tts-ai

tts-ai

Description

The Text-to-Speech Library provides a simple unified interface for generating high-quality speech audio using top text-to-speech providers like OpenAI, Google Cloud, and ElevenLabs.

With just a few lines of code, you can produce natural human-like voice audio for your applications and products.

Features

• Unified API for multiple TTS providers
• Generate audio from text with speak() method
• Split long text into chunks automatically
• Switch voices and models easily
• Save generated audio to file
• Seamlessly concatenate audio fragments
• Handles provider authentication
• MIT license

Getting Started

Install

pnpm add tts-ai

Usage

Without .env file

import { TtsOpenAI } from 'tts-ai';

const uploadToS3 = (audio: ArrayBuffer) => {
  // upload
};
const tts = new TtsOpenAI({
  apiKey: 'YOUR_API_KEY',
  uploadHandler: uploadToS3,
});

await tts.speak('Hello world');
await tts.upload();

With .env file

OpenAi_TTS_API_KEY = YOUR_API_KEY

import { TtsOpenAI } from 'tts-ai';

const tts = new TtsOpenAI();

await tts.speak('Hello world');
await tts.save();

See documentation for full usage details.

Providers

The library supports the following text-to-speech providers:

• OpenAI
• Google Cloud
• ElevenLabs

Contributing

Contributions are welcome!

License

This project is licensed under the MIT license.