions while hiding supported indicator windows from screen captures.
• Improved fullscreen, fixed-display, foreign-window, and maximized-window indicator handling.
• Reduced hotkey recording startup latency and fixed exact modifier-combination matching.
• Recovered failed dictation audio and added audio diagnostics export for troubleshooting capture failures.
• Improved selected USB microphone capture, multichannel input handling, and system-audio recorder sample handling.
• Deferred the recording start cue until input is ready and improved Parakeet onboarding/setup status.
• Made plugin settings windows scrollable and restored workflow action targets.
• Improved onboarding layout, transcription helper compatibility, memory extraction for normal dictations, and plugin registry release metadata.
• Hardened webhook sensitive header storage and local API token enforcement.

Developer and Distribution Notes

• The stable Sparkle appcast entry for 1.4.0 uses the default channel and requires macOS 14.0 or later.
• Homebrew updates are intentionally stable-only and are triggered by the final v1.4.0 tag.
• Release candidates and daily builds remain on their dedicated Sparkle channels and do not update Homebrew.
• Plugin SDK workflow snapshots expose read-only workflow metadata without handing plugins internal app model objects.

New Features

• add dictionary HTTP API endpoints (#575)

Other Changes

• Show indicators for active recorder sessions
• Add recorder HTTP API
• Hide indicators from supported screen captures (#585)
• Fix workflow LLM input boundaries (#580)
• Fix Apple Intelligence scaffold echoes in workflows (#577)

Other Changes

• Add SignPath application documentation
• Avoid blocking streaming audio callbacks
• Serialize streaming audio sends
• Fix online live transcription behavior
• Stabilize Granite Speech dependency audit
• Handle dispatcher shutdown safely
• Harden dispatcher fallback during tests
• Stabilize plugin system test run
• Address acceleration reload review feedback
• Address remaining review nits
• Tighten review follow-up handling
• Fix CUDA acceleration reload
• Stabilize review check follow-ups
• Address HTTP API review findings
• Stabilize settings dispatcher events
• Stabilize HTTP API parity checks
• Align Windows HTTP API with Mac contract

New Features

• add dictionary HTTP API endpoints (#575)

Other Changes

• Fix workflow LLM input boundaries (#580)
• Fix Apple Intelligence scaffold echoes in workflows (#577)

Maintenance release v0.8.2-daily.20260520

Other Changes

• Harden workflow prompt tests
• Frame workflow LLM input as data
• Remove issue Discord relay workflow (#153)
• Add Smallest AI plugin release mapping
• Add Smallest AI Pulse transcription plugin

New Features

• manage downloaded plugin models (#570)

Bug Fixes

• keep indicators visible for maximized windows (#566)
• Clear blank sensitive header secrets
• Gate local API token enforcement
• Store sensitive headers in secrets
• Secure local API access

Other Changes

• gate downloaded model plugin releases to 1.4 (#572)
• Add Smallest AI Pulse transcription plugin (#568)
• Stabilize live transcript preview
• Fix live preview over maximized app windows (#557)
• Fix volatile live transcript corrections
• Restore workflow action targets (#556)
• Fix Live Transcript sentence accumulation (#554)
• Fix Live Transcript duplicate segments (#553)
• Add recording state menu bar logo (#551)
• Fix Live Transcript window accumulation
• Reduce Parakeet live preview latency
• Fix Intel Parakeet setup recommendation (#546)
• Defer recording start cue until input is ready
• Fix indicator suppression for foreign fullscreen notch windows (#543)
• Support multiple global hotkeys per action (#542)
• Remove workflow label background (#541)
• Add WhisperKit Distil Large v3 Turbo model (#539)
• Recover failed dictation audio (#534)
• Add Parakeet live transcription session
• Fix echo handling localization labels (#529)
• Make plugin settings windows scrollable (#527)
• Fix Supertonic plugin release build
• Fix Supertonic synthesizer cache synchronization
• Add experimental Supertonic TTS plugin
• Clean up plugin registry release metadata
• Fix onboarding welcome layout and transcription helper compatibility
• Fix Parakeet onboarding completion
• Extend OpenAI compatible transcription timeout
• Handle multichannel input capture formats

Bug Fixes

• keep indicators visible for maximized windows (#566)
• Clear blank sensitive header secrets
• Gate local API token enforcement
• Store sensitive headers in secrets
• Secure local API access

Other Changes

• Stabilize live transcript preview
• Fix live preview over maximized app windows (#557)
• Fix volatile live transcript corrections
• Restore workflow action targets (#556)
• Fix Live Transcript sentence accumulation (#554)
• Fix Live Transcript duplicate segments (#553)
• Add recording state menu bar logo (#551)
• Fix Live Transcript window accumulation
• Reduce Parakeet live preview latency
• Fix Intel Parakeet setup recommendation (#546)
• Defer recording start cue until input is ready
• Fix indicator suppression for foreign fullscreen notch windows (#543)
• Support multiple global hotkeys per action (#542)
• Remove workflow label background (#541)
• Add WhisperKit Distil Large v3 Turbo model (#539)
• Recover failed dictation audio (#534)
• Add Parakeet live transcription session
• Fix echo handling localization labels (#529)
• Make plugin settings windows scrollable (#527)
• Fix Supertonic plugin release build
• Fix Supertonic synthesizer cache synchronization
• Add experimental Supertonic TTS plugin
• Clean up plugin registry release metadata
• Fix onboarding welcome layout and transcription helper compatibility
• Fix Parakeet onboarding completion
• Extend OpenAI compatible transcription timeout
• Handle multichannel input capture formats

Other Changes

• Fix onboarding completion for unready transcription engines (#148)
• Fix Groq API key setup in onboarding (#147)
• Add OpenAI model parity and default provider clarity

Maintenance release v0.8.2-daily.20260517

Bug Fixes

• Clear blank sensitive header secrets
• Gate local API token enforcement
• Store sensitive headers in secrets
• Secure local API access

Other Changes

• Fix live preview over maximized app windows (#557)
• Fix volatile live transcript corrections
• Restore workflow action targets (#556)
• Fix Live Transcript sentence accumulation (#554)
• Fix Live Transcript duplicate segments (#553)
• Add recording state menu bar logo (#551)
• Fix Live Transcript window accumulation
• Reduce Parakeet live preview latency
• Fix Intel Parakeet setup recommendation (#546)
• Defer recording start cue until input is ready
• Fix indicator suppression for foreign fullscreen notch windows (#543)
• Support multiple global hotkeys per action (#542)
• Remove workflow label background (#541)
• Add WhisperKit Distil Large v3 Turbo model (#539)
• Recover failed dictation audio (#534)
• Add Parakeet live transcription session
• Fix echo handling localization labels (#529)
• Make plugin settings windows scrollable (#527)
• Fix Supertonic plugin release build
• Fix Supertonic synthesizer cache synchronization
• Add experimental Supertonic TTS plugin
• Clean up plugin registry release metadata
• Fix onboarding welcome layout and transcription helper compatibility
• Fix Parakeet onboarding completion
• Extend OpenAI compatible transcription timeout
• Handle multichannel input capture formats

