> For the complete documentation index, see [llms.txt](https://help.imagine.art/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.imagine.art/creative-suite/video-tools/lipsync.md).

# Lipsync

## What is Lipsync?

AI Lip Sync technology allows you to transform still images into dynamic, talking avatars by syncing facial movements to audio or text. With just a photo, text-to-speech, or voiceover, you can create professional-grade videos with lip-syncing avatars in minutes.

<figure><img src="/files/W3G9S6Q0nx7ofxHkJmvN" alt=""><figcaption></figcaption></figure>

## How to use Lipsync?

{% stepper %}
{% step %}
**Select** [**Lipsync**](https://www.imagine.art/lipsync-studio) from the side navigation.
{% endstep %}

{% step %}
**Select Your Lip Sync Model**\
Choose the lip sync model that best fits your project. Different models offer settings like duration, resolution, and aspect ratio, with unique results.

<figure><img src="/files/JxbGN9u6CG24aBTC5yFJ" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}
**Upload Your Image**\
Upload an image of your avatar or select one from your existing creations. Ensure the image is clear for the best results.
{% endstep %}

{% step %}
**Generate Audio or Write Text**\
Some models allow you to generate speech from a variety of voices, while others use text-to-speech with a default voice. Write the script or upload an audio file.

<figure><img src="/files/REPXMJf1J8gOd7j4HtE8" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}
**Describe the Scene**\
Enter the prompt to describe the scene or action your avatar will perform, such as "avatar speaking in a classroom."
{% endstep %}

{% step %}
**Click "Generate"**\
Hit **Generate** to create your talking avatar. The AI will sync the facial movements and lip sync to the provided audio or text.
{% endstep %}
{% endstepper %}

### Support

**Lipsync** is supported by the following models:

| **Model**                 | **Aspect Ratio**       | **Duration** | **Resolution**    |
| ------------------------- | ---------------------- | ------------ | ----------------- |
| **Kling 2.6 Pro**         | Same as image provided | 5s, 10s      | 1080p             |
| **Google Veo 3.1 Fast**   | 16:9, 9:16             | 8s           | 720p, 1080p       |
| **Google Veo 3.1**        | 16:9, 9:16             | 8s           | 720p, 1080p       |
| **Wan 2.5 Speak**         | 16:9, 9:16             | 5s, 10s      | 720p, 480p, 1080p |
| **Kling Avatars 2.0 Pro** | Same as image provided | 5s, 10s      | 1080p             |
| **Infini Talk**           | Same as image provided | 6s           | 720p, 1080p       |
| **OmniHuman - Bytedance** | Same as image provided | 5s, 10s      | 720p, 1080p       |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://help.imagine.art/creative-suite/video-tools/lipsync.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.