# Speech

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

The AI SDK provides the [`generateSpeech`](/docs/reference/ai-sdk-core/generate-speech)
function to generate speech from text using a speech model.

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

const audio = await generateSpeech({
  model: openai.speech('tts-1'),
  text: 'Hello, world!',
  voice: 'alloy',
});
```

To access the generated audio:

```ts
const audio = audio.audioData; // audio data e.g. Uint8Array
```

## Settings

### Provider-Specific settings

You can set model-specific settings with the `providerOptions` parameter.

```ts highlight="8-12"
import { experimental_generateSpeech as generateSpeech } from 'ai';
import { openai } from '@ai-sdk/openai';
import { readFile } from 'fs/promises';

const audio = await generateSpeech({
  model: openai.speech('tts-1'),
  text: 'Hello, world!',
  providerOptions: {
    openai: {
      // ...
    },
  },
});
```

### Abort Signals and Timeouts

`generateSpeech` accepts an optional `abortSignal` parameter of
type [`AbortSignal`](https://developer.mozilla.org/en-US/docs/Web/API/AbortSignal)
that you can use to abort the speech generation process or set a timeout.

```ts highlight="8"
import { openai } from '@ai-sdk/openai';
import { experimental_generateSpeech as generateSpeech } from 'ai';
import { readFile } from 'fs/promises';

const audio = await generateSpeech({
  model: openai.speech('tts-1'),
  text: 'Hello, world!',
  abortSignal: AbortSignal.timeout(1000), // Abort after 1 second
});
```

### Custom Headers

`generateSpeech` accepts an optional `headers` parameter of type `Record<string, string>`
that you can use to add custom headers to the speech generation request.

```ts highlight="8"
import { openai } from '@ai-sdk/openai';
import { experimental_generateSpeech as generateSpeech } from 'ai';
import { readFile } from 'fs/promises';

const audio = await generateSpeech({
  model: openai.speech('tts-1'),
  text: 'Hello, world!',
  headers: { 'X-Custom-Header': 'custom-value' },
});
```

### Warnings

Warnings (e.g. unsupported parameters) are available on the `warnings` property.

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

const audio = await generateSpeech({
  model: openai.speech('tts-1'),
  text: 'Hello, world!',
});

const warnings = audio.warnings;
```

### Error Handling

When `generateSpeech` cannot generate a valid audio, it throws a [`AI_NoAudioGeneratedError`](/docs/reference/ai-sdk-errors/ai-no-audio-generated-error).

This error can arise for any the following reasons:

- The model failed to generate a response
- The model generated a response that could not be parsed

The error preserves the following information to help you log the issue:

- `responses`: Metadata about the speech model responses, including timestamp, model, and headers.
- `cause`: The cause of the error. You can use this for more detailed error handling.

```ts
import {
  experimental_generateSpeech as generateSpeech,
  AI_NoAudioGeneratedError,
} from 'ai';
import { openai } from '@ai-sdk/openai';
import { readFile } from 'fs/promises';

try {
  await generateSpeech({
    model: openai.speech('tts-1'),
    text: 'Hello, world!',
  });
} catch (error) {
  if (AI_NoAudioGeneratedError.isInstance(error)) {
    console.log('AI_NoAudioGeneratedError');
    console.log('Cause:', error.cause);
    console.log('Responses:', error.responses);
  }
}
```

## Speech Models

| Provider                                                   | Model             |
| ---------------------------------------------------------- | ----------------- |
| [OpenAI](/providers/ai-sdk-providers/openai#speech-models) | `tts-1`           |
| [OpenAI](/providers/ai-sdk-providers/openai#speech-models) | `tts-1-hd`        |
| [OpenAI](/providers/ai-sdk-providers/openai#speech-models) | `gpt-4o-mini-tts` |
| [LMNT](/providers/ai-sdk-providers/lmnt#speech-models)     | `aurora`          |
| [LMNT](/providers/ai-sdk-providers/lmnt#speech-models)     | `blizzard`        |
| [Hume](/providers/ai-sdk-providers/hume#speech-models)     | `default`         |

Above are a small subset of the speech models supported by the AI SDK providers. For more, see the respective provider documentation.


## Navigation

- [Overview](/v4/docs/ai-sdk-core/overview)
- [Generating Text](/v4/docs/ai-sdk-core/generating-text)
- [Generating Structured Data](/v4/docs/ai-sdk-core/generating-structured-data)
- [Tool Calling](/v4/docs/ai-sdk-core/tools-and-tool-calling)
- [Prompt Engineering](/v4/docs/ai-sdk-core/prompt-engineering)
- [Settings](/v4/docs/ai-sdk-core/settings)
- [Embeddings](/v4/docs/ai-sdk-core/embeddings)
- [Image Generation](/v4/docs/ai-sdk-core/image-generation)
- [Transcription](/v4/docs/ai-sdk-core/transcription)
- [Speech](/v4/docs/ai-sdk-core/speech)
- [Language Model Middleware](/v4/docs/ai-sdk-core/middleware)
- [Provider & Model Management](/v4/docs/ai-sdk-core/provider-management)
- [Error Handling](/v4/docs/ai-sdk-core/error-handling)
- [Testing](/v4/docs/ai-sdk-core/testing)
- [Telemetry](/v4/docs/ai-sdk-core/telemetry)


[Full Sitemap](/sitemap.md)