All Models

gpt realtime whisper

whisper

Streaming speech-to-text model for low-latency transcript deltas from live audio

Providers1
ReleasedMay 7, 2026
Input Modalitiesaudio
Output Modalitiestext

Available Providers (1)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
Vercel AI Gatewayopenai/gpt-realtime-whisper/MTok/MTok

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output