`generateSpeech()`

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

Generates speech audio from text.

import { experimental_generateSpeech as generateSpeech } from 'ai';
import { openai } from '@ai-sdk/openai';

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

console.log(audio);

Examples

OpenAI

import { experimental_generateSpeech as generateSpeech } from 'ai';
import { openai } from '@ai-sdk/openai';

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

ElevenLabs

import { experimental_generateSpeech as generateSpeech } from 'ai';
import { elevenlabs } from '@ai-sdk/elevenlabs';

const { audio } = await generateSpeech({
  model: elevenlabs.speech('eleven_multilingual_v2'),
  text: 'Hello from the AI SDK!',
  voice: 'your-voice-id', // Required: get this from your ElevenLabs account
});

Import

API Signature

Parameters

<PropertiesTable content={[ { name: 'model', type: 'SpeechModelV4', description: 'The speech model to use.', }, { name: 'text', type: 'string', description: 'The text to generate the speech from.', }, { name: 'voice', type: 'string', isOptional: true, description: 'The voice to use for the speech.', }, { name: 'outputFormat', type: 'string', isOptional: true, description: 'The output format to use for the speech e.g. "mp3", "wav", etc.', }, { name: 'instructions', type: 'string', isOptional: true, description: 'Instructions for the speech generation.', }, { name: 'speed', type: 'number', isOptional: true, description: 'The speed of the speech generation.', }, { name: 'language', type: 'string', isOptional: true, description: 'The language for speech generation. This should be an ISO 639-1 language code (e.g. "en", "es", "fr") or "auto" for automatic language detection. Provider support varies.', }, { 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.', }, ]} />

Returns

<PropertiesTable content={[ { name: 'audio', type: 'GeneratedAudioFile', description: 'The generated audio.', properties: [ { type: 'GeneratedAudioFile', parameters: [ { name: 'base64', type: 'string', description: 'Audio as a base64 encoded string.', }, { name: 'uint8Array', type: 'Uint8Array', description: 'Audio as a Uint8Array.', }, { name: 'mediaType', type: 'string', description: 'Media type of the audio (e.g. "audio/mpeg").', }, { name: 'format', type: 'string', description: 'Format of the audio (e.g. "mp3").', }, ], }, ], }, { 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<SpeechModelResponseMetadata>', description: 'Response metadata from the provider. There may be multiple responses if we made multiple calls to the model.', properties: [ { type: 'SpeechModelResponseMetadata', 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: 'body', isOptional: true, type: 'unknown', description: 'Optional response body.', }, { name: 'headers', type: 'Record<string, string>', isOptional: true, description: 'Response headers.', }, ], }, ], }, ]} />