ggml-org/whisper.cpp

Port of OpenAI's Whisper model in C/C++

72
/ 100
Verified

This project helps anyone who needs to convert spoken audio into written text quickly and efficiently. You provide an audio file (like an MP3 or WAV) and it outputs an accurate transcript of what was said. This tool is ideal for researchers, journalists, content creators, or anyone needing to transcribe recordings without relying on cloud services.

47,665 stars. Actively maintained with 160 commits in the last 30 days.

Use this if you need to transcribe audio files directly on your computer or mobile device, ensuring privacy and fast processing without an internet connection.

Not ideal if you prefer using web-based transcription services or require features like speaker diarization and advanced editing tools.

audio-transcription voice-to-text podcast-production interview-analysis meeting-minutes
No Package No Dependents
Maintenance 25 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

47,665

Forks

5,311

Language

C++

License

MIT

Last pushed

Mar 18, 2026

Commits (30d)

160

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ggml-org/whisper.cpp"

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