# Lip Sync

Here's a quick tutorial on how to use Lip Sync on Morphic:

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.

<figure><img src="https://3522324598-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FoPhHCbNZdzW70rakoLhf%2Fuploads%2FphR686IhIdP84BABX9eU%2FCleanShot%202026-04-14%20at%2019.24.47.png?alt=media&#x26;token=c0391088-6fc8-4155-a1f9-016df7c2a052" alt=""><figcaption></figcaption></figure>

4. Choose your model: Sync V3 or Seedance 2.0.

<figure><img src="https://3522324598-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FoPhHCbNZdzW70rakoLhf%2Fuploads%2F6IWEnGjzPcDTJHt3EdFT%2FCleanShot%202026-04-14%20at%2019.25.11%202.png?alt=media&#x26;token=02055075-80ae-4e00-b78c-d50aff5af357" alt=""><figcaption></figcaption></figure>

5. Click the paper clip icon to attach your references. You can:

<figure><img src="https://3522324598-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FoPhHCbNZdzW70rakoLhf%2Fuploads%2FGXFLRIWRRfplbdZL8XoD%2FCleanShot%202026-04-14%20at%2019.35.50.png?alt=media&#x26;token=7ed62e7c-1b05-4497-81c8-9db40c70a054" alt=""><figcaption></figcaption></figure>

* 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

6. Attach a video, along with the audio file you want it synced to.

<div data-full-width="false"><figure><img src="https://3522324598-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FoPhHCbNZdzW70rakoLhf%2Fuploads%2FXGoZGANTG2mRVZko60MB%2FCleanShot%202026-04-14%20at%2019.38.09.png?alt=media&#x26;token=725a3565-3e3b-4202-a59e-405e90b6ed49" alt=""><figcaption></figcaption></figure></div>

7. Optionally, add a prompt with any extra direction, or leave the prompt bar empty.
8. Optionally, click the Preferences icon to set how Morphic handles length mismatches between your audio and video.
9. Click generate.

Note: If you're using Seedance 2.0, add a prompt of at least 3 characters (e.g., "create a lip sync") before generating.

### Tips for better results

* Use a video with the character's face clearly framed and the mouth visible throughout the clip you want synced.
* Feed it clean audio. Background noise, overlapping voices, or heavy music behind dialogue can weaken the sync.
* Match the audio tone to the character. A high-energy voice on a still, neutral portrait can look mismatched even with perfect lip sync.
* Keep the audio and source clip close in length. Large gaps force Morphic to stretch, loop, or trim, which can soften the final result even with the right Preferences set.
* Go easy on head movement in the source video. Limited, natural motion gives the sync the cleanest landing; fast cuts and extreme angles make it harder.

### Understanding Preferences

Audio and video often aren't the same length. Preferences control how the mismatch is handled in your output.

<div><figure><img src="https://3522324598-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FoPhHCbNZdzW70rakoLhf%2Fuploads%2FH0HHWxtMPMr6ZXfGBqqQ%2FCleanShot%202026-04-14%20at%2019.29.27.png?alt=media&#x26;token=55b1fbe6-0465-46e9-8a6f-f5e4530d5b7b" alt="" width="375"><figcaption></figcaption></figure> <figure><img src="https://3522324598-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FoPhHCbNZdzW70rakoLhf%2Fuploads%2FwpbnY5Skk1ptVk7A5C6U%2FCleanShot%202026-04-14%20at%2019.29.34.png?alt=media&#x26;token=f947e33b-469b-495f-a3d5-2e1c54871506" alt="" width="375"><figcaption></figcaption></figure></div>

| Option  | What it does                                                                                                                       |
| ------- | ---------------------------------------------------------------------------------------------------------------------------------- |
| Cut Off | Trims the longer of the audio or video to match the shorter one.                                                                   |
| Loop    | When the video is shorter than the audio, loops the video to match the audio.                                                      |
| Bounce  | When the video is shorter than the audio, plays the video forward then reverses it to match the audio.                             |
| Silence | When the video is longer than the audio, pads the audio with silence to match the video.                                           |
| Remap   | Slows down or speeds up the video to match the audio duration exactly. Keeps the full content of both by adjusting playback speed. |

### Lip sync credits consumption

| Model        | Auto         | 480p (SD)   | 720p (HD)    | 1080p (FHD) |
| ------------ | ------------ | ----------- | ------------ | ----------- |
| Sync V3      | 12 credits/s | -           | -            | -           |
| LTX 2.3      | 9 credits/s  | -           | -            | -           |
| Seedance 2.0 | -            | 28 credits  | 60 credits   | 60 credits  |
| Veed Fabric  | -            | 7 credits/s | 14 credits/s | -           |

Note: Seedance 2.0 charges a flat rate per generation. Per-second models are calculated based on output duration. For example, a 10-second lip-sync video using Veed Fabric at 720p (HD) would cost 140 credits (14 credits/s x 10s).

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**](mailto:support@morphic.com)**.**


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://morphic.com/docs/video/lip-sync.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
