Video Dubbing (SoniTranslate)

Video Dubbing (SoniTranslate)

Dubs a video into another language using open source projects, in a Gradio page. For creators who want to translate the speech in a video.

Made by G-Rost 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: This Space is a Gradio page for dubbing videos with open source projects, under the name SoniTranslate. Dubbing means replacing the spoken audio of a video with speech in another language. The repository holds the app, a soni_translate package, voice and pipeline scripts, MDX model files and a Colab notebook, and it names many speech models for specific languages.

Who it suits: Video creators, educators and teams who want their videos heard in another language. Developers can also read it as an example of several open source speech tools combined in one app.

Industry | Who uses it | How they use it | Example
Content creation | YouTubers and video makers | Make a version of a video in another language | Upload a short clip and pick a target language
Education | Teachers | Share lecture videos with students who speak other languages | Dub a short lesson clip
Marketing | Small business teams | Reuse one video for several markets | Dub a product demo
Software | Developers | Study how speech tools are chained together | Read app_rvc.py and the soni_translate folder

If you only need subtitles and not a new voice track, you can skip it.

Where to use it: The app runs in these places:

• A web browser: open the Space page on Hugging Face and use it there.
• Windows, macOS or Linux: run a copy on your own computer with Python.
• Google Colab, through the notebook in the repository.

Use case | Who | What they get back
Dub a video | Creators | The video with speech in another language
Try it online | Curious visitors | Whatever the Gradio page returns for the file they give it
Study the code | Developers | A Python package, scripts and docs to read

How to set it up: You need a few things first:

• Python
• The huggingface_hub package, which the first command installs
• The packages listed in requirements.txt
• System packages from packages.txt, which Hugging Face installs with apt-get for the hosted Space

The repository also holds pre-requirements.txt and requirements_xtts.txt, which the steps below do not mention. The steps download the Space, install Gradio at the version the Space uses, add the other packages and start the app.

1. Install the Hugging Face package.
2. Download the Space into a folder called SoniTranslate_2.
3. Move into that folder.
4. Install Gradio 5.29.0.
5. Install the packages from requirements.txt.
6. Start the app.

pip install -U huggingface_hub
hf download G-Rost/SoniTranslate_2 --repo-type space --local-dir SoniTranslate_2
cd SoniTranslate_2
pip install gradio==5.29.0
pip install -r requirements.txt
python app_rvc.py

How to use it: Open the Space page on Hugging Face, or start the local copy with the last command above. Gradio serves a web page where you give the app a video and choose how to dub it. The card does not list the controls.

python app_rvc.py

Tool | What it does
hf download | Copies the Space's files into a folder on your computer
python app_rvc.py | Starts the dubbing app on your own computer

Example: You open the Space, give it a short video and choose a target language. The page then returns a version of the video with the speech in that language.

For newcomers and experts: If you are new to this, open the Space page and try a short clip first. You do not need to install anything for that. Long videos take much more time to process.

If you know the field, the Space names many wav2vec2 models for particular languages, such as Pashto, Amharic, Kazakh, Albanian, Tamil and Estonian. The repository has folders and files named after MDX models, XTTS and a voice conversion pipeline, so it chains several open tools.

You give the app a video
Speech is picked out and turned into text
The text is translated
New speech is made and joined to the video

Good to know: The card says only that this is video dubbing with open source projects. Check the page for which languages and voices it offers.

• License: mit, as the Space lists it.
• Cost to run: none named. The hosted Space runs on the cpu-basic hardware at Hugging Face.
• Data it reaches: the videos you give it. A local copy also downloads the Space's files and the models it needs from Hugging Face.
• Not for: none stated in the card.

On Hugging Face, 13 November 2026

• Likes: 3
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/G-Rost/SoniTranslate_2
• Files: https://huggingface.co/spaces/G-Rost/SoniTranslate_2/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.