FENRlR/MB-iSTFT-VITS2
Application of MB-iSTFT-VITS components to vits2_pytorch
This project helps you create custom text-to-speech (TTS) voices. You provide audio recordings and corresponding text transcripts, and it generates a model that can convert new text into natural-sounding speech in that voice. It's designed for speech synthesis researchers and engineers who want to build high-quality, potentially state-of-the-art TTS systems.
134 stars.
Use this if you need to train a custom text-to-speech model from your own audio datasets for research or application development, especially if you are working with languages like Russian.
Not ideal if you need a pre-trained, ready-to-use voice without the need for custom model training, or if you lack a high-quality dataset of audio and text for your target voice.
Stars
134
Forks
31
Language
Python
License
MIT
Category
Last pushed
Dec 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/FENRlR/MB-iSTFT-VITS2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
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...
AlexandaJerry/vits-mandarin-biaobei
application of vits on mandarin tts
Artrajz/vits-simple-api
A simple VITS HTTP API, developed by extending Moegoe with additional features.