> ## 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](https://docs.imagine.art/ai-models/video/wan-2-5.md). 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.

## 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

**1. Open Lipsync Studio**

Go to **Video** and select **Lipsync Studio** from the Video Tools tabs.

**2. Select the model**

Open **Select Model** and choose **Wan 2.5 Speak**.

**3. Set aspect ratio, duration and resolution**

Choose **16:9** or **9:16**, **5s** or **10s**, and a resolution.

**4. 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**.

**5. Generate**

Click **Generate**.

## Other Lipsync Studio models

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


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