Kitten-TTS-Server and KittenTTS
These are ecosystem siblings—one is the underlying TTS model (15M parameter lightweight architecture) while the other is an enhanced API server and web UI wrapper that deploys and exposes that same model for practical use.
About Kitten-TTS-Server
devnen/Kitten-TTS-Server
Self-host the ultra-lightweight Kitten TTS model with this enhanced API server with an intuitive Web UI, large text processing for audiobooks, and GPU acceleration.
This project helps anyone who needs to convert written text into natural-sounding spoken audio. You input text, select from various natural voices and models, and it outputs high-quality audio files. This is ideal for content creators, audiobook producers, developers building voice interfaces, or anyone needing to generate speech on their own computer or local network.
About KittenTTS
soldier444xd/KittenTTS
KittenTTS is an ultra-lightweight, CPU-friendly text-to-speech model with 15M params for real-time, high-quality voices. Open source, fast start. 😺
This project helps developers integrate high-quality, natural-sounding speech into their applications or devices. It takes plain text as input and generates clear, lifelike audio output that can run efficiently even on mobile phones or small computers. Developers creating apps, games, or embedded systems would find this useful for adding voice features.
Scores updated daily from GitHub, PyPI, and npm data. How scores work