Gradio Lipsync Wav2lip

Gradio Lipsync Wav2lip

Runs Wav2Lip lip syncing in a Gradio page, which matches mouth movements to speech audio, for people who experiment with video and voice tools.

Made by manavisrani07 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: Gradio Lipsync Wav2lip is a Gradio page built around Wav2Lip, a lip-sync model. Lip sync means matching the mouth movements in a video to a speech recording. The repository holds Wav2Lip model code, face detection and face parsing folders, and checkpoints. The source does not describe the controls.

Who it suits: Developers and hobbyists who want to try lip syncing without building a pipeline of their own.

Industry | Who uses it | How they use it | Example
Video production | Editors and hobbyists | Try matching a clip's mouth movements to a recording | Testing a short clip with a new voice track
Software | Developers of video tools | Study how a lip-sync demo is put together | Reading inference.py and the model folders
Research | People who test speech and video models | Run Wav2Lip in a browser without local setup | Trying one clip on the hosted page

If you do not work with video and speech audio, you can skip it.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Python 3.8 on Windows, macOS or Linux, for a copy you run yourself

Use case | Who | What they get back
Try lip sync on a clip | Hobbyists | A clip with mouth movements matched to speech
Read a working demo | Developers | A Gradio app with Wav2Lip model code to study
Test Wav2Lip online | Researchers | A hosted page with nothing to install

How to set it up: Online, nothing needs installing. For a copy on your own computer you need a few things first.

• Python 3.8
• The pip tool
• The packages listed in requirements.txt

1. Install the Hugging Face hub package.
2. Download the Space's files into a folder.
3. Move into that folder.
4. Install Gradio at the pinned version.
5. Install the packages from requirements.txt.
6. Start app.py.

pip install -U huggingface_hub
hf download manavisrani07/gradio-lipsync-wav2lip --repo-type space --local-dir gradio-lipsync-wav2lip
cd gradio-lipsync-wav2lip
pip install gradio==4.43.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space's page, or start app.py from your own copy, and follow the labels on the page. The source documents no controls, so the page itself is the guide.

python app.py

Example: You open the page with a short clip of a face and a speech recording, then run it. What you should get back is the clip with its mouth movements matched to that speech. The source shows no sample output, so check the result yourself.

For newcomers and experts: Think of lip sync as making a mouth move in time with the words you hear. To start, open the hosted page and try one short clip and one short recording.

The repository has folders for Wav2Lip models, face detection, face parsing, an ESRGAN model and basicsr, with checkpoints and weights stored alongside. The source does not explain how the parts fit together. The Space runs on cpu-basic hardware at Hugging Face on Python 3.8.

Open the page in a browser
Give it a face clip and speech audio
Wav2Lip matches mouth movements to the audio
The synced clip comes back

Good to know:

• License: Apache 2.0
• Cost to run: none named
• Data it reaches: the clips and audio you give it, plus the checkpoints and weights stored in the repository
• Not for: the source names no forbidden uses, so use only footage and voices you have the right to use

On Hugging Face, 13 November 2026

• Likes: 197
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/manavisrani07/gradio-lipsync-wav2lip
• Files: https://huggingface.co/spaces/manavisrani07/gradio-lipsync-wav2lip/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.