🎙️ VoiceCraft - AI-Powered Voice Processing Platform

English | 简体中文

A powerful AI voice processing platform that integrates Text-to-Speech (TTS) functionality. Based on Microsoft Edge TTS, it supports dozens of voice options, providing users with a complete voice processing solution.

Live Demo: https://tts.pptboard.com

✨ Features

• 🗣️ Text-to-Speech (TTS) - Powered by Microsoft Edge TTS, supporting 20+ Chinese voices and dozens of foreign languages.
• 🌍 Multi-language Support - Fully supports 16 UI languages.
• ⚡ Instant Generation - Generates high-quality audio files instantly.
• 🆓 Completely Free - No registration required, no usage limits.
• 📱 Responsive Design - Perfectly adapts to desktop and mobile devices, with full dark mode support.
• 🎛️ Rich Parameters - Adjust speech rate, pitch, and voice styles easily.
• 📥 Downloadable Audio - Generated audio can be directly downloaded in MP3 format.
• 🔗 API Compatibility - Fully compatible with the OpenAI TTS API format.

🚀 One-Click Deployment

You can quickly deploy the frontend UI of this project using the buttons below:

Deploy to Vercel

Thanks to Nuxt 3's zero-config capabilities, you can simply click the Vercel button above to deploy. Vercel will automatically detect and build the Nuxt frontend as well as the Serverless API.

Deploy to Cloudflare Pages

The repository includes a wrangler.toml configuration file. Click the Cloudflare button above to deploy the frontend globally via Cloudflare Pages.

---

🎯 Quick Start (Local Development)

Requirements

• Node.js (v18+)
• pnpm (v8+)

🚀 Installation & Run

# Clone the repository
git clone https://github.com/iss-tools/edge-tts-demo.git
cd edge-tts-demo

# Install dependencies
pnpm install

# Start the development server (Nuxt 3 Full-stack)
pnpm dev

• Web UI & API: http://localhost:3000

🔌 API Usage

The built-in Nitro server provides a fully OpenAI-compatible Text-to-Speech endpoint at /v1/audio/speech.

# cURL Example
curl -X POST "http://localhost:3000/v1/audio/speech" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Hello, this is a test",
    "voice": "en-US-AriaNeural",
    "speed": 1.0,
    "pitch": "0"
  }' \
  --output speech.mp3

📝 Git Commit Conventions

This project uses Husky, commitlint, and lint-staged to enforce code quality and standard commit messages. Your commit messages must follow the Conventional Commits format.

Supported prefixes include:

• feat: A new feature
• fix: A bug fix
• docs: Documentation only changes
• style: Changes that do not affect the meaning of the code (white-space, formatting, missing semi-colons, etc)
• refactor: A code change that neither fixes a bug nor adds a feature
• perf: A code change that improves performance
• test: Adding missing tests or correcting existing tests
• chore: Changes to the build process or auxiliary tools and libraries such as documentation generation

Example: git commit -m "feat: add user login"

Note: ESLint will automatically format your code during the pre-commit phase. Ensure your code passes all linting rules.

🤝 Contributing

Issues and Pull Requests are always welcome!

📄 License

MIT License