CoverGen RVC is an autonomous pipeline designed to create covers using any RVC v2 trained AI voice from a local audio file. This tool is ideal for developers looking to add singing functionality to their AI assistants, chatbots, or VTubers, and for those who simply want to hear their favorite characters sing their favorite songs.
-
Inference WebUI: Easily generate AI covers by selecting a local audio file and applying a trained RVC model. The interface is designed to be intuitive, making the process straightforward even for those new to voice conversion technologies.
-
Model Downloader: Conveniently download RVC models from within the WebUI. Simply navigate to the "Download Model" tab, paste the download link, and give it a unique name. You can find trained voice models in the AI Hub Discord. Ensure the downloaded zip file contains the
.pthmodel file and optionally, an.indexfile. -
Upload Functionality: The WebUI also supports uploading a zip file containing the necessary model files, or directly uploading the
.pthand.indexfiles.
The use of the converted voice is prohibited for the following purposes:
- Criticizing or attacking individuals.
- Advocating for or opposing specific political positions, religions, or ideologies.
- Publicly displaying strongly stimulating expressions without proper zoning.
- Selling voice models and generated voice clips.
- Impersonation of the original owner of the voice with malicious intent to harm others.
- Fraudulent activities, including identity theft or fraudulent phone calls.
The author is not liable for any direct, indirect, consequential, incidental, or special damages arising out of or in any way connected with the use, misuse, or inability to use this software.
For more information, visit the original project on Hugging Face.