Seed Voice Conversion

Seed Voice Conversion

Converts speech from one voice to another in a Gradio page on ZeroGPU hardware, built on Seed-VC. For developers and audio makers who want to try voice conversion.

Made by Plachta on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Seed Voice Conversion is a Gradio Space for Seed-VC, a voice conversion tool. It changes the voice in a piece of speech into a different voice, and it runs on ZeroGPU hardware, so you can try it in a browser with nothing to install. Its main file is app_v1v2.py.

Who it suits: It suits developers, audio makers and researchers who want to try voice conversion and see how the code is put together.

Industry | Who uses it | How they use it | Example
Audio production | Audio makers | Try changing a voice in a recording | Convert a short clip and listen to it
Software | Developers | Read how a voice conversion app is wired up | Open app_v1v2.py and the modules folder
Speech research | Researchers | Test a conversion model on their own clips | Compare the result with the original clip

If you do not work with audio, you can skip it. Use only voices you have the right to use.

Where to use it:

• A web browser, on the Space's page on Hugging Face
• A local copy of the files, run with Python under Windows, macOS or Linux

Use case | Who | What they get back
Change a voice | Audio makers | A clip that keeps the speech but sounds like another voice
Study the code | Developers | A Gradio app with a wrapper and several modules
Test a model | Researchers | Conversion results from the named models

How to set it up:

• A web browser, which is all the online page needs
• Python, for a local copy
• The Python packages listed in requirements.txt

1. Open the Space's page on Hugging Face to use it online. Nothing needs installing.
2. For a local copy, install the Hugging Face hub package and download the Space's files.
3. Move into the downloaded folder.
4. Install Gradio 5.24.0, then the packages from requirements.txt.
5. Start the app with python app_v1v2.py.

pip install -U huggingface_hub
hf download Plachta/Seed-VC --repo-type space --local-dir Seed-VC
cd Seed-VC
pip install gradio==5.24.0
pip install -r requirements.txt
python app_v1v2.py

How to use it: Open the page, or the one your local copy starts, give it a speech clip and follow the controls the Gradio interface shows. The README lists no controls, so the page itself is the guide.

Example: Load a short recording of speech and run the conversion. The page returns audio with the same words in a changed voice.

For newcomers and experts: Open the Space page and try one short clip first. Nothing needs installing, and you can judge by ear what the conversion does.

The repository holds app.py and app_v1v2.py, a wrapper called seed_vc_wrapper.py, and folders for configs, modules and dac. The Space names several models, including ByteDance/MegaTTS3, funasr/campplus, lj1995/VoiceConversionWebUI and two nvidia bigvgan vocoders. The README is only a configuration header, so how each one is used is something to read in the code.

You give the page a speech clip
The app prepares the audio
A conversion model changes the voice
A vocoder turns the result back into sound
The page plays the converted audio

Good to know: The README gives no usage notes, so the steps above follow from how the Space is built.

• License: GPL-3
• Cost to run: none named, and the online copy runs on ZeroGPU hardware
• Data it reaches: the audio you give it and the models the Space names

On Hugging Face, 13 November 2026

• Likes: 561
• Built with: gradio
• License: gpl-3.0

Links

• Space: https://huggingface.co/spaces/Plachta/Seed-VC
• Files: https://huggingface.co/spaces/Plachta/Seed-VC/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.