| LocalVideoDub - Linux AI Video Dubbing Utility |
|
|
| Install: |
|
|
| Extract the LocalVideoDub folder anywhere you want, including a USB thumb drive. |
|
|
| Open a terminal inside the LocalVideoDub folder and run: |
|
|
| bash install_environment.sh |
|
|
| The first installation can take a while depending on your internet speed. |
|
|
| When installation is complete, launch the program with: |
|
|
| bash launch.sh |
|
|
| You will see a lot of terminal text while models and services load. This is normal. When the server is ready, you will see text mentioning: |
|
|
| Debugger is active |
|
|
| Open the WebUI in your browser: |
|
|
| 127.0.0.1:5000 |
|
|
| Bookmark it if desired. |
|
|
| To stop the server at any time, press CTRL+C while the terminal window is active. |
|
|
| Nothing is installed system-wide. Everything remains self-contained inside the LocalVideoDub folder. |
|
|
| The compressed download is approximately 800MB because all required models are included. The fully installed size is approximately 9GB. |
|
|
| --- |
|
|
| Basic Usage: |
|
|
| 1. Load a short video or photo into "Target Video or Photo" |
| 2. (Optional) Load external audio if your target video has no speech |
| 3. Enter your text into "Replacement Speech Text" |
| 4. Click "Execute Video Generation" |
|
|
| The finished video will appear in the WebUI on the left side. Click the video to play it. |
|
|
| Generated videos are also saved in the: |
|
|
| outputs folder. |
|
|
| You can use the program as many times as you want. |
|
|
| --- |
|
|
| Important Notes: |
|
|
| * The less punctuation you use, the better the speech generation tends to work. |
| * If you use a photo or silent video, you must also provide audio for voice cloning. |
| * The application uses older but reliable tools (GFPGAN and Wav2Lip). Results will vary depending on the source material. |
| * Best results are usually achieved with videos around 720x720 resolution. |
| * Leave "Seed" and "Acoustic Temperature" at their defaults unless you want to experiment. |
| * Place reusable source clips inside the "clips" folder for convenience. |
| * If your speech is longer than the original video, the video will automatically loop to match the audio length. |
|
|
| --- |
|
|
| Tips for Better Results: |
|
|
| * Keep the subject facing forward whenever possible. |
| * Minimal head movement produces better lip sync. |
| * Side angles and extreme facial rotations will not work properly. |
| * Avoid videos where the mouth opens extremely wide or moves erratically. |
| * Male facial hair can sometimes create texture artifacts around the mouth area. |
| * Close-up faces work best. |
| * The cleaner and simpler the source video, the better the output. |
|
|
| A 720x720 Mona Lisa sample image and matching audio clip are included in the "clips" folder for testing. |
|
|
| --- |
|
|
| OOM (Out Of Memory) Errors: |
|
|
| If you encounter an OOM (Out Of Memory) error: |
|
|
| 1. Stop the server with CTRL+C |
| 2. Restart the application |
| 3. Refresh the WebUI |
|
|
| This usually resolves the issue. |
|
|
| --- |
|
|
| System Tested On: |
|
|
| Xubuntu Linux |
| NVIDIA RTX 3050 8GB |
| 32GB System RAM |
|
|
| --- |
|
|
| This project is considered stable and feature complete. Future updates are unlikely unless major issues are discovered. |
|
|
| Have fun. Be responsible. |
|
|
| -- R.G. |
| 05-21-2026 |
|
|