Bug Fixes

• Clear blank sensitive header secrets
• Gate local API token enforcement
• Store sensitive headers in secrets
• Secure local API access

Other Changes

• Fix Live Transcript sentence accumulation (#554)
• Fix Live Transcript duplicate segments (#553)
• Add recording state menu bar logo (#551)
• Fix Live Transcript window accumulation
• Reduce Parakeet live preview latency
• Fix Intel Parakeet setup recommendation (#546)
• Defer recording start cue until input is ready
• Fix indicator suppression for foreign fullscreen notch windows (#543)
• Support multiple global hotkeys per action (#542)
• Remove workflow label background (#541)
• Add WhisperKit Distil Large v3 Turbo model (#539)
• Recover failed dictation audio (#534)
• Add Parakeet live transcription session
• Fix echo handling localization labels (#529)
• Make plugin settings windows scrollable (#527)
• Fix Supertonic plugin release build
• Fix Supertonic synthesizer cache synchronization
• Add experimental Supertonic TTS plugin
• Clean up plugin registry release metadata
• Fix onboarding welcome layout and transcription helper compatibility
• Fix Parakeet onboarding completion
• Extend OpenAI compatible transcription timeout
• Handle multichannel input capture formats

Maintenance release v0.8.2-daily.20260516

Bug Fixes

• Clear blank sensitive header secrets
• Gate local API token enforcement
• Store sensitive headers in secrets
• Secure local API access

Other Changes

• Fix Intel Parakeet setup recommendation (#546)
• Defer recording start cue until input is ready
• Fix indicator suppression for foreign fullscreen notch windows (#543)
• Support multiple global hotkeys per action (#542)
• Remove workflow label background (#541)
• Add WhisperKit Distil Large v3 Turbo model (#539)
• Recover failed dictation audio (#534)
• Add Parakeet live transcription session
• Fix echo handling localization labels (#529)
• Make plugin settings windows scrollable (#527)
• Fix Supertonic plugin release build
• Fix Supertonic synthesizer cache synchronization
• Add experimental Supertonic TTS plugin
• Clean up plugin registry release metadata
• Fix onboarding welcome layout and transcription helper compatibility
• Fix Parakeet onboarding completion
• Extend OpenAI compatible transcription timeout
• Handle multichannel input capture formats

Other Changes

• add v0.8.1 release notes
• Add OpenRouter model catalog and transcription support (#143)
• Fix cloud dictation final decoding (#144)
• Harden plugin registry categories (#142)
• Make Live Transcript window movable
• Fix local GPU acceleration reload (#138)
• Handle Live Transcript failures
• Add xAI Grok plugin support and branded plugin logos

TypeWhisper v0.8.1

TypeWhisper 0.8.1 is a focused Windows release that expands cloud provider coverage, improves plugin marketplace reliability, and fixes several dictation and local transcription issues found after 0.8.0.

New Features

• Added OpenRouter model catalog support so compatible models can be discovered and selected more easily.
• Added OpenRouter transcription support for cloud dictation workflows.
• Added the xAI Grok provider plugin with streaming transcription, text generation, and TTS support.
• Added branded plugin logos for major bundled providers.

Improvements

• Hardened plugin registry category handling so marketplace entries stay compatible as categories expand.
• Made the Live Transcript window movable and improved its settings experience.
• Improved local GPU acceleration reload behavior for local transcription providers.

Fixes

• Fixed final decoding for cloud dictation responses.
• Fixed Live Transcript failure handling so provider errors are surfaced more reliably.
• Improved model acceleration layout coverage and related plugin system behavior.

Bug Fixes

• Clear blank sensitive header secrets
• Gate local API token enforcement
• Store sensitive headers in secrets
• Secure local API access

Other Changes

• Add WhisperKit Distil Large v3 Turbo model (#539)
• Recover failed dictation audio (#534)
• Add Parakeet live transcription session
• Fix echo handling localization labels (#529)
• Make plugin settings windows scrollable (#527)
• Fix Supertonic plugin release build
• Fix Supertonic synthesizer cache synchronization
• Add experimental Supertonic TTS plugin
• Clean up plugin registry release metadata
• Fix onboarding welcome layout and transcription helper compatibility
• Fix Parakeet onboarding completion
• Extend OpenAI compatible transcription timeout
• Handle multichannel input capture formats

Maintenance release v0.8.1-daily.20260514

TypeWhisper v0.8.0

TypeWhisper 0.8.0 is a major Windows release focused on faster local transcription, a broader plugin marketplace, richer speech and TTS provider support, and steadier everyday dictation behavior.

New Features

• Added GPU acceleration for local transcription so supported local models can run faster on capable Windows systems.
• Added multi-category plugin marketplace support, making discovery clearer as plugins expand across transcription, text generation, TTS, memory, and workflow integrations.
• Added the Supertonic TTS provider plugin and a dedicated TTS marketplace category.
• Added side-specific modifier hotkeys for workflows that need distinct left/right keyboard shortcuts.
• Added Russian localization for the Windows app.
• Added Windows indicator style variants for a more flexible recording status experience.
• Added licensed industry term packs for specialized vocabulary workflows.
• Expanded OpenAI and ChatGPT plugin capabilities.

Improvements

• Improved plugin marketplace behavior and polish, including category handling and uninstall state feedback.
• Improved whisper.cpp native runtime packaging so bundled local transcription dependencies are more reliable.
• Improved touch scrolling across ScrollViewer controls.
• Limited Supertonic TTS runtime packaging to keep bundled plugin output cleaner.

Fixes

• Fixed microphone reconnect handling.
• Reduced repeated short transcription phrases and improved dictation ellipsis cleanup.
• Fixed plaintext insertion for email clients.
• Fixed live preview font size updates.
• Fixed live transcript no-speech handling.
• Fixed dictionary usage count localization.
• Fixed marketplace plugin uninstall state handling.

