GPT Realtime Whisper
Streaming speech-to-text model for live audio, delivering transcripts as the speaker talks.
- Input price
- —
- Output price
- —
- Context
- 128K
- Max output
- —
- Modalities
- InputAudioOutputText
- Capability
- —
- 30-day uptime
- —
- Released
- 2026-11-04
- Knowledge cutoff
- —
Speech to text
Providers
This model is served by the dedicated providers below. We pick the provider for each request, so provider preferences don’t apply, including a provider named in your request. Prices in USD per 1M tokens. Need a custom setup? Contact [email protected].
Included providers1
- SuccessTTFT
- OpenAIUnited States——
Pricing
Prices for this model. Each request is billed at these prices, whichever provider serves it.
- Transcription
- $0.000256list $0.000284-10%
- per second
Similar models
Other models with the same output types at a similar price.