ChirpTTS Documentation
Everything you need to get started with ChirpTTS and integrate text-to-speech into your projects
Getting Started
ChirpTTS provides multiple ways to use our text-to-speech technology, depending on your needs and technical requirements.
Cloud API
The quickest way to integrate ChirpTTS. Use our hosted API to generate speech from your applications.
Cloud API Documentation →Self-Hosted
Run ChirpTTS on your own infrastructure. Ideal for complete control, offline use, or privacy requirements.
Self-Hosted Guide →API Reference
Our API provides simple endpoints for text-to-speech conversion and voice management. Below are the core endpoints you'll use.
POST /api/tts
Convert text to speech
{
"text": "Your text to convert to speech",
"voice": "default",
"speed": 1.0,
"pitch": 1.0,
"format": "mp3"
}GET /api/voices
List available voices
Self-Hosted Guide
Running ChirpTTS on your own infrastructure gives you complete control and privacy. Our open source solution can be deployed on most Linux servers or desktop systems.
System Requirements
- • Linux server (Ubuntu 20.04+ recommended)
- • 4GB RAM minimum (8GB+ recommended for multiple users)
- • 10GB disk space for models
- • Python 3.8 or higher
Quick Start
Install from our GitHub repository
git clone https://github.com/your-repo/chirptts cd chirptts pip install -r requirements.txt python setup.py install
Voice Customization
ChirpTTS allows you to clone and customize voices for your specific needs.
Voice cloning functionality is coming soon. Sign up to be notified when this feature launches.