collabora/WhisperLive
A nearly-live implementation of OpenAI's Whisper.
This tool helps professionals instantly convert spoken language into written text, whether it's from a live microphone feed or a pre-recorded audio file. It takes your speech as input and provides accurate, real-time transcription as text output. Anyone who needs fast, reliable audio-to-text conversion for meetings, interviews, or content creation would find this useful.
3,894 stars. Actively maintained with 6 commits in the last 30 days.
Use this if you need to transcribe spoken words into text almost immediately, allowing for live captions, meeting notes, or quick analysis of audio content.
Not ideal if you need a desktop application with a graphical user interface or if you require advanced audio editing features alongside transcription.
Stars
3,894
Forks
536
Language
Python
License
MIT
Category
Last pushed
Mar 17, 2026
Commits (30d)
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/collabora/WhisperLive"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
Kieirra/murmure
Fully local, private and cross platform Speech-to-Text with LLM Post-processing
Softcatala/whisper-ctranslate2
Whisper command line client compatible with original OpenAI client based on CTranslate2.
pavelzbornik/whisperX-FastAPI
FastAPI service on top of WhisperX
royshil/obs-localvocal
OBS plugin for local speech recognition and captioning using AI
kurianbenoy/whisper_normalizer
A python package for whisper normalizer