Pocket TTS
Fully local, offline text-to-speech using Kyutai's Pocket TTS model. Generate high-quality audio from text without any API calls or internet connection. Features 8 built-in voices, voice cloning support, and runs entirely on CPU.
🚀 Pocket TTS is a fully offline text-to-speech tool that converts text into natural-sounding audio without needing internet or API calls. It includes 8 built-in voices and supports voice cloning from your own audio samples. Everything runs locally on your CPU—no special hardware required.
💡 Perfect for creating voiceovers, accessibility features, or adding audio to applications. Use it via simple command-line commands or integrate it directly into Python projects. Ideal for privacy-conscious users who want complete control over their data.
✨ Generate high-quality speech in 2-6x real-time speed with minimal latency (~200ms). Fast setup, easy to use, and completely free—just download the model once and you're ready to go.
Requirements
Python package for Pocket TTS text-to-speech
Machine learning framework (CPU version)
Python runtime environment