faster-whisper
Open source · Voice and TTS · SYSTRAN/faster-whisper
What it does
faster-whisper is a faster reimplementation of OpenAI's Whisper speech-to-text model. It turns audio into text with timestamps and uses less memory than the original.
Good for: Transcribing recordings, podcasts or calls on your own machine.
faster-whisper on GitHub (opens in a new tab)
Visitor votes, one per browser. Your own vote is kept on this device only. How votes work.
The signals we checked
- Licence
- MIT (OSI-approved open-source licence)
- Popularity
- Stars: 25,883 (checked 16 Oct 2026)
- Last commit
- 15 Oct 2026
- Open issues and PRs
- 24
- Status
- Active (not archived)
- Self-host
- ModeratePython package; works on CPU, much quicker with an NVIDIA GPU.
- GitHub topics
- deep-learning
- inference
- openai
- quantization
- speech-recognition
- speech-to-text
- transformer
- whisper
More in voice and tts
- whisper.cpp Offline transcription on modest hardware, or inside your own app.
- Chatterbox Generating voiceover locally, as long as you have the rights to any voice you clone.
- Piper Offline speech for home automation, assistants or accessibility tools.
No affiliate links on this page, and we are not paid by this project. The summary is our own plain-English description; check the repo for current features before you rely on it.
Stars, licences and commit dates come from the GitHub API, checked 16 Oct 2026. "Last commit" is the last push to the repo. Star counts are a rough popularity signal, not a quality score. There are no affiliate links in this section: links go straight to each project.