> ## 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.

# Infini Talk

> Audio-driven talking-avatar model in ImagineArt Lipsync Studio — animate a portrait with lip sync, head and body motion.

## Infini Talk

Infini Talk creates realistic talking avatars from an image and an audio track. It is based on [InfiniteTalk](https://github.com/MeiGen-AI/InfiniteTalk), an open-source audio-driven video generation model from MeiGen-AI that syncs lips, head movement, body posture and facial expressions to the audio. In ImagineArt it's in **Lipsync Studio**.

## Specifications

| Feature | Details |
| - | - |
| **Developer** | MeiGen-AI (open source) |
| **Where to find it** | Video Studio → **Lipsync Studio** |
| **Resolution** | 480p or 720p |
| **Inputs** | One image (JPG, JPEG, PNG or WEBP, up to 30MB), audio and an optional prompt |
| **Audio** | Upload an audio file with **Add Audio**, or create one with **Generate Audio** |
| **Duration** | Set by the length of your audio |

## 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 **Infini Talk**.

**3. Choose a resolution**

Pick **480p** or **720p** under **Resolution**.

**4. Add your image, audio and prompt**

Upload the image under **Upload Image**, then click **Add Audio** or **Generate Audio**. Use **Prompt** to describe expression or motion.

**5. Generate**

Click **Generate**.

> [!TIP]
>
> See [Lipsync](https://docs.imagine.art/video-tools/lipsync.md) for tips on choosing a portrait that syncs well.

## Other Lipsync Studio models

| Model | Resolution | Inputs |
| - | - | - |
| **Infini Talk** | 480p–720p | Image + audio + prompt |
| [Fabric 1.0](https://docs.imagine.art/ai-models/video/fabric-1-0.md) | 480p–720p | Image + audio |
| [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 |
| [Wan 2.5 Speak](https://docs.imagine.art/ai-models/video/wan-2-5-speak.md) | 480p–1080p | Image + audio text + prompt |


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