Add-ons

Native on-device transcription using Apple's Speech framework with real-time streaming results.

Cloud transcription using AssemblyAI's Universal models with real-time WebSocket streaming and REST fallback.

Use signed-in Codex, Claude, OpenCode, and Antigravity CLIs as isolated LLM providers on macOS and Windows.

Local Canary speech recognition on Apple silicon, with the Sophea model for Greek and English and import of compatible models.

Cloud speech-to-text and text-to-speech via Cartesia APIs. Requires a Cartesia API key.

Ultra-fast cloud LLM inference powered by Cerebras Wafer-Scale Engine hardware.

LLM processing via Anthropic's Claude API for custom prompts and text workflows.

Transcription through a Cloudflare Tunnel on macOS or Cloudflare Workers AI on Windows.

Local Cohere Transcribe 03-2026 speech recognition via GGUF and CrispASR on macOS and Windows.

Cohere Transcribe speech recognition on macOS and Windows, plus Cohere Command LLM workflows on Windows.

Local streaming transcription with NetEase Youdao's Confucius4-R2T2 model, run through an audio.cpp server on your Mac.

Real-time cloud transcription via Deepgram's Nova models with WebSocket streaming and smart formatting.

Cloud transcription via ElevenLabs Scribe v2 with realtime streaming, REST fallback and word timestamps.

Local, offline memory storage using JSON files with text-based search.

Remove configurable filler words from transcriptions before they are inserted.

Fast cloud transcription and LLM inference powered by Fireworks AI's optimized model serving.

Google Gemini cloud transcription and Gemini/Gemma workflows on macOS and Windows.

Local LLM provider for Windows workflows that runs Gemma 3 GGUF models on the CPU with the bundled llama.cpp runtime.

Local Russian speech recognition with GigaAM v3 by Sber, including punctuation and capitalization.

Real-time cloud transcription with Gladia Solaria, plus automatic fallback to pre-recorded processing.

Google Cloud Speech-to-Text with service-account authentication and chunking for long recordings.

IBM Granite Speech locally through MLX on macOS or Python/PyTorch on Windows.

Ultra-fast cloud transcription and LLM processing powered by Groq's custom LPU hardware.

Review and manually contribute corrected dictation text to help improve TypeWhisper.

Create Linear issues from voice input using custom prompts and the Action Plugin system.

A floating window that shows your transcription in real time as you speak.

Run GGUF models on your Mac with llama.cpp and Metal, including single-file GGUF models from Hugging Face or your own .gguf file. No API key required.

Local LLM on Apple Silicon via MLX with Gemma 4, Qwen3.5, and LFM2.5 models. No API key required.

Connect TypeWhisper workflows to MCP tools over stdio or Streamable HTTP and turn dictated or selected text into fixed actions.

Store and search workflow memories in MemPalace Cloud or a self-hosted instance.

Muse Voice Transcribe for cloud transcription and Muse Spark for LLM workflows on Windows and macOS.

Cloud transcription with Microsoft MAI Transcribe through Azure Speech, including language detection, terminology biasing, transcript styles, timestamps, and optional speaker diarization.

Mistral cloud transcription with Voxtral Transcribe 3, live text through Voxtral Realtime, and Mistral text models for workflows.

Save TypeWhisper transcriptions as Markdown notes directly inside your Obsidian vault.

Universal adapter for any OpenAI-compatible API - connect Ollama, LM Studio, vLLM, and more.

Semantic memories stored in OpenAI Vector Stores.

Cloud transcription, OpenAI/ChatGPT prompts, and text-to-speech. Use an API key for STT/TTS or ChatGPT login for prompts.

Cloud transcription and LLM workflows through OpenRouter with model catalogs and pricing, plus the account balance on macOS.

Ultra-fast local transcription using NVIDIA's Parakeet TDT model, optimized for Apple Silicon.

Qwen3-ASR locally through MLX on macOS or sherpa-onnx on Windows.

Cloud transcription via the Reson8 speech-to-text API with real-time WebSocket streaming. Requires an API key.

Cloud transcription via the Sber SaluteSpeech REST API. Requires a user-supplied SaluteSpeech Authorization Key.

Run shell scripts on transcribed text for custom text transformations and processing pipelines.

Offline transcription on Windows with NVIDIA Parakeet, Parakeet Ultra and Canary, on the CPU or, for Parakeet, on any graphics card with Vulkan.

Cloud transcription via the Smallest AI Pulse STT API on both platforms, with Lightning text-to-speech on Windows. Requires a Smallest API key.

Soniox regional cloud transcription with live dictation on both platforms, plus text-to-speech on macOS.

Real-time cloud transcription via Speechmatics with Enhanced and Standard models and configurable server region.

Experimental local text-to-speech with Supertonic 3 ONNX models. Requires accepting the OpenRAIL-M model license before downloading model assets.

Read text aloud with the voices installed in macOS.

Cloud transcription and LLM workflows through Vercel AI Gateway with one API key, model catalogs, pricing, and credit balance.

Mistral's Voxtral speech recognition running locally on your Mac through MLX.

Import audio from supported web links into the TypeWhisper file transcription queue.

Send transcriptions to any HTTP endpoint for custom integrations and automations.

Offline Whisper transcription on Windows with whisper.cpp, on the CPU or on a graphics card with NVIDIA CUDA or Vulkan.

Local on-device transcription using WhisperKit with CoreML, optimized for Apple Silicon.

Cloud LLM, speech-to-text, and text-to-speech via xAI Grok APIs on macOS and Windows.