Bug Fixes

• Clear blank sensitive header secrets
• Gate local API token enforcement
• Store sensitive headers in secrets
• Secure local API access

Other Changes

• Fix Supertonic plugin release build
• Fix Supertonic synthesizer cache synchronization
• Add experimental Supertonic TTS plugin
• Clean up plugin registry release metadata
• Fix onboarding welcome layout and transcription helper compatibility
• Fix Parakeet onboarding completion
• Extend OpenAI compatible transcription timeout
• Handle multichannel input capture formats

Other Changes

• Add TTS marketplace category
• Limit Supertonic TTS runtime packaging
• Add Supertonic TTS provider plugin (#119)
• Fix dictation ellipsis cleanup (#116)
• Reduce short repeated transcription phrases (#117)
• Fix plaintext insertion for email clients (#118)
• Fix live preview font size updates (#114)
• Fix dictionary usage count localization (#115)
• Fix live transcript no-speech handling (#113)

TypeWhisper 1.4.0-rc3 refreshes the 1.4 release-candidate line from current main (855a5823). This candidate focuses on lower-latency dictation starts, workflow engine overrides, audio diagnostics, model/plugin refreshes, licensed term packs, watch-folder file jobs, and memory extraction fixes since 1.4.0-rc2.

Highlights

• Added the OpenAI voice refresh for TypeWhisper 1.4 and refreshed the Qwen3 ASR plugin for 1.1.0.
• Reduced hotkey recording start latency and cold-start latency.
• Fixed exact modifier-combo hotkey matching.
• Added dictation workflow engine overrides.
• Removed legacy profile runtime rules.
• Added support diagnostics export for audio device failures.
• Allowed USB input selection without preflight capture.
• Added licensed industry term packs.
• Fixed Parakeet startup model selection status.
• Fixed memory extraction for normal dictations.
• Added watch folder file-job automation.

Testing Focus

• Verify hotkey start/cold-start latency and exact modifier combinations.
• Smoke-test dictation workflow engine overrides and normal dictation memory extraction.
• Export audio diagnostics and select USB input devices without preflight capture.
• Check OpenAI, Qwen3, and Parakeet plugin/model settings.
• Download and apply licensed industry term packs.
• Run watch folder file-job automation.
• Confirm the RC release publishes DMG/ZIP assets and updates Sparkle on the release-candidate channel.

Bug Fixes

• remove legacy profile runtime rules (#502)
• reduce hotkey cold-start latency (#497)
• reduce hotkey recording start latency

Other Changes

• Add watch folder file job automation (#514)
• Fix memory extraction for normal dictations (#512)
• Add SDK auth role status for OpenAI transcription (#511)
• Add audio diagnostics export (#510)
• Allow USB input selection without preflight capture (#508)
• Add dictation workflow engine overrides (#509)
• Add licensed industry term packs
• Fix Parakeet startup model selection status (#501)
• Fix scheduled app test CI (#500)
• Refresh Qwen3 ASR plugin for 1.1.0
• Clarify GPL and commercial licensing copy
• Fix exact modifier combo matching
• Add OpenAI voice refresh for TypeWhisper 1.4

Other Changes

• Add Russian UI localization (#105)

TypeWhisper 1.3.3 is a stable hotfix release for the 1.3 line. It fixes selected USB audio interfaces still being marked as not compatible before preview or recording can start.

Bug Fixes

• Fixed USB microphones and audio interfaces, including RME Babyface-style devices, being blocked by selection-time compatibility checks.
• Kept non-Bluetooth input selection non-blocking so TypeWhisper can reach the input-only HAL preview and recording path added in 1.3.2.
• Preserved Bluetooth route activation, stabilization, and aggregate-route validation behavior.

Testing Focus

• If a USB interface still showed (Not compatible) in TypeWhisper 1.3.2, test selecting it again in 1.3.3.
• After selection, use Test Microphone to confirm the device now reaches preview capture.

Bug Fixes

• remove legacy profile runtime rules (#502)
• reduce hotkey cold-start latency (#497)
• reduce hotkey recording start latency

Other Changes

• Add licensed industry term packs
• Fix Parakeet startup model selection status (#501)
• Fix scheduled app test CI (#500)
• Refresh Qwen3 ASR plugin for 1.1.0
• Clarify GPL and commercial licensing copy
• Fix exact modifier combo matching
• Add OpenAI voice refresh for TypeWhisper 1.4

Other Changes

• Add Windows indicator style variants (#102)
• Add licensed industry term packs

TypeWhisper 1.3.2 is a stable hotfix release for the 1.3 line. It fixes selected USB audio interfaces being marked as not compatible when the selected input and current output device use different clocks or sample rates.

Bug Fixes

• Fixed selected USB microphones and audio interfaces that could show (Not compatible) before preview or recording started.
• Routed explicit non-Bluetooth input devices through an input-only CoreAudio HAL capture path, avoiding stale AVAudioEngine full-duplex formats when input and output clocks differ.
• Kept the existing AVAudioEngine route for system default and Bluetooth inputs, preserving the established Bluetooth stabilization and recovery behavior.
• Downmixed multi-channel input buffers to mono before the existing 16 kHz transcription conversion path.

Testing Focus

• If a USB interface such as an RME Babyface, Elgato Wave XLR, or similar device showed (Not compatible) in TypeWhisper 1.3.1, test selecting it again in 1.3.2.
• If the device still fails, also test with the interface set as the macOS default input and with input/output sample rates aligned at 48 kHz.

Bug Fixes

• reduce hotkey cold-start latency (#497)
• reduce hotkey recording start latency

Other Changes

• Fix scheduled app test CI (#500)
• Refresh Qwen3 ASR plugin for 1.1.0
• Clarify GPL and commercial licensing copy
• Fix exact modifier combo matching
• Add OpenAI voice refresh for TypeWhisper 1.4

Other Changes

• Fix marketplace plugin uninstall state (#100)

Bug Fixes

• reduce hotkey recording start latency

Other Changes

• Refresh Qwen3 ASR plugin for 1.1.0
• Clarify GPL and commercial licensing copy
• Fix exact modifier combo matching
• Add OpenAI voice refresh for TypeWhisper 1.4

Bug Fixes

• enable touch scroll on all ScrollViewer controls (#99)

Other Changes

• Add OpenAI voice refresh for TypeWhisper 1.4

Other Changes

• Expand OpenAI / ChatGPT plugin capabilities (#98)
• Prepare v0.7.2 release
• Reduce repeated transcription phrases (#96)
• Add preview bubble auto-hide setting
• Add Japanese localization
• Add manual workflows and advanced workflow triggers on Windows (#94)
• Keep preview bubble compact and scrolled

TypeWhisper v0.7.2

TypeWhisper 0.7.2 is a stability and polish release for Windows. It improves dictation reliability, adds Japanese localization, makes the preview bubble easier to control, and hardens the newest workflow and paste behavior from the 0.7 line.

New Features

• Added Japanese localization for the Windows app.
• Added an auto-hide setting for the preview bubble.
• Added manual workflow controls and advanced workflow triggers on Windows.

