Lip Sync

How to sync a character's mouth to an audio track, and how to handle audio and video that are not the same length.

Lip Sync on Morphic matches a character's mouth to an audio track. Some models re-voice a video you already have; others start from a portrait or character image and make a talking video as long as the speech.

  1. Go to Morphic.
  2. Open an existing file, or click 'New file' to create a new one under a project.
  3. Head to the global prompt bar at the bottom of the Canvas, switch the mode to Video, then select Lip Sync.

The Video mode menu with Lip Sync highlighted

  1. Choose your lip sync model. Which models you see depends on what your organization has switched on for lip sync, so the list can differ from a teammate's. See Model access.

The lip sync model picker, listing Sync V3, HeyGen, Kling Lip Sync, LTX 2.5, MiniMax H3 Max, OmniHuman 2.0, Seedance and Veed Fabric, with the HeyGen submenu open on HeyGen Avatar 6 and HeyGen Avatar 6 Turbo

  • HeyGen Avatar 6 and HeyGen Avatar 6 Turbo, on every plan, take one portrait or one character video plus speech up to 10 minutes, and return a talking video as long as the speech, at up to 2K. Turbo costs less. A video of a real person is refused; use a portrait for a real person
  1. Click the paper clip icon to attach your references. You can:
  • Select on Canvas - pick references already placed on your Canvas
  • Select from Assets - pick from your Assets library
  • Upload asset - upload a file from your device

The attach menu: Select on Canvas, Select from Assets and Upload asset

  1. Attach a video, or an image for a model that starts from a portrait, along with the audio file you want it synced to.

The prompt bar in Lip Sync, with an empty References box asking for 1 video and 1 audio

To choose what happens when the audio and video lengths differ, click the settings button and pick a 'Sync Mode':

Lip sync settings above the prompt bar, with Sync Mode set to Default

The Sync Mode menu: Default, Cut Off, Loop, Bounce, Silence and Remap

OptionWhat it does
Cut OffTrims the longer of the audio or video to match the shorter one.
LoopWhen the video is shorter than the audio, loops the video to match the audio.
BounceWhen the video is shorter than the audio, plays the video forward then reverses it to match the audio.
SilenceWhen the video is longer than the audio, pads the audio with silence to match the video.
RemapSlows down or speeds up the video to match the audio duration exactly. Keeps the full content of both by adjusting playback speed.

What it costs

Lip sync models are priced differently from one another, and most are billed per second of output. The current rate for every lip sync model is in the Lip sync table on Plans & Credits.

That's how you use the Lip Sync feature on Morphic. It's a great fit for filmmakers, animators, and marketers who want to generate AI lip sync videos for characters, ads, and dialogue-driven scenes.


If you have any trouble or have any questions, feel free to reach out. We're happy to help. Write to us at support@morphic.com.

On this page