Model Voice & audio
Whisper large-v3
Open-source MIT-licensed multilingual speech recognition model by OpenAI supporting transcription, translation, and timestamps.
Open-source MIT-licensed multilingual speech recognition model by OpenAI supporting transcription, translation, and timestamps.
- Best for
- Transcription
- Pricing model
- Open source
- Platforms
- Self-host, API, CLI
- Active since
- N/A
What you can do
- MIT open-source weights
- Multilingual ASR & translation
- Word & segment timestamps
Listing & Verification
- ✓ Official source: github.com
- ✓ GitHub · 113248 stars
- ✓ Last verified: Nov 22, 2026 · Needs re-check (>90d)
- ✓ Official direct link only — no downloads, mirrors or proxy inference
Verified Community Reviews
No published user reviews yet. Star average appears once 5+ reviews are published.