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

# HeyGen

> Create talking-avatar and talking-photo videos from text with HeyGen.

# HeyGen

> **In one line:** Let your UnleashX agent turn a script into a video of a presenter — either a digital avatar or a talking version of a photo you provide.

|                    |                                                                               |
| ------------------ | ----------------------------------------------------------------------------- |
| **Category**       | AI & Media                                                                    |
| **Authentication** | Platform-managed                                                              |
| **Setup time**     | \~1 minute                                                                    |
| **Difficulty**     | Easy                                                                          |
| **Best for**       | Spokesperson videos, personalized outreach, training clips, and announcements |

## 1. Overview

HeyGen creates avatar videos: you give it text and it produces a video of a lifelike presenter speaking your words. It can use a built-in avatar, or animate a still photo into a "talking photo."

Once connected, your agent can generate text-to-video (an avatar reads your script) and image-to-video (a supplied photo becomes the speaker), optionally choosing a voice. The agent can submit the job and either return immediately with a video ID or wait for the finished video URL.

Connecting HeyGen to UnleashX lets your agents produce on-brand presenter videos at scale — personalized welcome messages, product walkthroughs, or campaign clips — straight from a script.

## 2. What you'll need

<Note>
  HeyGen is **built into UnleashX**. There is no HeyGen account for you to create and no API key for you to manage.
</Note>

* An active UnleashX account.
* The HeyGen / avatar-video feature enabled on your workspace/plan.
* A script (the text the avatar will say). For talking-photo, a public image URL.
* Permission to edit the agent (admin or editor role). Without it, ask a workspace admin to enable the feature.

## 3. Get your credentials

<Info>
  There are **no credentials to create**. HeyGen is platform-managed — UnleashX provisions and rotates the underlying HeyGen API key. You never see or handle it.
</Info>

If you are a workspace admin, optional platform-side configuration includes the HeyGen base URL and the generation endpoint (UnleashX ships working defaults). Avatar IDs and voice IDs are optional inputs you can pass per request.

| Platform-managed setting        | Plain-English reason it exists                                   |
| ------------------------------- | ---------------------------------------------------------------- |
| HeyGen API key                  | Provisioned and rotated by UnleashX so videos generate securely. |
| Base URL / generate endpoint    | Points UnleashX at the correct HeyGen API. Defaults are preset.  |
| Avatar ID / Voice ID (optional) | Lets you pick a specific presenter or voice per request.         |

## 4. Connect on UnleashX

<Steps>
  <Step title="Open your agent">
    Go to [https://www.tryunleashx.com](https://www.tryunleashx.com) and open the agent that should generate avatar videos.
  </Step>

  <Step title="Open Data Connectors">
    In the agent, click **Data Connectors**.
  </Step>

  <Step title="Find HeyGen and add it">
    Locate **HeyGen** and click **Connect** / **Add**. It's platform-managed — no key to paste, it activates immediately.
  </Step>

  <Step title="Confirm it's connected">
    The HeyGen tool should now show a **Connected** badge.
  </Step>
</Steps>

### Use HeyGen in a Workflow

Once connected, you can add **HeyGen** to any automation from the **Workflows** builder. Its triggers and tools appear in the Apps panel, marked with an **MCP** badge.

<Steps>
  <Step title="Add a trigger or action node">
    Open **Workflows → New Workflow**. On the canvas, click **+ Add Trigger** (or the **+** below any node) to add a step.

    <img src="https://mintcdn.com/unleashx/LXZeho1M8XzFkz0k/images/mcp/workflows/05-add-trigger.png?fit=max&auto=format&n=LXZeho1M8XzFkz0k&q=85&s=449a0c03b0c7b40e571ec02373a85259" alt="Add a trigger on the workflow canvas" width="1390" height="722" data-path="images/mcp/workflows/05-add-trigger.png" />
  </Step>

  <Step title="Pick HeyGen from the Apps panel">
    In the **Paths** panel, open the **Apps** tab and select **HeyGen**. Use the search box if you have many connectors.

