collabora/WhisperLive

A nearly-live implementation of OpenAI's Whisper.

68
/ 100
Established

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.

live-captioning meeting-transcription audio-to-text content-creation interview-analysis
No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

3,894

Forks

536

Language

Python

License

MIT

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.