unilight/jatts
JATTS: A modern, research-oriented Japanese Text-to-speech Open-sourced Toolkit
This toolkit helps researchers working with Japanese speech synthesize human-like speech from text. It takes Japanese text as input and generates high-quality audio, allowing them to compare different text-to-speech models using various datasets and evaluation metrics. The primary users are speech synthesis researchers and academics.
Use this if you are a researcher focused on comparing and evaluating different Japanese text-to-speech models and need a flexible toolkit for experimentation.
Not ideal if you need a production-ready system optimized for inference speed or a simple tool for basic Japanese text-to-speech conversion.
Stars
44
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/unilight/jatts"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
RVC-Boss/GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
High-Logic/Genie-TTS
GPT-SoVITS ONNX Inference Engine & Model Converter
chinokikiss/GSV-TTS-Lite
GSV-TTS-Lite A high-performance inference engine specifically designed for the GPT-SoVITS...
FENRlR/MB-iSTFT-VITS2
Application of MB-iSTFT-VITS components to vits2_pytorch
AlexandaJerry/vits-mandarin-biaobei
application of vits on mandarin tts