Improvements

• Kept the preview bubble compact and scrolled so longer live transcription output stays easier to follow.
• Improved Parakeet transcription tail handling with optional tail padding, better final-result selection, and internal diagnostics for clipped endings.
• Added audio tail telemetry around recording stop so hard-to-reproduce tail clipping can be diagnosed more clearly.

Fixes

• Reduced repeated transcription phrases in final dictation output.
• Fixed paste handoff latency so inserted text is less likely to race with the target app.
• Preserved clean no-speech handling for short and quiet clips while improving final transcription padding.

TypeWhisper 1.4.0-rc2 refreshes the 1.4 release-candidate line on the current main branch. This candidate is based on e9808037 and focuses on workflow ordering, recorder reliability, plugin SDK polish, and integration fixes since 1.4.0-rc1.

Highlights

• Added drag-and-drop ordering for workflows, with matching priority following the saved workflow order.
• Kept workflow reordering disabled while search is filtering the list, so filtered subsets do not rewrite global priority by accident.
• Added combined workflow trigger support and spoken-punctuation compatibility coverage for older workflow behavior.
• Improved recorder reliability for FaceTime/system audio sample handling and selected USB microphones with mismatched output clocks.
• Fixed Gemma plugin cache recovery after failed downloads.
• Added structured speaker diarization support for AssemblyAI through the Plugin SDK path.
• Tightened the 1.4 community plugin registry automation and permissions.
• Replaced spoken-language flag icons with neutral language badges.
• Fixed fixed-display indicators in fullscreen Spaces and clarified the German recorder settings label.

Testing Focus

• Verify workflow drag reorder affects matching priority and remains disabled while filtering.
• Smoke-test combined trigger workflows and spoken-punctuation compatibility controls.
• Record with selected USB microphones and system audio or FaceTime paths.
• Retry a Gemma model download after failure and verify cache recovery.
• Check AssemblyAI diarization settings and structured speaker labels.
• Confirm the 1.4 community registry feed and Integrations tabs still resolve plugins correctly.
• Verify fixed-display indicators in fullscreen Spaces.

Bug Fixes

• disambiguate German recorder settings label
• support combined workflow triggers (#466)

Other Changes

• Fix fixed-display indicators in fullscreen spaces
• Add Swift CodeQL quality workflow
• Set AssemblyAI minimum host version for diarization release
• Add structured speaker diarization SDK path
• Fix selected USB mic capture with mismatched output clocks (#474)
• Fix system audio recorder sample handling
• Replace spoken language flags with neutral badges
• Limit community registry workflow permissions
• Add community plugin registry workflow
• Refactor first-party plugin sources into the SDK package (#464)
• Mirror v1 plugin releases to community registry (#462)
• Refactor RTF clipboard formatting (#463)
• Add xAI Grok plugin (#461)

Maintenance release v0.7.2-daily.20260507

Bug Fixes

• disambiguate German recorder settings label
• support combined workflow triggers (#466)

Other Changes

• Fix system audio recorder sample handling
• Replace spoken language flags with neutral badges
• Limit community registry workflow permissions
• Add community plugin registry workflow
• Refactor first-party plugin sources into the SDK package (#464)
• Mirror v1 plugin releases to community registry (#462)
• Refactor RTF clipboard formatting (#463)
• Add xAI Grok plugin (#461)

Other Changes

• Fix paste handoff latency (#87)

Other Changes

• Refactor first-party plugin sources into the SDK package (#464)
• Mirror v1 plugin releases to community registry (#462)
• Refactor RTF clipboard formatting (#463)
• Add xAI Grok plugin (#461)

Other Changes

• Fix mouse-mapped hotkeys on Windows (#84)
• Fix/escape cancel stuck state (#85)

TypeWhisper 1.4.0-rc1 opens the 1.4 release-candidate line with the first community-plugin preparation work and a clearer Integrations hub. This work is intentionally scoped to 1.4; the 1.3.x line continues to use the existing official plugin registry feed.

Highlights

• Added the plugins-community-v1.json registry feed for 1.4 preview and stable builds.
• Kept 1.3.x builds on the existing plugins-v1.json marketplace feed.
• Added registry source metadata so official and community plugins can be separated in the app UI.
• Redesigned Integrations around a compact grouped list with dedicated Installed, Discover, and Manual tabs.
• Added source, hosting, and multi-capability badges plus compact capability filtering so bundled, marketplace, community, manual, local, cloud, transcription, LLM, action, and memory integrations can be scanned together.
• Exposed user workflows to plugins through read-only Plugin SDK snapshots for community plugin use cases such as workflow-aware post-processing.
• Removed the 1.3-era Legacy cleanup surface from Settings. The 1.4 settings navigation goes directly to Workflows without a Legacy migration page.

Testing Focus

• Verify official marketplace plugins still resolve from plugins-v1.json on 1.3.x.
• Verify 1.4.0-rc*, 1.4.0 daily, and 1.4.0 stable builds resolve from plugins-community-v1.json.
• Smoke-test the Integrations hub tabs, Discover search, Community toggle, capability filter menu, multi-capability badges, manual bundle installation, and incompatible bundle warnings.
• Verify plugins can read host.availableWorkflows without receiving internal app model objects.
• Verify the Settings sidebar no longer shows a Legacy page and old profile/prompt navigation requests land in Workflows.

Other Changes

• Fix mouse-mapped hotkeys on Windows (#84)
• Fix/escape cancel stuck state (#85)
• Fix Windows SendInput struct layout for auto-paste (#83)
• Fix Escape cancel hotkey registration (#82)

TypeWhisper 1.3.1 is a stable maintenance release for the 1.3 line. It brings the workflow improvements from the 1.3.1 release candidates to stable users, adds direct workflow text hotkeys and a spoken-language dictation template, improves plugin metadata, and includes reliability fixes for Deepgram code-switching, Bluetooth audio, indicators, local LLM cleanup, and large automation requests.

New Features

• Added an Apple Translate workflow processor for local translation workflows on supported macOS configurations.
• Added a manual workflow trigger so workflows can stay out of automatic dictation matching and run from the Workflow Palette instead.
• Added a recorder toggle in the menu bar for faster access to app audio recording.
• Added packaging support for the bundled Filler Words plugin.
• Added a workflow dictation template for spoken-language transformations.
• Added direct workflow text hotkeys so workflows can run on selected or supplied text without starting a dictation.

