kstonekuan/tambourine-voice
Your personal voice interface for any app. Speak naturally and your words appear wherever your cursor is, with fully customizable AI voice dictation. Open source alternative to Wispr Flow.
Built on the Pipecat framework, it uses a Tauri-based desktop app communicating via WebRTC to a Python server that chains together modular STT and LLM providers—supporting everything from cloud APIs (Deepgram, OpenAI, Anthropic) to fully local models (Whisper, Ollama). Beyond basic transcription, it applies context-aware formatting rules that detect the active application and adjust output style accordingly (e.g., formal tone for email, casual for messaging), with customizable prompts and personal dictionaries to handle technical terminology and proper nouns.
313 stars.
Stars
313
Forks
66
Language
Rust
License
AGPL-3.0
Category
Last pushed
Mar 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/kstonekuan/tambourine-voice"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
amicalhq/amical
🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓...
Notely-Voice/NotelyVoice
A 100% private AI voice transcription app that converts speech to text in 100+ languages. Built...
Saik0s/Whisperboard
The open-source iOS app that's making quality voice transcription more accessible on mobile devices.
sveinbjornt/hear
Command line interface for the built-in speech recognition and transcription capabilities in macOS.
233stone/vocotype-cli
VocoType 是一款运行在本地端侧的隐私安全语音输入工具，通过快捷键即可将语音实时转换为文字并自动输入到当前应用。支持语音转文字MCP、AI...