VoxCPM2 Myanmar Voice Clone Test

VoxCPM2 Myanmar Voice Clone Test

Tests voice cloning with the VoxCPM2 model before it is connected to Dubbing Studio. For dubbing and speech developers who need the speaker's permission to clone a voice.

Made by hub10 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: VoxCPM2 Myanmar Voice Clone Test is a separate Space for trying voice cloning with the VoxCPM2 model. Its author built it to test cloning before wiring it into a tool called Dubbing Studio. The name points to Myanmar.

Reference clips and generated audio are temporary files in the Space and are not added to its repository.

Who it suits: Developers and dubbing teams who want to check how voice cloning behaves before they build it into a pipeline.

Industry | Who uses it | How they use it | Example
Media | Dubbing teams | Test a cloned voice before using it in a studio tool | Clone a voice from a short reference clip
Software | Speech developers | Check the model in a small separate app | Run the Space and listen to the output
Research | Speech researchers | Try voice cloning on a lesser-served language | Test Myanmar text with a reference voice

You can skip it if you do not have the speaker's permission, since the README says to clone a voice only with that permission.

Where to use it:

• A web browser, on the Space's page at Hugging Face, with nothing to install
• Windows, macOS or Linux with Python, from a copy you download

Use case | Who | What they get back
Clone a voice | Developers | Speech in the cloned voice
Prepare a dub | Dubbing teams | A test clip to judge quality before integration

How to set it up:

• Python 3.12.12 on your computer
• The Python packages listed in requirements.txt
• Docker, if you want to build it from the included Dockerfile
• The huggingface_hub package, which gives you the hf command

1. Install the huggingface_hub package.
2. Download the Space with the hf command.
3. Move into the downloaded folder.
4. Install the pinned Gradio version.
5. Install the packages from requirements.txt.
6. Start the app with Python.

pip install -U huggingface_hub
hf download hub10/voxcpm2-myanmar-clone-test --repo-type space --local-dir voxcpm2-myanmar-clone-test
cd voxcpm2-myanmar-clone-test
pip install gradio==6.20.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space's page in your browser, or start your own copy with the command below. Add a reference clip of a speaker who has given permission, enter the text to speak and run the clone.

python app.py

Example: You upload a short reference clip from a speaker who agreed to it and type a line of text. The app returns that line spoken in the cloned voice as a temporary file you can play.

For newcomers and experts: If you are new to voice cloning, use a clean clip of your own voice for the first try. Only use another person's voice with their permission.

If you know the field, the Space runs the VoxCPM2 model from openbmb on a Gradio page, on GPU hardware at Hugging Face. It is a test bench, so expect plain controls and no polish.

You add a reference clip and text
app.py sends them to the VoxCPM2 model
The model produces cloned speech
The temporary audio plays on the page

Good to know:

• License: the Space lists apache-2
• Cost to run: none named
• Data it reaches: the reference clips and text you give it, kept as temporary Space files
• Not for: cloning a voice without the speaker's permission, which the README rules out

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/hub10/voxcpm2-myanmar-clone-test
• Files: https://huggingface.co/spaces/hub10/voxcpm2-myanmar-clone-test/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.