Bug Fixes

• Exposed Deepgram multilingual code-switching support so mixed-language dictation can use the provider capability correctly.
• Reduced workflow post-processing latency so prompt and processor workflows return results faster after transcription.
• Wrapped Apple Intelligence workflow input so dictated text is treated as source content instead of executable instructions.
• Stabilized Bluetooth dictation capture and guarded AirPods output volume during audio routing changes.
• Opted indicators out of fullscreen spaces to avoid unexpected overlay behavior when apps use fullscreen mode.
• Restored indicator visibility across macOS spaces.
• Disabled automatic Live Transcript opening by default.
• Auto-unloaded local LLM post-processing resources after use to reduce background memory pressure.
• Supported large CLI transcriptions without truncating or failing oversized requests.
• Kept the language list available before transcription plugins finish loading.
• Fixed a Parakeet live preview fallback race.

Other Changes

• Classified plugin hosting explicitly so local and cloud plugins appear with clearer metadata in plugin listings.
• Documented plugin hosting metadata in the SDK manifest guidance.
• Updated Parakeet vocabulary boosting capability detection for current local-model behavior.
• Expanded automated coverage for workflow text hotkeys, spoken-language workflow templates, plugin hosting compatibility, and Deepgram multilingual code-switching.

Maintenance release v0.7.1-daily.20260504

Bug Fixes

• expose multilingual code-switching (#451)

Other Changes

• prepare 1.3.1-rc2 release (#448)

Maintenance release v0.7.1-daily.20260503

TypeWhisper 1.3.1-rc2 is planned as the final release candidate before 1.3.1. This update rounds out the 1.3.1 line with spoken-language workflow dictation templates, direct text hotkeys for workflows, and clearer plugin hosting metadata before the stable release.

New Features

• Added a workflow dictation template for spoken-language transformations.
• Added direct workflow text hotkeys so workflows can run on selected or supplied text without starting a dictation.

Bug Fixes

• Classified plugin hosting explicitly so local and cloud plugins appear with clearer metadata in plugin listings.

Other Changes

• Documented plugin hosting metadata in the SDK manifest guidance.
• Expanded automated coverage for workflow text hotkeys, spoken-language workflow templates, and plugin hosting compatibility.

Other Changes

• Fix Windows SendInput struct layout for auto-paste (#83)
• Fix Escape cancel hotkey registration (#82)

TypeWhisper 1.3.1-rc1 starts the 1.3.1 release-candidate line with new workflow processors, manual workflow controls, plugin improvements, and a focused reliability pass for Bluetooth audio, indicators, local LLM post-processing, and large automation requests.

New Features

• Added an Apple Translate workflow processor for local translation workflows on supported macOS configurations.
• Added a manual workflow trigger so workflows can stay out of automatic dictation matching and run from the Workflow Palette instead.
• Added a recorder toggle in the menu bar for faster access to app audio recording.

Bug Fixes

• Reduced workflow post-processing latency so prompt and processor workflows return results faster after transcription.
• Wrapped Apple Intelligence workflow input so dictated text is treated as source content instead of executable instructions.
• Stabilized Bluetooth dictation capture and guarded AirPods output volume during audio routing changes.
• Opted indicators out of fullscreen spaces to avoid unexpected overlay behavior when apps use fullscreen mode.
• Disabled automatic Live Transcript opening by default.
• Auto-unloaded local LLM post-processing resources after use to reduce background memory pressure.
• Supported large CLI transcriptions without truncating or failing oversized requests.
• Kept the language list available before transcription plugins finish loading.

Other Changes

• Updated Parakeet vocabulary boosting capability detection for current local-model behavior.
• Added packaging support for the bundled Filler Words plugin.

New Features

• add Apple Translate workflow processor (#427)
• add recorder menu bar toggle (#414)
• add manual workflow trigger (#411)

Bug Fixes

• opt indicators out of fullscreen spaces (#434)
• wrap Apple Intelligence workflow input (#432)
• disable live transcript auto-open by default (#430)
• auto-unload local LLM post-processing (#425)
• reduce workflow post-processing latency (#426)
• update Parakeet vocabulary boosting capability (#423)
• support right-side modifier hotkeys (#413)
• support large CLI transcriptions (#410)
• keep language list available before plugins load (#404)
• guard AirPods output volume during audio routing (#403)

Other Changes

• prepare 1.3.0 stable release (#402)
• Add WhisperKit lifecycle regression tests (#401)

Maintenance release v0.7.1-daily.20260501

New Features

• add Apple Translate workflow processor (#427)
• add recorder menu bar toggle (#414)
• add manual workflow trigger (#411)

Bug Fixes

• auto-unload local LLM post-processing (#425)
• reduce workflow post-processing latency (#426)
• update Parakeet vocabulary boosting capability (#423)
• support right-side modifier hotkeys (#413)
• support large CLI transcriptions (#410)
• keep language list available before plugins load (#404)
• guard AirPods output volume during audio routing (#403)

Other Changes

• prepare 1.3.0 stable release (#402)
• Add WhisperKit lifecycle regression tests (#401)

Maintenance release v0.7.1-daily.20260430

Maintenance release v0.7.1-daily.20260429

New Features

• add recorder menu bar toggle (#414)
• add manual workflow trigger (#411)

Bug Fixes

• support right-side modifier hotkeys (#413)
• support large CLI transcriptions (#410)
• keep language list available before plugins load (#404)
• guard AirPods output volume during audio routing (#403)

Other Changes

• prepare 1.3.0 stable release (#402)
• Add WhisperKit lifecycle regression tests (#401)

Maintenance release v0.7.1-daily.20260428

Maintenance release v0.7.1-daily.20260427

Bug Fixes

• keep language list available before plugins load (#404)
• guard AirPods output volume during audio routing (#403)

Other Changes

• prepare 1.3.0 stable release (#402)
• Add WhisperKit lifecycle regression tests (#401)

Maintenance release v0.7.1-daily.20260426

TypeWhisper v0.7.0

TypeWhisper 0.7.0 is a major workflow and automation release for Windows. It brings the workflow system into the main settings experience, expands file transcription automation, adds new provider capabilities, and tightens dictation reliability for everyday use.

New Features

• Added the unified Workflows surface for prompt actions, matching rules, workflow-specific hotkeys, language and model overrides, output formatting, and action routing.
• Added batch file transcription queues with per-file status tracking, export options, and improved model selection behavior.
• Added watch folder transcription so folders can be monitored and processed automatically with configurable export output.
• Added the recent transcriptions palette for quickly finding, editing, copying, and reusing recent dictation results.
• Added the ElevenLabs transcription plugin, including streaming support and localized settings.
• Added TTS provider plugin support, including host services, playback sessions, voice metadata, and a built-in Windows SAPI provider.
• Added stable, release-candidate, and daily update channel support in the app and release packaging.

