Whisper is OpenAI’s open speech recognition model family for multilingual transcription and translation-related tasks, released with code and model weights.
AI Model Intelligence
Whisper
OpenAI · Whisper family · Audio → text
Intelligence Summary
Model- Model intelligence
- Developer OpenAI
- Family Whisper
- Modalities Audio → text
- API OpenAI API speech endpoints related to Whisper; also self-host open weights.
- Licensing MIT license for the open Whisper release.
- Deployment Self-host and OpenAI API.
- Documentation Official docs
- Last reviewed Jul 2026
All AI Models → · Official docs →
Editorial overview
Capabilities
- Automatic speech recognition
- Multilingual transcription
- Speech translation to English (as documented)
API availability
OpenAI API speech endpoints related to Whisper; also self-host open weights.
Deployment options
Self-host and OpenAI API.
Limitations
- Performance varies by audio quality and language
- Not a diarization system by itself
Related technologies
Related glossary terms
Why it matters
Whisper is tracked as a first-class model entity on Brel Digital so buyers and researchers can compare developer, modalities, licensing posture, and official documentation without relying on vendor marketing copy.
Related glossary terms
Last reviewed
Sources
Correction request
If a technology assignment or hub description is inaccurate, submit a correction via the Corrections Policy.
All technologies → · AI Models → · APIs & SDKs → · Integrations → · Compliance → · Browse all companies → · Explore industries → · Compare →