> ## Documentation Index
> Fetch the complete documentation index at: https://docs.imagine.art/llms.txt
> Use this file to discover all available pages before exploring further.

# Wan 2.5 Speak

> Alibaba's Wan 2.5 in ImagineArt Lipsync Studio — generate a talking video from an image and a written script.

## Wan 2.5 Speak

Wan 2.5 Speak is the Lipsync Studio version of Alibaba's [Wan 2.5](/ai-models/video/wan-2-5). Instead of uploading an audio file, you write what the subject should say in **Audio Text**, and the model generates the video with matching speech. In the model list it is described as "The best in class open source model with audio".

## Specifications

| Feature | Details |
| - | - |
| **Developer** | Alibaba |
| **Where to find it** | Video Studio → **Lipsync Studio** |
| **Resolution** | 480p, 720p or 1080p |
| **Duration** | 5 or 10 seconds |
| **Aspect ratios** | 16:9, 9:16 |
| **Inputs** | One image (JPG, JPEG, PNG or WEBP, up to 30MB), **Audio Text** script (up to 2,000 characters) and a **Prompt** (up to 2,000 characters) |

## How to use

<Steps>
  <Step title="Open Lipsync Studio">
    Go to **Video** and select **Lipsync Studio** from the Video Tools tabs.
  </Step>

  <Step title="Select the model">
    Open **Select Model** and choose **Wan 2.5 Speak**.
  </Step>

  <Step title="Set aspect ratio, duration and resolution">
    Choose **16:9** or **9:16**, **5s** or **10s**, and a resolution.
  </Step>

  <Step title="Add your image, script and prompt">
    Upload the image under **Upload Image**. Type the spoken lines in **Audio Text**, and describe the scene or motion in **Prompt**.
  </Step>

  <Step title="Generate">
    Click **Generate**.
  </Step>
</Steps>

## Other Lipsync Studio models

| Model | Resolution | Inputs |
| - | - | - |
| **Wan 2.5 Speak** | 480p–1080p | Image + audio text + prompt |
| [Fabric 1.0](/ai-models/video/fabric-1-0) | 480p–720p | Image + audio |
| [Infini Talk](/ai-models/video/infini-talk) | 480p–720p | Image + audio + prompt |
| [Kling Avatars 2.0 Pro](/ai-models/video/kling-avatars-2-0-pro) | — | Image + audio + prompt |
| [OmniHuman](/ai-models/video/omnihuman) | — | Image + audio + prompt |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.