Speech

Generates audio from the input text.

npm i @xsai/generate-speech

Examples

import {  } from '@xsai/generate-speech'
import {  } from 'node:buffer'

const  = await ({
  : 'http://localhost:5050',
  : 'Hello, I am your AI assistant! Just let me know how I can help bring your ideas to life.',
  : 'tts-1',
  : 'en-US-AnaNeural',
})

const  = .()

Edit on GitHub

Structured Data

Generates structured data for a given prompt and schema.

Transcription

Transcribes audio into the input language.

Speech

Examples

On this page