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.
Supports all 7 KittenTTS models (15M–80M parameters) with hot-swappable selection and automatic Hugging Face downloads, built on FastAPI with OpenAI-compatible endpoints. Implements GPU acceleration via ONNX Runtime I/O binding for reduced latency, alongside intelligent text chunking for audiobook generation. Optimized for edge deployment from Raspberry Pi 5 to NVIDIA GPUs with named voice support and Docker containerization.
246 stars. No commits in the last 6 months.
Stars
246
Forks
31
Language
Python
License
MIT
Category
Last pushed
Aug 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/devnen/Kitten-TTS-Server"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
snakers4/silero-models
Silero Models: pre-trained text-to-speech models made embarrassingly simple
snakers4/silero-stress
Silero Stress — pre-trained enterprise-grade automated stress and homograph disambiguation for...
JSchmie/ScrAIbe-WebUI
WebUI for ScAIbe
abus-aikorea/voice-pro
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot...
isaiahbjork/orpheus-tts-local
Run Orpheus 3B Locally With LM Studio