ekwek1/soprano-factory
Soprano-Factory: Train your own 2000x realtime text-to-speech model
This project helps audio producers, content creators, and AI voice developers create custom voice models for text-to-speech applications. You provide your own audio recordings and corresponding text transcripts, and it generates a new, personalized voice model. This is for anyone who needs to quickly generate expressive, high-fidelity speech in unique voices or languages.
212 stars.
Use this if you need to train a custom, high-performance text-to-speech voice model on your own hardware using your unique audio data.
Not ideal if you are looking for a pre-trained, ready-to-use text-to-speech model without needing custom voices or styles.
Stars
212
Forks
33
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ekwek1/soprano-factory"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
TuananhCR/Dia-Finetuning-Vietnamese
TTS Dia finetuning for Vietnamese
dangvansam/viet-tts
VietTTS: An Open-Source Vietnamese Text to Speech
thinhlpg/vixtts-demo
A Vietnamese Voice Cloning Text-to-Speech Model ✨
NTT123/vietTTS
Vietnamese Text to Speech library
modelscope/KAN-TTS
KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at ...