GoHighLevel Workflows Can Now Make Video: The AI Video Generation Action Explained

Status check: the action is listed as new under Automations on HighLevel's changelog. The entry doesn't mention Labs or a beta. It isn't tested in my account yet, so this is based on HighLevel's release notes. If you don't see it under AI Actions in your workflow builder yet, check the changelog entry linked below or ask HighLevel support.

What the action does

Until now, a workflow could send a video you uploaded in advance, but it couldn't make one. The AI Video Generation action lets the workflow create the clip itself from a prompt. HighLevel puts it this way: no camera, no editor, no studio.

The settings at a glance

How to set it up (steps from HighLevel)

1. Go to Automation > Workflows and open a workflow.
2. Add the AI Video Generation action from AI Actions.
3. Select the model and the quality. The defaults are Veo 3.1 Quality and Standard (720p).
4. Write the prompt, or insert a custom value so the prompt comes from your data at run time.
5. Click Enhance Prompt or start from a template (optional).
6. Add reference images (optional).
7. Open Additional Settings for the size, the duration and Generate Audio (optional).
8. Save the action, then use the returned video URL in the next steps.

What you can do with the video URL

HighLevel lists the next steps: send the link in an email or SMS, save it to a custom field, or pass it to a webhook. Because the prompt can pull from your data, one workflow can make a different video for every contact who passes through it.

Practical uses for an agency client:

• A personal thank you clip: after a booking or purchase, build the prompt from the service or product name and text the link with the confirmation.
• Product mockups on demand: when a new product is added and a webhook fires, start from the Product Mockups template with the product photo as a reference image, then save the URL to a custom field for the team to review.
• Short social clips: use the Social Post template in Portrait size and send the URL to a webhook or to your team for approval before anything is posted.

Keep a human check before anything goes out publicly. AI video can surprise you, and a short review step in the workflow costs very little.

Cost and privacy: read this before you switch it on

• Premium action: each execution has an additional charge. HighLevel says the cost depends on the model, the quality, the duration and Generate Audio (which raises the per second cost), and asks you to treat any cost figure as a planning estimate, not a fixed rate.
• Watch your triggers: a workflow that makes a video for every contact can add up fast on a big list, so test it on a small tagged group first.
• Public links: every video is stored at a public URL that anyone with the link can open without logging in. Keep customer data out of prompts unless you're comfortable with that.
• Reference images need 8 seconds: the duration switches to 8 seconds automatically when you add one.

New (29 Oct 2026): AI Analyze Video workflow action

HighLevel has added a second video action, posted on its changelog on 29 October 2026. AI Analyze Video lets a workflow watch a video. You give it a public video URL and a prompt, Google Gemini looks at the picture and listens to the sound, and it returns a text answer (the Response) for the actions that follow. It takes a public YouTube link or a direct link to a video file such as MP4, MOV or WebM. Vimeo and TikTok page links are blocked by those sites, and each action analyses one video URL.

Setup, as HighLevel describes it:

1. In Automation > Workflows, open a workflow and add AI analyze video from AI Actions.
2. Select the model: Gemini 3.8 Flash (the default) or Gemini 3.5 Flash Lite.
3. Add the video URL, typed in or inserted from a previous step or a custom value, and write the prompt.
4. Optionally open the Test tab and click Test Action. Then save the action and use the Response in the next steps.

Example uses: check a clip made by AI Video Generation before it reaches a customer, or summarise a video sent in through a form and save the summary to a custom field.

Cost: it is a premium action, charged per run based on the tokens used, so the model, video length and answer length all affect the cost. I haven't tested it in my account yet, so this is from HighLevel's release notes.

Where it fits with this week's other workflow updates

This sits nicely next to the new Loop, Router and AI Agent Skills: a Loop could run the video action once per product in a webhook, and a Router could send each clip to the right team. For the rest of this week's HighLevel news, see my running LevelUp 2026 roundup.