Improvements

• Expanded the local HTTP API and bundled CLI with per-request engine and model overrides, language hints, translation targets, dictionary term management, and dictation controls.
• Improved automation compatibility for external tools through richer API parsing, status responses, and CLI installation support.
• Improved file transcription handling for larger queues, subtitle export, media formats, and watch folder output.
• Improved plugin marketplace and plugin host behavior so bundled and external plugins can expose more capabilities consistently.
• Improved short and quiet speech handling with configurable padding and gain behavior.
• Refined README, issue templates, PR templates, package dry runs, plugin smoke checks, and release workflow coverage.

Fixes

• Fixed dictation tail clipping so the end of short recordings is less likely to be cut off.
• Hardened automatic paste reliability after transcription completes.
• Fixed prompt provider selection and related history/prompt provider race conditions.
• Fixed autostart toggle handling.
• Hardened watch folder exception handling so background folder processing is more resilient.

TypeWhisper 1.3 is the stable macOS release centered on the new Workflows experience, more capable automation surfaces, and a broad round of dictation, UI, and local-model reliability work across the 1.3.0-rc* cycle.

Highlights

• Unified Workflows - TypeWhisper now brings prompt actions and matching rules into one dedicated Workflows surface, with a native editor, wizard flow, and a global Always fallback trigger.
• Better automation control - The local HTTP API and CLI now support per-request STT engine and model selection, while multilingual language hints make mixed-language dictation easier to steer.
• More polished dictation feedback - Spoken feedback, adjustable transcript sizing, faster recent-transcription recovery, and grouped menu bar actions make day-to-day use smoother.
• Stronger local-model path - The 1.3 cycle hardens local plugin downloads, Hugging Face token handling, model restore behavior, and Parakeet language filtering.

Workflows & Prompt Processing

• Replaced the old Prompt Actions and Rules settings surfaces with the new unified Workflows experience.
• Added a native macOS sidebar and wizard-style create/edit flow for workflows.
• Added a global Always workflow trigger that acts as the fallback after website and app-specific matches.
• Hardened workflow prompts so dictated text is always treated as source text to transform, not instructions to execute.
• Added per-workflow temperature controls for supported LLM providers.
• Preserved focus in the original target app during local prompt processing.

Dictation, Feedback & UI Polish

• Added spoken feedback through the bundled System Voice plugin, scoped to transcription readback only.
• Added multilingual language hints with multi-select search and selected-count feedback.
• Added shortcuts for reopening recent transcriptions and a recovery palette for recent results.
• Added adjustable live transcript preview sizing for dictation overlays.
• Improved the notch and overlay indicator behavior, including active-screen re-anchoring and timer layout fixes.
• Grouped menu bar actions into clearer sections for faster navigation.
• Fixed Fn hotkey handling so both press-and-release and press-and-hold strategies work reliably.

Local Models, Plugins & Reliability

• Upgraded the local model runtime and download flows for bundled on-device plugins.
• Added shared Hugging Face token handling for the bundled local-model plugins and clearer validation where required.
• Fixed Parakeet language filtering against the current FluidAudio upstream behavior.
• Improved WhisperKit restore and unload handling.
• Split the marketplace feeds by compatibility line and hardened plugin loading so incompatible external bundles are skipped instead of breaking launch.
• Made dictionary prompts engine-aware and kept streaming dictionary terms working across AssemblyAI, Soniox, and SpeechAnalyzer.
• Added subtitle exports for Watch Folder jobs.

Power Users & Automation

• Added per-request STT engine and model selection through the local HTTP API and the typewhisper CLI.
• Kept the documented /v1/* API and CLI command surface stable for the 1.x line.
• Improved plugin compatibility validation and diagnostics for marketplace and bundled plugins.

Other Changes

• Add WhisperKit lifecycle regression tests (#401)

Other Changes

• Add recent transcriptions palette (#72)
• Add short and quiet clip handling controls
• Add TTS provider plugin support
• Add advanced API and CLI settings
• Add batch file transcription queue
• Harden watch folder exception handling
• Implement watch folder file transcription
• Add Windows workflow automation
• Add Raycast-compatible Windows API support
• Add About update channel selector
• Align automation API and CLI

TypeWhisper 1.3.0-rc5 is planned as the final release candidate before 1.3.0. This update tightens the new Workflows experience with a global fallback trigger and safer prompt boundaries, adds a round of menu bar and indicator polish, and refreshes the local-model path with the Parakeet language-filter fix plus shared Hugging Face token handling.

New Features

• Added a global Always workflow trigger that acts as the fallback after website and app-specific workflow matches.
• Grouped the menu bar actions into clearer sections so the most common dictation and app actions are faster to scan.

Bug Fixes

• Hardened workflow prompts so dictated text is treated as source content to transform instead of instructions to execute.
• Preserved focus in the original target app during local prompt processing so on-device workflows do not foreground TypeWhisper unexpectedly.
• Fixed notch timer wrapping so longer timers stay readable without breaking the indicator layout.
• Fixed Parakeet language filtering to match the current FluidAudio upstream behavior more reliably.

Other Changes

• Added a shared Hugging Face token helper for the bundled local-model plugins, including Parakeet, Gemma 4, Granite, Qwen3, Voxtral, and WhisperKit.
• Expanded automated coverage around workflow matching, workflow prompt boundaries, menu bar indicator settings, notch layout, and plugin manifest validation.

Other Changes

• Fix notch timer wrapping

Other Changes

• Add Raycast-compatible Windows API support
• Add About update channel selector
• Align automation API and CLI

Maintenance release v0.6.2-rc1

Maintenance release v0.6.2-daily.20260423

TypeWhisper 1.3.0-rc4 makes the new unified Workflows experience the headline feature of the 1.3 release-candidate line, backed by watch-folder subtitle exports, adjustable live transcript sizing, recent-transcription shortcuts, and a round of dictation, indicator, and WhisperKit fixes since rc3.

New Features

• Replaced the old Prompt Actions and Rules settings surfaces with the new unified Workflows experience, including the new dedicated settings area for creating, editing, and organizing workflows.
• Added subtitle exports for Watch Folder jobs.
• Added an adjustable live transcript preview size for dictation overlays.
• Added shortcuts for reopening recent transcriptions.

Bug Fixes

• Restored the prompt palette shortcut when the default provider is unavailable.
• Fixed active-screen indicator placement so overlays re-anchor more reliably.
• Reduced recorder live preview lag during dictation.
• Improved WhisperKit restore and unload handling.

Other Changes

• Added the German Medicine community term pack.

