Introduction
An overview of the complete features and structure of Supertone API.
Supertone API is a RESTful API that can synthesize emotionally expressive voices from text. Based on a voice library integrated with Play, it can generate natural speech with just text input, providing various features from voice exploration to usage management.
Features
Text-to-Speech
Converts text to speech. Users can pass language, style, model, and detailed voice settings (pitch, speed, etc.) along with voice ID.
Voice Exploration
You can retrieve all voices available in your current account or search by conditions such as language, style, and name.
Speech Duration Prediction
Before generating speech, you can predict how many seconds of audio the input text will generate. This feature can be called without deducting credits.
Credits and Usage Check
Provides endpoints to check your accountโs remaining credit balance and voice time used through the API.
Documentation
- Authentication: Guides authentication methods for using the API.
- Endpoint Reference: You can check calling methods and response structures for each feature.
After its official launch, Supertone API operates as a scalable voice synthesis platform that organically connects Play, console, and voice generation features beyond simple calling functionality.