API Documentation

Unified TTS Interface Documentation

Welcome to UnifiedTTS API

UnifiedTTS provides a unified text-to-speech interface, aggregating multiple TTS providers to offer you rich speech synthesis choices.

Quick Start

1. Get API Key

First, you need to register an account and get your API Key for authentication.

2. Choose Model

View all available TTS models through the models list API.

3. Make Request

Use the TTS API for text-to-speech processing.

Example Request

curl -X POST https://unifiedtts.com/api/v1/common/tts-sync \
    -H "X-API-Key: your-api-key" \
    -H "Content-Type: application/json" \
    -d '{
    "model": "edge-tts",
    "text": "Hello, world!",
    "voice": "en-US-JennyNeural",
    "speed": 1.0,
    "pitch": 1.0,
    "volume": 1.0,
    "format": "mp3"
    }'

Synchronous Text-To-Speech（TTS） API

Synchronous text-to-speech service, supporting multiple providers' TTS models with unified interface and unified calling parameters

  • Support multiple TTS providers
  • Real-time speech synthesis
  • High-quality audio output
  • Customizable voice parameters
View details

Models List API

Get a list of all available TTS models and understand supported languages and features

  • Get all available models
  • Sorted by provider
  • Real-time updates
  • Detailed model information
View details

Voices List API

Query the voice list supported by a specific model, including voice characteristics and usage recommendations

  • Model-specific voices
  • Detailed voice information
  • Gender and age identification
  • Language support description
View details