Bug Fixes

• restore prompt palette shortcut when default provider is unavailable

Other Changes

• Add adjustable live transcript preview size
• Fix active screen indicator placement
• Fix WhisperKit restore and unload handling
• remove duplicate settings sidebar toggle
• replace prompts and rules with workflows
• add missing 1.3.0 rc2 and rc3 release notes

Bug Fixes

• restore prompt palette shortcut when default provider is unavailable

Other Changes

• add missing 1.3.0 rc2 and rc3 release notes

TypeWhisper 1.3.0-rc3 refreshes the 1.3 release-candidate line with the redesigned prompt workflow, per-prompt temperature controls, a recent-transcription recovery palette, and the new post-update licensing prompt, plus a round of dictation, dictionary, and plugin-loading fixes since rc2.

New Features

• Redesigned Prompt Actions settings with a native macOS sidebar and a wizard-style create/edit flow.
• Added per-prompt temperature controls for supported LLM providers, including recommended defaults for the built-in presets.
• Added a recent transcription recovery palette so you can quickly reopen and reinsert recent results.
• Added a post-update licensing prompt that routes upgraded installs into the refreshed licensing flow.

Bug Fixes

• Refined quiet-dictation and short-speech handling for more reliable low-signal recordings.
• Made dictionary prompts engine-aware so providers can clip global dictionary terms to their documented limits without destabilizing the session.
• Isolated disabled plugins so they stay registered without being eagerly loaded, which reduces startup and settings regressions from incompatible bundles.
• Removed the duplicate settings sidebar button on macOS 14.

Other Changes

• Documented the new DictionaryTermsBudgetProviding plugin SDK hook for engines with explicit dictionary-term limits.

New Features

• add prompt temperature controls and lazy plugin loading

Bug Fixes

• remove duplicate macOS 14 settings sidebar button

TypeWhisper 1.3.0-rc2 rolls up the stabilization work that landed after rc1, with a focus on push-to-talk reliability, short-speech handling, audio recovery hardening, and the refreshed local-model and licensing flows.

Reliability & Input Handling

• Fixed modifier-combo push-to-talk so transient flagsChanged churn does not stop recording before the final key release.
• Added the default push-to-talk discard behavior when extra keys interrupt an active hold, while keeping the stop point predictable on the actual hotkey release.
• Added an advanced opt-in to transcribe more short and quiet clips instead of classifying them as no speech.
• Hardened audio recovery, preview recovery, and recording-abort cleanup around route changes and device loss.
• Delayed media playback resume after dictation to avoid premature restarts.
• Ignored benign startup configuration changes that should not trigger unnecessary recovery work.

Local Models & Plugins

• Upgraded the shared local-model runtime stack and added Gemma 4 support with clearer model-policy messaging.
• Improved local-model download, cancellation, and Hugging Face token flows across the bundled local plugins.
• Fixed Gemini model discovery and prompt-processing fallback handling.

Settings & UX

• Redesigned the in-app licensing settings flow.
• Aligned spoken-language picker labels and search behavior with the app locale.

New Features

• redesign the licensing settings flow

Bug Fixes

• ignore benign startup config change on recording start
• align language picker search with app locale
• bounded recovery + terminal error propagation

Other Changes

• Fix Gemini model discovery and prompt fallback handling
• Trigger website rebuilds for preview releases

Other Changes

• Trigger website rebuilds for preview releases

TypeWhisper v0.6.1

TypeWhisper 0.6.1 is a focused stability release that tightens dictation behavior, file transcription model selection, provider state handling, and release packaging.

Improvements

• Improved provider and model state handling so the app is less likely to lose the selected configuration while switching between engines and prompts.
• Refined the bundled Groq integration with better LLM model selection and refresh behavior.

Fixes

• Fixed recorder-compatible hotkey parsing so captured shortcuts round-trip correctly through the UI and runtime hotkey pipeline.
• Fixed file transcription to load the model the user actually selected instead of falling back unexpectedly.
• Fixed the silent-stop overlay reset path and closed a streaming session leak that could leave overlay state behind after recording ended.

Release Prep

• Hardened the release workflow so app tags prefer curated notes from docs/releases/ and fall back to commit-generated notes only when no curated file exists.
• Scoped previous-tag lookup to app tags only, preventing plugin tags from polluting app release note ranges.
• Prepared the Windows release metadata for 0.6.1, including CLI version reporting and Groq plugin metadata alignment for plugin-groq-v1.0.2.

TypeWhisper 1.3.0-rc1 opens the 1.3 release-candidate line. The release adds spoken feedback, per-request STT control through the HTTP API and CLI, multilingual language hints, and the new plugin-compatibility safeguards introduced after #327, on top of a set of hotkey, audio, and plugin reliability fixes.

New Features

• Spoken feedback (text-to-speech) with a new System Voice marketplace plugin that uses the built-in macOS AVSpeechSynthesizer voices. Voice and speed are configurable in the settings, and the feedback is scoped to transcription readback only.
• Per-request STT engine and model selection through the HTTP API (engine/model on /v1/transcribe) and the CLI (typewhisper transcribe --engine <id> --model <id>). When omitted, the active profile defaults are used.
• Multilingual language hints with a multi-select picker, inline search, and a selected-count indicator, wired through to the transcription providers.

Bug Fixes

• Restored GPT-5 and Codex compatibility for the bundled OpenAI plugin.
• Fixed Fn-hotkey handling so both press-and-release and press-and-hold strategies work reliably.
• Spoken feedback is now limited to transcription readback and no longer narrates unrelated UI events.
• Addressed the 1.2.3 review blockers (K1-K4, M1, M7, M8) in the release pipeline and plugin registry.
• Split the marketplace into legacy and v1 feeds, moved plugin and term-pack fetches out of startup, and hardened plugin loading so incompatible external bundles are skipped instead of breaking launch.
• Hardened audio recovery during Bluetooth route changes to avoid crashes.
• Dictionary terms are forwarded through the streaming providers (AssemblyAI, Soniox, SpeechAnalyzer) without breaking the live session.

Other Changes

• Refactored the Qwen3 context-bias formatter for cleaner prompt injection and easier future tuning.
• Incremental live transcription, Google Cloud STT release mapping, and the multi-release plugin registry are carried forward from the late 1.2.x work.
• All current marketplace plugins now have v1 releases for the RC line, including System Voice as an installable TTS plugin.

