← All models
GPT Realtime Whisper
whisper
Streaming speech-to-text model for low-latency transcript deltas from live audio
- Family
- whisper
- Providers
- 1
- Context
- 16,000
- Output
- 2,000
- Knowledge
- -
- Weights
- Closed
- Input
- audio
- Output
- text
- Release date
- 2026-05-07
- Updated
- 2026-05-07
Providers
Source: models.dev