LipSync in the Video Timeline
LipSync lets you create a new speaking video by combining an existing video clip with an audio clip on the Video timeline.
LipSync in the Video Timeline
LipSync lets you create a new speaking video by combining an existing video clip with an audio clip on the Video timeline.
It is useful when you already have a character performance and want the mouth movement to follow dialogue, narration, or voice-over.
What you need
- 1 video clip on the Video timeline
- 1 audio clip on the Video timeline
- the two clips aligned at the point where speech should begin
The audio clip can come from uploaded audio, recorded voice-over, text-to-speech, or voice change, as long as it exists as a timeline audio clip.
How to use LipSync
- Open the Video tab
- Place your source video clip on the timeline
- Add or import the audio clip you want to sync
- Align the audio under the video so the speech starts at the correct moment
- Select exactly one video clip and one audio clip
- Right-click the selection and choose LipSynch
- Review the LipSync settings
- Generate the result
LipSync settings
- Expressiveness controls how subtle or expressive the lip movement should feel
- Active Speaker Detection helps the system focus on the person who is speaking
What happens after generation
LipSync does not overwrite your original clip.
Instead, Ciaro creates a new generated video version linked to the same shot. Your original source video stays intact, and the new lip-synced result becomes available as another version of that shot.
Best practices
For the best results, start with a source video where:
- the character's face is visible
- the mouth area is readable
- the character already appears ready to speak
- the shot is not too distant or heavily obscured
A common end-to-end workflow
A common voice workflow is:
- design a reusable voice
- record or create the audio
- convert the audio into the designed voice if needed
- align the audio under the video clip
- run LipSynch