About
OpenAI's open-source speech recognition model. Highly accurate transcription and translation across 96+ languages. Can run locally, powers many third-party transcription tools.
Features
- Multilingual transcription: supports 96+ languages with language auto-detection
- Translation mode: directly translates any supported language into English text
- Word-level timestamps: generate precise timing for each word (enabled with 'word_timestamps=True')
- Multiple model sizes: from tiny (39M parameters) to large-v3 (1.5B parameters)
- Robust to noise: trained on diverse audio conditions including music, echo, and crowd noise
Links
Categories
Reviews
4.6
Write a Review
Get new AI tools weekly
Subscribe to our newsletter and never miss a tool.
Get new AI tools weekly
Subscribe to our newsletter and never miss a tool.