GPT Transcribe
GPT Transcribe is a high-accuracy speech-to-text model for completed audio files, streamed file transcripts, and committed turns in Realtime sessions. It supports context, keyword hints, and multiple language hints. Priced by audio duration. Your use is subject to OpenAI's Terms & Privacy Policies.
- Price
- $0.27, Per hour of audio
import { experimental_transcribe as transcribe } from 'ai';import { gateway } from '@ai-sdk/gateway';import { readFile } from 'node:fs/promises';
const result = await transcribe({ model: gateway.transcriptionModel('openai/gpt-transcribe'), audio: await readFile('audio.mp3'),});Copy link to headingPlayground
Try out GPT Transcribe by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Speech to text
Record a short clip from your microphone and the model transcribes it to text.
Record a clip to see the transcript here.
Copy link to headingProviders
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 |
|---|