ai/docs/07-reference/01-ai-sdk-core/11-transcribe.mdx

AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway or go direct to OpenAI, Anthropic, Google, or any other model provider.

---
title: transcribe
description: API Reference for transcribe.
---

# `transcribe()`

Generates a transcript from an audio file.

```ts
import { transcribe } from 'ai';
import { openai } from '@ai-sdk/openai';
import { readFile } from 'fs/promises';

const { text: transcript } = await transcribe({
  model: openai.transcription('gpt-4o-transcribe'),
  audio: await readFile('audio.mp3'),
});

console.log(transcript);
```

## Import

<Snippet text={`import { transcribe } from "ai"`} prompt={false} />

## API Signature

### Parameters

<PropertiesTable
  content={[
    {
      name: 'model',
      type: 'TranscriptionModelV4',
      description: 'The transcription model to use.',
    },
    {
      name: 'audio',
      type: 'DataContent (string | Uint8Array | ArrayBuffer | Buffer) | URL',
      description:
        'The audio file to generate the transcript from. HTTP(S) URLs are sent directly to models with native URL support unless a custom download function is supplied; other models download the audio locally.',
    },
    {
      name: 'timestampGranularities',
      type: "Array<'word' | 'segment'>",
      isOptional: true,
      description:
        'Word and segment timings to request. Supported by the OpenAI, Azure Speech, Vertex Gemini, and xAI adapters. Explicit provider options take precedence; these adapters warn about unavailable requested timings. AI Gateway warns that it does not forward this option; use provider options or a direct provider model. Omit this option to keep provider defaults. An empty array requests no additional timing detail; it does not suppress timings returned by default.',
    },
    {
      name: 'providerOptions',
      type: 'Record<string, JSONObject>',
      isOptional: true,
      description: 'Additional provider-specific options.',
    },
    {
      name: 'maxRetries',
      type: 'number',
      isOptional: true,
      description: 'Maximum number of retries. Default: 2.',
    },
    {
      name: 'abortSignal',
      type: 'AbortSignal',
      isOptional: true,
      description: 'An optional abort signal to cancel the call.',
    },
    {
      name: 'headers',
      type: 'Record<string, string>',
      isOptional: true,
      description: 'Additional HTTP headers for the request.',
    },
    {
      name: 'telemetry',
      type: 'TelemetryOptions',
      isOptional: true,
      description:
        'Telemetry configuration. Supports functionId, recordInputs, recordOutputs, isEnabled, and per-call integrations.',
    },
    {
      name: 'download',
      type: '(options: { url: URL; abortSignal?: AbortSignal }) => Promise<{ data: Uint8Array; mediaType: string | undefined }>',
      isOptional: true,
      description:
        'Custom download function for fetching audio from URLs. Supplying this option forces local downloading even for models with native URL support. Use `createDownload()` from `ai` to create a download function with a custom size limit (e.g. `createDownload({ maxBytes: 50 * 1024 * 1024 })`) or fetch transport (e.g. `createDownload({ fetch })` with `guarded-fetch` on Node.js for untrusted URLs). Default: native URL transcription when supported, otherwise built-in download with 2 GiB limit.',
    },
  ]}
/>

### Returns

<PropertiesTable
  content={[
    {
      name: 'text',
      type: 'string',
      description: 'The complete transcribed text from the audio input.',
    },
    {
      name: 'segments',
      type: 'Array<{ text: string; startSecond: number; endSecond: number }>',
      description:
        'An array of transcript segments, each containing a portion of the transcribed text along with its start and end times in seconds.',
    },
    {
      name: 'words',
      type: 'Array<{ text: string; startSecond: number; endSecond: number }>',
      isOptional: true,
      description:
        'Word-level timings when the adapter exposes them, including timings returned by default. Undefined when unavailable. Existing segments behavior is preserved: some providers also put word timings in segments.',
    },
    {
      name: 'language',
      type: 'string | undefined',
      description:
        'The language of the transcript in ISO-639-1 format e.g. "en" for English.',
    },
    {
      name: 'durationInSeconds',
      type: 'number | undefined',
      description: 'The duration of the transcript in seconds.',
    },
    {
      name: 'warnings',
      type: 'Warning[]',
      description:
        'Warnings from the model provider (e.g. unsupported settings).',
    },
    {
      name: 'providerMetadata',
      type: 'Record<string, JSONObject>',
      isOptional: true,
      description:
        'Optional metadata from the provider. The outer key is the provider name. The inner values are the metadata. Details depend on the provider.',
    },
    {
      name: 'responses',
      type: 'Array<TranscriptionModelResponseMetadata>',
      description:
        'Response metadata from the provider. There may be multiple responses if we made multiple calls to the model.',
      properties: [
        {
          type: 'TranscriptionModelResponseMetadata',
          parameters: [
            {
              name: 'timestamp',
              type: 'Date',
              description: 'Timestamp for the start of the generated response.',
            },
            {
              name: 'modelId',
              type: 'string',
              description:
                'The ID of the response model that was used to generate the response.',
            },
            {
              name: 'headers',
              type: 'Record<string, string>',
              isOptional: true,
              description: 'Response headers.',
            },
          ],
        },
      ],
    },
  ]}
/>