    <img src="https://mintcdn.com/unleashx/LXZeho1M8XzFkz0k/images/mcp/workflows/06-apps-list.png?fit=max&auto=format&n=LXZeho1M8XzFkz0k&q=85&s=bbb8bb6e668c4f8e1f6fd5e4955a45f0" alt="Choose your app from the Apps list" width="2446" height="1550" data-path="images/mcp/workflows/06-apps-list.png" />
  </Step>

  <Step title="Choose a trigger or tool">
    Pick the trigger or action you want. Configure its fields — required fields are marked with a red asterisk (\*).
  </Step>

  <Step title="Add or select your account">
    Under **Selected account**, choose an already-connected account, or click **Add Account** to connect one now.
  </Step>

  <Step title="Save and test">
    Fill in the remaining fields and click **Save**. Use **Test** to verify the step, then toggle **Publish** when the workflow is ready.
  </Step>
</Steps>

<Note>
  The steps are the same for every connector. For the full workflow builder guide, see [Using MCP in Workflows](/mcp/workflows).
</Note>

## 5. Available tools

| Tool           | What it does                                           | Changes data? |
| -------------- | ------------------------------------------------------ | ------------- |
| Text to Video  | Generate a talking-avatar video from a text script     | ✏️ Yes        |
| Image to Video | Generate a talking-photo video from an image plus text | ✏️ Yes        |
| Get Info       | Report HeyGen configuration and readiness              | No            |

<Note>
  The generate tools are marked ✏️ Yes because they create a new video. They do not modify or delete any existing data.
</Note>

## 6. Example usage

**"Have an avatar read this welcome message for new customers."**
→ Runs **Text to Video** with the script (and optional avatar/voice), returning a video ID or URL.

**"Turn this headshot into a short talking-photo intro."**
→ Runs **Image to Video** with the image URL and the script.

## 7. Permissions & data access

**UnleashX can:**

* Send your script (and optional image URL, avatar, voice) to HeyGen.
* Submit the generation job and fetch the resulting video status/URL.

**UnleashX cannot:**

* Generate video from content you don't provide.
* Edit or delete videos created outside this flow.
* Access your HeyGen account assets beyond what you pass in.

**To disconnect:** Open the agent → **Data Connectors** → **HeyGen** → **Disconnect**. Access is revoked immediately.

## 8. Troubleshooting

| Problem                   | What it means                                  | How to fix it                                                       |
| ------------------------- | ---------------------------------------------- | ------------------------------------------------------------------- |
| "prompt is required"      | No script text was supplied                    | Provide the text the avatar should say                              |
| "image\_url is required"  | Talking-photo called without an image          | Pass a public image URL                                             |
| Status stuck / timeout    | The video is still rendering                   | Poll again, or call with `wait_for_completion` set                  |
| 401 / credential error    | The platform-managed HeyGen key is unavailable | Platform-side — contact **[cs@unleashx.ai](mailto:cs@unleashx.ai)** |
| 403 / feature not enabled | HeyGen isn't enabled on your plan              | Ask a workspace admin or contact support                            |

For general connector issues, see [/mcp/integrations](/mcp/integrations).

## 9. Frequently asked questions

**Is my script or photo stored?**
They're sent to HeyGen to render the video. They are not retained by the integration beyond producing your result.

**Do I need a HeyGen account?**
No. HeyGen is platform-managed — UnleashX provides and rotates the key.

**Can I choose the avatar and voice?**
Yes. Pass an `avatar_id`, `voice_id`, or `talking_photo_id` per request; otherwise sensible defaults are used.

**Can multiple team members use it?**
Yes. Once enabled on the workspace, anyone with access to the agent can generate videos.

## 10. References

* HeyGen API docs: [https://docs.heygen.com/](https://docs.heygen.com/)
* UnleashX dashboard: [https://www.tryunleashx.com](https://www.tryunleashx.com)
* UnleashX integrations help: [/mcp/integrations](/mcp/integrations)