# VideoSDK AI avatar

**URL:** <https://devforum.zoom.us/t/videosdk-ai-avatar/134151>\
**Category:** Video SDK\
**Tags:** video-sdk\
**Created:** [June 18, 2025, 2:04pm UTC](https://devforum.zoom.us/t/videosdk-ai-avatar/134151 "2025-06-18T14:04:59Z")\
**Posts on this page:** 9\
**Page:** 1

<div class="post-metadata">

**Author:** ![Piotr](https://sea2.discourse-cdn.com/flex016/user_avatar/devforum.zoom.us/piotr/32/49447_2.png) [@Piotr](https://devforum.zoom.us/u/Piotr)\
**Post date:** [June 18, 2025, 2:04pm UTC](https://devforum.zoom.us/t/videosdk-ai-avatar/134151/1 "2025-06-18T14:04:59Z")

</div>

Hello,  
i would like to ask if it is possible to build AI avatar that will be able to communicate real time with other participant and will have access to the audio/video? Is there any api in video sdk to create such converstational bot that will be meeting participant?

Thank you

---

<div class="post-metadata">

**Author:** ![ticorrian.heard](https://sea2.discourse-cdn.com/flex016/user_avatar/devforum.zoom.us/ticorrian.heard/32/70213_2.png) [@ticorrian.heard](https://devforum.zoom.us/u/ticorrian.heard)\
**Post date:** [June 20, 2025, 5:06pm UTC](https://devforum.zoom.us/t/videosdk-ai-avatar/134151/2 "2025-06-20T17:06:36Z")

</div>

Hi @Piotr At the moment, there is no AI avatar for Video SDK . We do have feature [raw data](https://developers.zoom.us/docs/video-sdk/ios/raw-data/) that you could use to implement that feature in your application.

---

<div class="post-metadata">

**Author:** ![freelancer.nak](https://sea2.discourse-cdn.com/flex016/user_avatar/devforum.zoom.us/freelancer.nak/32/40968_2.png) [@freelancer.nak](https://devforum.zoom.us/u/freelancer.nak)\
**Post date:** [June 21, 2025, 11:42am UTC](https://devforum.zoom.us/t/videosdk-ai-avatar/134151/3 "2025-06-21T11:42:24Z")

</div>

@Piotr Hi,

Thank you for your question!

Video SDK’s **native SDKs** (Linux, Windows, macOS) support **raw data access** for remote participants, so you can process audio/video streams directly for your AI avatar.

For the **Web SDK** , direct raw data access isn’t provided. You’ll need to apply alternatives — for example, access the underlying **`<video>`** and **`<audio>`** tags or their **media stream objects** , and then pipe or process those streams as needed.

In both native and web cases, I suggest you:

- **Create virtual audio and video devices** and pipe input/output streams to and from these devices.  
On **Linux** , for example, you can use tools like `v4l2loopback` (for virtual video devices) and `snd-aloop` (for virtual audio devices) to route and process streams cleanly.
- Optionally explore third-party avatar/AI APIs that provide conversational or visual avatars, such as **HeyGen** , **Tavus** , or similar platforms that can integrate with your media streams.

Let me know if you’d like guidance on setting up virtual devices or integrating external avatar APIs!

Best,  
Naeem Ahmed

---

<div class="post-metadata">

**Author:** ![Piotr](https://sea2.discourse-cdn.com/flex016/user_avatar/devforum.zoom.us/piotr/32/49447_2.png) [@Piotr](https://devforum.zoom.us/u/Piotr)\
**Post date:** [June 24, 2025, 12:28pm UTC](https://devforum.zoom.us/t/videosdk-ai-avatar/134151/4 "2025-06-24T12:28:33Z")

</div>

We will implement solution with Web VideoSDK. Do you have any tutorial on how to set up a poc of Avatar with raw data usage?

---

<div class="post-metadata">

**Author:** ![Piotr](https://sea2.discourse-cdn.com/flex016/user_avatar/devforum.zoom.us/piotr/32/49447_2.png) [@Piotr](https://devforum.zoom.us/u/Piotr)\
**Post date:** [June 24, 2025, 12:30pm UTC](https://devforum.zoom.us/t/videosdk-ai-avatar/134151/5 "2025-06-24T12:30:31Z")

</div>

Here is the raw data tutorial. Is this proper way to implement avatar in webSDK? [Video SDK - web - Raw data](https://developers.zoom.us/docs/video-sdk/web/raw-data/)

---

<div class="post-metadata">

**Author:** ![ticorrian.heard](https://sea2.discourse-cdn.com/flex016/user_avatar/devforum.zoom.us/ticorrian.heard/32/70213_2.png) [@ticorrian.heard](https://devforum.zoom.us/u/ticorrian.heard)\
**Post date:** [June 24, 2025, 3:26pm UTC](https://devforum.zoom.us/t/videosdk-ai-avatar/134151/6 "2025-06-24T15:26:27Z")

</div>

Thats correct @Piotr you can also view the raw data sample app [here](https://github.com/zoom/videosdk-web-processor-sample)

---

<div class="post-metadata">

**Author:** ![Piotr](https://sea2.discourse-cdn.com/flex016/user_avatar/devforum.zoom.us/piotr/32/49447_2.png) [@Piotr](https://devforum.zoom.us/u/Piotr)\
**Post date:** [June 24, 2025, 5:54pm UTC](https://devforum.zoom.us/t/videosdk-ai-avatar/134151/7 "2025-06-24T17:54:25Z")

</div>

Thanks a lot! Maybe do you have any example on how to integrate avatar using raw wideo?

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/flex016/uploads/zoomdeveloper/original/3X/6/1/614bdd549b610bbaa46ff934617683a02bdaa03c.png) [@system](https://devforum.zoom.us/u/system)\
**Post date:** [June 27, 2025, 6:29pm UTC](https://devforum.zoom.us/t/videosdk-ai-avatar/134151/8 "2025-06-27T18:29:59Z")

</div>

Closed on June 27, 2025, 6:29pm UTC

This topic was automatically closed 25 hours after the last reply. New replies are no longer allowed.

---

<div class="post-metadata">

**Author:** ![ticorrian.heard](https://sea2.discourse-cdn.com/flex016/user_avatar/devforum.zoom.us/ticorrian.heard/32/70213_2.png) [@ticorrian.heard](https://devforum.zoom.us/u/ticorrian.heard)\
**Post date:** [July 1, 2025, 2:56pm UTC](https://devforum.zoom.us/t/videosdk-ai-avatar/134151/9 "2025-07-01T14:56:45Z")

</div>

At the moment, we do not a sample app for that.