ORI-Muchim/One-Click-MB-iSTFT-VITS2
MB-iSTFT-VITS2(Data Preprocessing + Whisper + Text Preprocessing + Making config.json + Training, Inference) ONE-CLICK
This tool helps you create custom text-to-speech (TTS) voices by taking raw audio recordings of a speaker and converting them into a ready-to-use voice model. You provide audio files organized by speaker, and the tool outputs a trained voice model that can generate new speech from text in that speaker's voice. This is ideal for voice artists, content creators, or anyone needing to generate synthetic speech from custom voice datasets.
Use this if you need a streamlined way to train a high-quality, custom text-to-speech voice model from audio recordings with minimal manual configuration.
Not ideal if you don't have access to powerful hardware (like a GPU with at least 12GB VRAM and 16GB RAM) or if you're looking for an off-the-shelf TTS solution without custom voice training.
Stars
13
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ORI-Muchim/One-Click-MB-iSTFT-VITS2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
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