Contact us!
If you encounter an error, please reach out to the Lipdub Team.
- Discord: Click on the <?> button in the lower right hand corner of the Lipdub app to join the discord community
- Email: Discord is preferred, but if not possible, reach out to the support team at support@lipdub.ai
Accessing Lipdub’s Discord server
Connect, share, and discuss everything LipDub on our Discord server! It has the latest updates, showcases upcoming features, and is your best place to contact support for the fastest response! There is also much more helpful resources that can help you get started using the platform! 😉
Source audio is important!
The audio in the source video (video you upload) is important! But it is not a restriction.
- LipDub has an experimental feature called "Maintain Expression" that uses the original audio to train an AI model based on the audio viseme/phonemes. However this is experimental and may yield worse results if the original video that you upload does not have its original audio.
- If you are trying to lip-sync an AI avatar that doesn't have any source audio, then simply uploading a video without any audio is also fine
While the audio for the input video matters, the new audio you'd like to lip-sync to does NOT!
- LipDub is language agnostic. You can upload any language and LipDub will lip-sync the actor to it.
- LipDub is HIGHLY sensitive. If you upload a dub audio with background music or SFX, we will lipsync the actor to instruments or SFX if the actor is on screen. This is why we recommend voice-isolated dialogue stems for the dub audio.
Third and final point:
- Audio for Training data does not matter! Training data videos will just used to for training the AI model from a visual standpoint. it will not use the audio in the "Additional Footage for Training" section in the Advanced Workflow Guide.
Upload training footage to training section
Specifically for Advanced Workflow, we recommend uploading footage that is exclusively for training, into the training section. This will keep your project organized!
Video footage that is uploaded to this “Additional Footage for Training” will not be Lip-synced and therefore will not appear in the final step “4. Upload Audio & Generate”.
Check out What is ‘Additional Footage for Training’ & How to capture it On-Set? to understand what we mean by Additional Footage for Training.
Check the ‘unassigned tracks’ on Label Actors step
Make sure you check the ‘unassigned track’ section on the label actors step!
There’s a chance that some face detections belonging to speaking actors have not be assigned correctly. If they are, they need to be re-assigned to the correct actor.
The following video shows a user checking the ‘unassigned tracks’ section and seeing face detections that belong to Adam. The tracks are then being correctly assigned to Adam