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.

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.

OpenAI-compatible transcription via Cloudflare Tunnel with service token authentication.

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

Cloud transcription via ElevenLabs Scribe v2 with low-latency realtime streaming and REST fallback.

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

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

LLM processing powered by Google's Gemini 2.5 model family for custom prompts.

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

Cloud transcription via Google Cloud Speech-to-Text using a service-account JSON key with automatic chunking for long recordings.

IBM Granite Speech-to-Text running locally on Apple Silicon with MLX.

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

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.

Save transcriptions directly to your Obsidian vault with auto-detection, daily notes, and frontmatter support.

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

Cloud-based semantic memory storage using the OpenAI Vector Store API.

Cloud transcription and LLM processing using OpenAI's Whisper and GPT models.

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

Local MLX-based speech recognition powered by Qwen3. Runs entirely on-device.

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

Local speech recognition using Mistral's Voxtral model via MLX with streaming support.

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

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

A minimal example LLM plugin demonstrating the TypeWhisperPluginSDK.