Skip to content
OpenAI

gpt-realtime-whisper

gpt-realtime-whisper is a streaming speech-to-text model for realtime transcription, returning transcript text while audio is still arriving, with a tunable latency and accuracy tradeoff and pricing based on audio duration rather than tokens. Your use is subject to OpenAI's Terms & Privacy Policies.

Websockets
Use with AI GatewayView docs
import { experimental_streamTranscribe as streamTranscribe } from 'ai';
import { createGateway, gateway } from '@ai-sdk/gateway';
import { readFile } from 'node:fs/promises';


const modelId = 'openai/gpt-realtime-whisper';


// Mint this on your server, then send only the short-lived token to the client.
const { token } = await gateway.experimental_transcription.getToken({
  model: modelId,
});
const clientGateway = createGateway({ apiKey: token });


// Raw 24 kHz, 16-bit signed little-endian mono PCM audio.
const bytes = await readFile('audio.pcm');
const audio = new ReadableStream<Uint8Array>({
  start(controller) {
    controller.enqueue(new Uint8Array(bytes));
    controller.close();
  },
});


const result = streamTranscribe({
  model: clientGateway.transcription(modelId),
  audio,
  inputAudioFormat: { type: 'audio/pcm', rate: 24000 },
});


for await (const part of result.fullStream) {
  if (part.type === 'transcript-delta') {
    process.stdout.write(part.delta);
  }
}


console.log('\nFinal:', await result.text);
Read docs
OverviewAboutProvidersSimilarFAQ

Providers

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider
Input
Capabilities
ZDR
No Training
Release Date
OpenAI
Legal:Terms•Privacy
$1.02/hr
05/07/2026