# `transcribe()`

<Note type="warning">`transcribe` is an experimental feature.</Note>

Generates a transcript from an audio file.

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

const { text: transcript } = await transcribe({
  model: openai.transcription('whisper-1'),
  audio: await readFile('audio.mp3'),
});

console.log(transcript);
```

## Import

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

## API Signature

### Parameters

<PropertiesTable
  content={[
    {
      name: 'model',
      type: 'TranscriptionModelV3',
      description: 'The transcription model to use.',
    },
    {
      name: 'audio',
      type: 'DataContent (string | Uint8Array | ArrayBuffer | Buffer) | URL',
      description: 'The audio file to generate the transcript from.',
    },
    {
      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: 'download',
      type: '(options: { url: URL; abortSignal?: AbortSignal }) => Promise<{ data: Uint8Array; mediaType: string | undefined }>',
      isOptional: true,
      description:
        'Custom download function for fetching audio from URLs. Use `createDownload()` from `ai` to create a download function with custom size limits, e.g. `createDownload({ maxBytes: 50 * 1024 * 1024 })`. Default: 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: '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.',
            },
          ],
        },
      ],
    },
  ]}
/>


## Navigation

- [generateText](/docs/reference/ai-sdk-core/generate-text)
- [streamText](/docs/reference/ai-sdk-core/stream-text)
- [embed](/docs/reference/ai-sdk-core/embed)
- [embedMany](/docs/reference/ai-sdk-core/embed-many)
- [rerank](/docs/reference/ai-sdk-core/rerank)
- [generateImage](/docs/reference/ai-sdk-core/generate-image)
- [transcribe](/docs/reference/ai-sdk-core/transcribe)
- [generateSpeech](/docs/reference/ai-sdk-core/generate-speech)
- [experimental_generateVideo](/docs/reference/ai-sdk-core/generate-video)
- [Agent (Interface)](/docs/reference/ai-sdk-core/agent)
- [ToolLoopAgent](/docs/reference/ai-sdk-core/tool-loop-agent)
- [createAgentUIStream](/docs/reference/ai-sdk-core/create-agent-ui-stream)
- [createAgentUIStreamResponse](/docs/reference/ai-sdk-core/create-agent-ui-stream-response)
- [pipeAgentUIStreamToResponse](/docs/reference/ai-sdk-core/pipe-agent-ui-stream-to-response)
- [tool](/docs/reference/ai-sdk-core/tool)
- [dynamicTool](/docs/reference/ai-sdk-core/dynamic-tool)
- [createMCPClient](/docs/reference/ai-sdk-core/create-mcp-client)
- [Experimental_StdioMCPTransport](/docs/reference/ai-sdk-core/mcp-stdio-transport)
- [jsonSchema](/docs/reference/ai-sdk-core/json-schema)
- [zodSchema](/docs/reference/ai-sdk-core/zod-schema)
- [valibotSchema](/docs/reference/ai-sdk-core/valibot-schema)
- [Output](/docs/reference/ai-sdk-core/output)
- [ModelMessage](/docs/reference/ai-sdk-core/model-message)
- [UIMessage](/docs/reference/ai-sdk-core/ui-message)
- [validateUIMessages](/docs/reference/ai-sdk-core/validate-ui-messages)
- [safeValidateUIMessages](/docs/reference/ai-sdk-core/safe-validate-ui-messages)
- [createProviderRegistry](/docs/reference/ai-sdk-core/provider-registry)
- [customProvider](/docs/reference/ai-sdk-core/custom-provider)
- [cosineSimilarity](/docs/reference/ai-sdk-core/cosine-similarity)
- [wrapLanguageModel](/docs/reference/ai-sdk-core/wrap-language-model)
- [wrapImageModel](/docs/reference/ai-sdk-core/wrap-image-model)
- [LanguageModelV3Middleware](/docs/reference/ai-sdk-core/language-model-v2-middleware)
- [extractReasoningMiddleware](/docs/reference/ai-sdk-core/extract-reasoning-middleware)
- [simulateStreamingMiddleware](/docs/reference/ai-sdk-core/simulate-streaming-middleware)
- [defaultSettingsMiddleware](/docs/reference/ai-sdk-core/default-settings-middleware)
- [addToolInputExamplesMiddleware](/docs/reference/ai-sdk-core/add-tool-input-examples-middleware)
- [extractJsonMiddleware](/docs/reference/ai-sdk-core/extract-json-middleware)
- [stepCountIs](/docs/reference/ai-sdk-core/step-count-is)
- [hasToolCall](/docs/reference/ai-sdk-core/has-tool-call)
- [isLoopFinished](/docs/reference/ai-sdk-core/loop-finished)
- [simulateReadableStream](/docs/reference/ai-sdk-core/simulate-readable-stream)
- [smoothStream](/docs/reference/ai-sdk-core/smooth-stream)
- [generateId](/docs/reference/ai-sdk-core/generate-id)
- [createIdGenerator](/docs/reference/ai-sdk-core/create-id-generator)
- [DefaultGeneratedFile](/docs/reference/ai-sdk-core/default-generated-file)


[Full Sitemap](/sitemap.md)