daswer123/xtts-api-server
A simple FastAPI Server to run XTTSv2
Exposes XTTSv2's multilingual text-to-speech capabilities through REST endpoints with support for voice cloning via speaker samples, configurable model versions, and optional GPU acceleration via DeepSpeed. Includes streaming mode for low-latency audio generation, result caching, and low-VRAM operation modes, with Docker deployment and integration hooks for applications like SillyTavern. Supports both official and custom fine-tuned models loaded from HuggingFace or local directories.
577 stars and 17,930 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
577
Forks
156
Language
Python
License
MIT
Category
Last pushed
Jul 21, 2024
Monthly downloads
17,930
Commits (30d)
0
Dependencies
18
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/daswer123/xtts-api-server"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
jamiepine/voicebox
The open-source voice synthesis studio
devnen/Chatterbox-TTS-Server
Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible...
jianchang512/ChatTTS-ui
一个简单的本地网页界面，使用ChatTTS将文字合成为语音，同时支持对外提供API接口。A simple native web interface that uses ChatTTS to...
Aivis-Project/AivisSpeech-Engine
AivisSpeech Engine: AI Voice Imitation System - Text to Speech Engine
nari-labs/dia
A TTS model capable of generating ultra-realistic dialogue in one pass.