Open-Source AI Video Dubber

Clone the repo: git clone https://github.com/EliasLindbergs/ai-video-dubber.git
Download the following pre-trained models and place them in the corresponding folders:

In the inference notebook, replace API_KEY with your OpenAI API key (https://platform.openai.com/account/api-keys) and AUTH_TOKEN with your pyannote access token (visit hf.co/pyannote/embedding and accept user conditions, then visit hf.co/settings/tokens to create an access token)

Re-name your video to “video.mp4” (or whatever extension it has) and place it in a Media folder
Run the inference notebook and collect the generated dubbed video "final_video_output.mp4" in the Media folder

Name		Name	Last commit message	Last commit date
Latest commit History 12 Commits
LibriTTS		LibriTTS
Models/LibriTTS		Models/LibriTTS
Utils		Utils
Vocoder/LibriTTS		Vocoder/LibriTTS
README.md		README.md
inference.ipynb		inference.ipynb
models.py		models.py
utils.py		utils.py
vocoder.py		vocoder.py
vocoder_utils.py		vocoder_utils.py

Provide feedback