IDEA-Emdoor-Lab/UniTTS
A TTS Trained on Universal Audio.
This project helps generate natural-sounding speech from text, particularly for Chinese. You provide the system with text you want to convert to speech, and optionally, a reference audio clip and its corresponding text to guide the voice's style. The output is high-quality, expressive audio that captures subtle emotional nuances. This is ideal for content creators, educators, or anyone needing realistic spoken audio for Chinese applications.
No commits in the last 6 months.
Use this if you need to generate highly natural and emotionally expressive Chinese speech from text, especially when you want to match a specific voice style or handle conversational and complex narratives.
Not ideal if your primary need is for speech synthesis in languages other than Chinese and English, or if you require an extremely lightweight, low-resource system for basic text-to-speech without advanced emotional modeling.
Stars
41
Forks
3
Language
Python
License
—
Category
Last pushed
Jun 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/IDEA-Emdoor-Lab/UniTTS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rsxdalv/TTS-WebUI
A single Gradio + React WebUI with extensions for ACE-Step, Kimi Audio, Piper TTS, GPT-SoVITS,...
playht/pyht
PlayHT Python SDK - AI Text-to-Speech Streaming & Voice Cloning API
aedocw/epub2tts
Turn an epub or text file into an audiobook
DrewThomasson/VoxNovel
VoxNovel: generate audiobooks giving each character a different voice actor.
gianpaj/sexyvoice
Voice Cloning, Voice Call and Text to Speech platform. Perfect for content creators, developers,...