#191 · Primary category： Speech & Audio
speech-to-text
Real-time transcription using faster-whisper
Project last updated：07/23/24
GitHub Stars
614
Forks
99
Contributors
1
License
MIT
Why we included this project
This desktop app turns a microphone feed into live text, with faster-whisper doing the transcription and Silero VAD splitting audio into speech segments so each one is transcribed as a unit. Well-separated sentences come back in under a second on a mid-range GPU like an RTX 3060. The browser-based GUI lets you adjust model size, VAD thresholds, and transcription settings without editing code, and it also handles audio files in wav, mp3, and ogg, exports SRT subtitles, and streams results over WebSocket for live captions. An optional OpenAI API hook can proofread the output. For meeting notes, live-stream subtitles, or accessibility work, this covers the plumbing so you can build on top of it.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
whisper.cpp
Port of OpenAI's Whisper model in C/C++
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production