lora-svc

singing voice change based on whisper, and lora for singing voice clone. You will feel the beauty of the code from this project. Uni-SVC main branch is for singing voice clone based on whisper with speaker encoder and speaker adapter. Uni-SVC main target is to develop lora for SVC. With lora, maybe clone a singer just need 10 stence after 10 minutes train. Each singer is a plug-in of the base model.

Features

Singing voice conversion based on whisper, UnivNet and NSF
Model which contains 56 singers of 50 hours singing data is training
You can preview models
Uni-SVC for baker
Uni-SVC for Opencpop
Open source singing voice conversion
Change sample rate of waves

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow lora-svc

lora-svc Web Site

Other Useful Business Software

Go From AI Idea to AI App Fast

One platform to build, fine-tune, and deploy ML models. No MLOps team required.

Access Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.

Try Free

Rate This Project

User Reviews

Be the first to post a review of lora-svc!

Additional Project Details

Programming Language

Python

Related Categories

Python Voice Cloning Software

Registered

2023-03-23

Similar Business Software

PERSO.ai

Perso AI Dubbing is an AI-powered video dubbing and translation platform that localizes content into 33+ languages in minutes, with speech recognition in 99+ languages. Teams upload a video, select target languages, and receive a studio-quality dubbed version — complete with lip-sync and voice...

See Software
Dub AI

Localize your content with seamless translation, voice cloning, multilingual support and much more at your fingertips. Localizing your content and reach a global audience with ease. Support up to 10 speakers at once with automatic speaker detection. Cloning any voice and maintaining brand...

See Software
InnAIO

InnAIO offers an AI-powered language translation solution centered on voice-cloning real-time translation devices that let users communicate across languages while preserving their own tone and expression, making conversations feel natural rather than robotic. Its core products, like the InnAIO...

See Software
Chatterbox

Chatterbox is a free, open source voice cloning AI model developed by Resemble AI, licensed under MIT. It enables zero-shot voice cloning using just 5 seconds of reference audio, eliminating the need for training. The model offers expressive speech synthesis with unique emotion control, allowing...

See Software
Resemble AI

Resemble clones voices from given audio data starting with just 5 minutes of data. Use that voice to iterate and create dynamic content on the fly using our authoring tool or the API. Discover How AI Voices Can Scale with Resemble's low latency API and 44 kHz AI Voices. Create realistic...

See Software
Play.ht

AI Powered Text to Voice Generation. Play.ht offers uncanny, high-fidelity AI Voices for any project where you need human-sounding voice overs and performances. Hollywood studios, auto manufacturers, and other large enterprises use Play.ht to create realistic and engaging voiceovers...

See Software