Whisper-1 — reviews, specs & pricing
OpenAI's speech-to-text transcription model.
Summary
Whisper is a general-purpose speech recognition model trained on diverse multilingual audio. It's available open-source and via OpenAI's API. It handles transcription and translation across many languages.
Sample use case
Used for transcription services, subtitles, and voice interfaces. Also used in accessibility tools.
Specifications
- Provider: openai
- License: closed
- Released: 2023-03-01
Pros
- Multilingual
- Open-source version available
- Robust to noise
Cons
- Can hallucinate text
- No speaker diarization built-in
- Latency for long audio
Average rating 0.0 from 0 community reviews on Reviuws.