Whisper V3
by OpenAI · open-source · Last verified 2026-03-17
OpenAI's state-of-the-art open-source automatic speech recognition model trained on 680K hours of multilingual audio. Supports 99 languages with near-human accuracy and includes translation, timestamp, and language detection capabilities.
https://openai.com/research/whisper ↗B+
B+—Good
Adoption: A+Quality: A+Freshness: B+Citations: A+Engagement: F
Specifications
- License
- MIT
- Pricing
- open-source
- Capabilities
- speech-recognition, multilingual-transcription, translation, timestamp-generation, language-detection
- Integrations
- huggingface, azure-openai, langchain, ffmpeg
- Use Cases
- transcription, subtitling, voice-assistants, meeting-notes, podcast-indexing
- API Available
- Yes
- Parameters
- 1.55B
- Context Window
- 30 seconds (chunked processing)
- Modalities
- audio-to-text
- Training Cutoff
- N/A
- Tags
- speech-to-text, transcription, multilingual, open-source, audio
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
77Adoption
90
Quality
90
Freshness
70
Citations
92
Engagement
0