OpenAI · whisper family
Streaming speech-to-text model for low-latency transcript deltas from live audio
Provider-specific prices and limits stay separate from canonical model facts.
| Provider | Provider model ID | Input | Output | Context | Output limit |
|---|---|---|---|---|---|
| Vercel AI Gateway | openai/gpt-realtime-whisper | Unknown | Unknown | Unknown | Unknown |
Attachments
No
Reasoning
No
Tool calling
No
Structured output
Unknown
Temperature
Yes