Kyutai TTS

About

Kyutai TTS Docker provides a production-ready, all-in-one solution for deploying the Kyutai Text-to-Speech model. It simplifies the setup process with one-click deployment, including automated GPU selection and port detection. Users can interact with the service through a user-friendly multi-language web UI, a flexible REST API with Swagger documentation, or integrate it into MCP workflows. The deployment includes smart GPU management features like lazy loading and automatic memory release, ensuring efficient resource utilization and making it suitable for production environments with HTTPS, health checks, and monitoring capabilities.

Key Features

• All-in-One Docker Image including models and dependencies
• Smart GPU Management with lazy loading and automatic memory release
• One-Click Deployment with automated GPU selection and port detection
• Production-Ready features including HTTPS, health checks, and monitoring
• Three Access Modes: Web UI, REST API, and MCP tools
• 2 GitHub stars

Use Cases

• Integrating advanced text-to-speech capabilities into applications via a REST API
• Deploying a self-hosted text-to-speech service with a web interface for direct user interaction
• Automating speech generation within larger workflows using MCP tools