`generateSpeech()`

generateSpeech is an experimental feature.

Generates speech audio from text.

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 from the AI SDK!',
});

console.log(audio);

Import

import { experimental_generateSpeech as generateSpeech } from "ai"

API Signature

Parameters

model:

SpeechModelV1

text:

string

voice?:

string

outputFormat?:

string

instructions?:

string

speed?:

number

providerOptions?:

Record<string, Record<string, JSONValue>>

maxRetries?:

number

abortSignal?:

AbortSignal

headers?:

Record<string, string>

Returns

audio:

GeneratedAudioFile

base64:

string

uint8Array:

Uint8Array

mimeType:

string

format:

string

warnings:

SpeechWarning[]

responses:

Array<SpeechModelResponseMetadata>

SpeechModelResponseMetadata

timestamp:

Date

modelId:

string

headers?:

Record<string, string>