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.
246 stars. No commits in the last 6 months.
Use this if you need to generate realistic speech from text using a high-performance system you can run on your own hardware, including compact devices like a Raspberry Pi, or with GPU acceleration.
Not ideal if you prefer a cloud-based service, require a very wide range of unique voices or languages beyond what's offered, or have extremely simple, infrequent text-to-speech needs.
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
abus-aikorea/voice-pro
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot...
JSchmie/ScrAIbe-WebUI
WebUI for ScAIbe
isaiahbjork/orpheus-tts-local
Run Orpheus 3B Locally With LM Studio
snakers4/silero-stress
Silero Stress — pre-trained enterprise-grade automated stress and homograph disambiguation for...