revdotcom/reverb

Open source inference code for Rev's model

41
/ 100
Emerging

This tool helps you convert audio recordings into text and identify who is speaking at different times. It takes audio files like MP3s and outputs a written transcript, optionally with speaker labels. Researchers, journalists, or analysts who work with spoken content can use this to quickly process interviews, meetings, or other audio data.

435 stars. No commits in the last 6 months.

Use this if you need to accurately transcribe audio into text and distinguish between multiple speakers in your recordings.

Not ideal if your primary need is real-time transcription for live conversations or if you require an offline solution that is not self-hosted.

audio-transcription speaker-identification qualitative-research meeting-analysis podcast-production
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

435

Forks

27

Language

Python

License

Apache-2.0

Last pushed

Apr 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/revdotcom/reverb"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.