LLM ReferenceLLM Reference
OpenAI API

GPT Realtime Whisper on OpenAI API

GPT Realtime 2 · OpenAI

Serverless

Why use GPT Realtime Whisper on OpenAI API?

OpenAI API offers GPT Realtime Whisper with competitive pricing. OpenAI is a leading AI research and deployment company dedicated to developing safe and beneficial artificial general intelligence (AGI) for humanity.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

About GPT Realtime Whisper

GPT Realtime Whisper is OpenAI's streaming speech-to-text model, released May 7, 2026. It transcribes spoken audio live as a speaker talks rather than waiting for utterance completion, making it suitable for live captions, meeting notes, classroom transcripts, and real-time agent pipelines. The model is exposed through /v1/realtime/transcription_sessions and is priced per minute at $0.017 rather than per token.

FAQ

What API model ID do I use for GPT Realtime Whisper on OpenAI API?

Use the model ID gpt-realtime-whisper when calling OpenAI API's API.

Who created GPT Realtime Whisper?

GPT Realtime Whisper was created by OpenAI as part of the GPT Realtime 2 model family.

Is GPT Realtime Whisper open source?

GPT Realtime Whisper is not open source; the seed data lists it as proprietary.

Get Started

Model Specs

Released2026-05-07
Architecturetransformer

Related Models on OpenAI API