New Features

• per-request STT engine/model selection (#317) (#325)
• add TTS providers for spoken feedback (#323)
• add multilingual language hints (#312) (#319)

Bug Fixes

• dedupe build-file UUID collision between Qwen3ContextBiasFormatter and MinimalIndicatorView
• limit spoken feedback to transcription readback (#324)
• address release 1.2.3 review blockers (K1-K4, M1/M7/M8) (#320)
• support Fn press/release hotkey strategies (#316)
• restore GPT-5 OpenAI plugin compatibility (#313)

Other Changes

• Fix plugin SDK compatibility handling (#328)
• Add double-escape cancel confirmation (#326)
• strip trailing newline from 1.3.0-rc1 release notes
• Refactor Qwen3 context bias formatting (#322)

New Features

• wire dictionary terms through transcription providers

Bug Fixes

• keep AssemblyAI streaming active with dictionary terms

Other Changes

• Update localized string catalog
• Allow optional profile scope and default fallback
• Fix PR guard bot handling
• Add Google Cloud STT plugin release mapping
• Keep plugin registry backward compatible
• Fix legacy plugin release migration
• Add multi-release registry and incremental live transcription
• fix audio recovery crash during Bluetooth route changes
• remove temporary plugin debug logging
• Remove deprecated activation option
• Allow empty correction replacements
• Add manual uninstall instructions to README
• Fix managed window activation on repeated menu bar opens
• Update localized string catalog ordering
• Fix #287 validate selected audio inputs on selection

TypeWhisper 1.2.2 is a stable maintenance release centered on the rebuilt OpenAI integration. The bundled OpenAI plugin is now presented as OpenAI / ChatGPT and can use either a traditional API key or a ChatGPT/Codex login for prompt processing.

Highlights

• OpenAI / ChatGPT login - the bundled OpenAI plugin now supports browser-based ChatGPT/Codex OAuth in addition to API-key auth.
• Better GPT-5 and Codex support - reasoning effort can be tuned directly in plugin settings, and the bundled model list now includes current GPT-5/Codex variants such as GPT-5.3-Codex-Spark.
• Fixed Codex response handling - the ChatGPT/Codex path now speaks the actual Codex Responses protocol, including the required request shape and SSE response parsing.

Fixes & Compatibility

• Fixed 400 failures from the ChatGPT/Codex endpoint caused by the old request format.
• Improved OpenAI OAuth compatibility for the browser login flow and Codex login import.
• Restored SDK compatibility for external plugins after extending the OpenAI chat helper, so older plugin builds keep loading correctly.
• The marketplace OpenAI / ChatGPT plugin now correctly requires TypeWhisper 1.2.2 or newer.

Bug Fixes

• guard incompatible transcription engines on Intel
• disable macOS 14 settings sidebar animation
• show script/region variants in language pickers
• use curated notes for GitHub releases

Other Changes

• cover script and region language display variants
• update stable release wording
• update stable release wording in README
• rename release readiness guide
• hide legacy 1.1 filename in README

New Features

• add whisper.cpp marketplace plugin

Bug Fixes

• add new plugins to marketplace registry workflow
• clear whisper model selection on unload

Other Changes

• harden CI and prepare v0.6.0 release
• Refine settings shell and localization
• Implement custom protocol handling and improve Discord claim integration
• Add supporter Discord claims and live profile context
• Refactor structured settings pages
• Polish settings, wizard, and snippets UX
• Overhaul Windows settings UI
• Fix Win hotkey modifier handling
• Add vocabulary boosting for local Parakeet transcription

TypeWhisper 1.2 is the new stable macOS release, focused on speed, reliability, and day-to-day polish. Dictation starts noticeably faster, background CPU use is lower while idle, and audio behavior is more resilient on real-world setups like AirPods, Bluetooth devices, and changing input routes.

Highlights

• Much faster dictation start – metadata capture and browser URL resolution no longer block the critical startup path.
• Lower idle CPU usage – background listeners were tightened up to reduce unnecessary CPU activity while TypeWhisper is idle.
• More reliable audio behavior – better recovery after AirPods, Bluetooth profile switches, and AVAudioEngine reconfiguration.
• Better day-to-day usability – a new Minimal indicator, transcript preview controls, and a more guided Rules workflow make TypeWhisper easier to use.

Speed & Efficiency

• Reduced dictation start latency by moving metadata capture and browser URL resolution off the critical path.
• Reduced unnecessary background CPU usage while TypeWhisper is idle.
• Improved handling for very short clips, especially when streaming preview is active or Parakeet is selected.
• Fixed streaming-preview and no-speech-guard behavior so brief speech is retained more reliably.

Reliability

• Hardened audio engine startup and teardown around AVAudioEngine race conditions.
• Improved recovery after AirPods and Bluetooth profile switches.
• Restored the selected Apple Speech model on app launch.
• Fixed engine startup so TypeWhisper auto-selects the configured engine more reliably.
• Fixed dictation start when no microphone is available, with a cleaner failure path.
• Fixed a hotkey event tap crash.
• Improved compatibility with remapped Hyperkey shortcuts and combo hotkeys, including Caps Lock edge cases.
• Fixed WhisperKit download progress so it stays attached to the selected model.
• Hardened bundled plugin installation and update flows so installed plugin bundles remain managed correctly.

Usability & Polish

• Added the new Minimal indicator style for a compact floating status view.
• Added a toggle to disable live transcript preview for Notch and Overlay indicators.
• Reframed Profiles as Rules with a guided editor for app- and website-based matching.
• Backported the modern settings sidebar so the updated navigation also works on macOS 14.
• Added an app visibility picker to choose between menu bar, Dock, or Dock-only-while-window-open behavior.
• Polished the notch indicator layout and matched its height more closely to the display safe area.
• Fixed multiple German localization issues and other small copy and layout regressions.
• Avoided unwanted clipboard history writes when clipboard preservation is enabled.

Add-ons & Platform Updates

• Added optional HuggingFace token support to the bundled Qwen3, Granite, and Voxtral MLX plugins for higher download limits and clearer download errors.
• Added the new Gemma 4 local LLM plugin via MLX for on-device prompt processing.
• Improved Gemma 4 prompt processing and bumped the bundled Gemma 4 plugin to 1.0.1.
• Localized built-in term pack metadata in English and German.
• Added the supporter Discord claim flow for eligible supporters.

Power Users & Developers

• Added dictation session IDs to API responses for local automation workflows.
• Added GPT-5 token parameter support to the OpenAI chat helper for SDK and plugin integrations.
• Improved plugin load diagnostics with structured OSLog logging.

Other Changes

• Add dictation session IDs to API responses

New Features

• improve Gemma4 prompt processing
• polish notch indicator layout and presentation (#257)
• backport settings sidebar to macOS 14

Bug Fixes

• keep WhisperKit download progress on selected model
• restore minimal indicator sources after merge
• keep installed dev plugins from deleting themselves
• add words label to usage tooltip

Other Changes

• add 1.2.0-rc5 release notes
• add PR guard workflow and CODEOWNERS
• enable Gemma4 plugin releases
• Add missing German localizations
• Fix hotkey event tap crash (Fixes #263)
• Add Gemma 4 local LLM plugin via MLX (#193)
• recreate build-release before logging (#261)
• Fix German localization for recording status feedback

Bug Fixes

• restore plugin ABI compatibility and log install failures