Skip to main content

How to Use HeyGen Video Podcast

Turn any topic into a polished two-host podcast video. No cameras, microphones, or editing suite required.

Written by L2 Support

What Is HeyGen Video Podcast?

HeyGen Video Podcast lets you turn an idea into a finished podcast video, complete with two Avatars talking it through like a real conversation. You pick a Host and a Guest, tell HeyGen what the episode is about, and it produces a natural back-and-forth between your two speakers, along with the scene they're sitting in and close-up shots of each one.

You give HeyGen something to talk about (a topic, a prompt, an uploaded document, or your own full script) and it handles the dialogue and the pacing for you.

💡 Good to know: A Video Podcast holds two speakers at most and runs up to three minutes. If you want a longer episode, the best approach is to create several short videos and combine them in your video editor.

A few people who tend to get the most out of it:

  • Content creators making short, talk-show-style clips for social feeds

  • Educators and trainers turning a single concept into a quick two-person explainer

  • Marketers and brands publishing bite-sized, on-topic episodes at scale

How to use HeyGen's Video Podcast feature:

Ready to create your podcast? From the Homepage, head to Apps > Create > Video Podcast and start bringing your conversation to life!

For an even faster start, use the built-in Ask AI assistant to jump straight to the Video Podcast tool, as shown below.

Step 1: Choose Your Host and Guest

At the top of the page you'll see two speaker slots; the Host and the Guest with a swap icon () between them.

Click on the Avatar to open its menu. From there you can pick an existing avatar from your HeyGen library with Choose Avatar, or create one from a photo with Upload photo. You can also use Invite a Guest to bring another HeyGen user’s avatar onto your podcast—making every episode truly one of a kind.

Step 2: Set Each Speaker's Voice

Under each avatar's name you'll see the voice assigned to that speaker, with a little play button so you can hear a sample and change to a different voice.

Try to choose two voices that contrast with each other. When the voices are distinct, the dialogue feels like two real people chatting rather than one narrator reading both sides.

Step 3 (Optional): Invite a Guest Speaker

Want a friend or colleague's avatar to co-host with you? Click Invite a guest (the star icon near the Guest slot) to open the Invite a guest speaker window.

This is where you request access to someone else's Avatar so they can guest-host your episode. Type in their email, click Send invite, and once they approve, their avatar becomes a shared speaker you can drop into the conversation alongside yours.

Step 4: Add Your Podcast Content

The Podcast Content box is where you can prompt what the episode should cover. You've got two ways to do this:

Let HeyGen write it for you. Leave the Use my own script toggle off, then either type a topic or prompt describing what you'd like your hosts to talk about, or upload a document using the upload icon below the box. HeyGen takes it from there and writes a natural, two-person conversation based on what you gave it.

Bring your own script. Flip on the Use my own script toggle and the box switches to Your Script mode. As the note on screen points out, when you paste in a full script, HeyGen formats it into the conversation exactly as written and doesn't rewrite your words.

Which Video Podcast Option Should You Choose?

Go with the AI option when you want speed and a ready-made structure. Use your own script when the exact wording matters, like brand messaging, legal or compliance language, or anything you've already had approved.

Step 5: Configure Your Video Settings

Choose the video layout, length, and resolution that best match your publishing platform and audience.

Select a Video Layout

Video Layout determines your video’s aspect ratio:

  • 16:9 Landscape: Best for YouTube, websites, presentations, and desktop viewing.

  • 9:16 Portrait: Best for YouTube Shorts, Instagram Reels, TikTok, and other vertical video feeds.

Choose the Video Length

Episodes can be 1, 2, or 3 minutes long. Three minutes is the maximum length for a single episode.

For longer videos, create a series of one- to three-minute episodes. You can then combine the episodes into one continuous video using your preferred video editor.

Set the Video Resolution

Resolution controls the video’s output quality:

  • 1080p: Recommended for higher-quality, professional-looking video.

  • 720p: Suitable when you need a smaller file or faster processing.

For the best viewing experience, select 1080p unless file size or processing speed is a priority.

Resolution feeds into your credit cost for the final video, which we'll get to in a moment, so match the quality to where the video will actually live. 1080p is a solid default for most things, while 720p can save you credits on quick drafts or lower-stakes clips.

Step 6 (Optional): Add Scene Instructions. Describe Your Podcast’s Visual Style

The Scene Instructions field is optional, but it's where you can shape the look and feel of the episode. Describe the setting, camera angles, atmosphere, lighting, pacing, and visual elements you want. Focus on the podcast’s environment and production style—not the dialogue

✍🏻 Example - Modern podcast studio with two hosts seated across from each other at a large matte walnut table with professional microphones mounted on black boom arms. The studio features a premium contemporary design with warm oak wood slat walls, charcoal acoustic panels, floating shelves decorated with books, plants, ceramics, and subtle LED accent lighting. Soft warm key lighting combined with gentle rim lighting creates a cinematic, inviting atmosphere with natural skin tones. Alternate between wide two-shots, close-ups of the active speaker, over-the-shoulder angles, and natural reaction shots with subtle camera movement and realistic podcast pacing.

Step 7: Generate Your Preview

Once your speakers, content, and settings are in place, click Generate Preview in the right-hand panel. Before you do, HeyGen shows an estimated credit cost (for example, "100 credits now · 140 total" in the screenshots).

The preview is your first draft. It gives you a full look at the episode so you can check everything before you commit to the final render. (There's more on how the charges break down in the billing section below.)

Step 8: Review the Script and Scene

When the preview is ready, you'll see your episode laid out in full.

  • The Script panel displays timestamped dialogue by speaker. Use each line’s play button to check the pacing, tone, and pronunciation.

  • The Details panel includes a scene preview, speaker thumbnails, and an option to regenerate the scene.

  • Review and edit everything before generating the final video. This helps prevent mistakes and avoids wasting credits on a version you need to redo.

Step 9: Create Your Podcast

Happy with your script, podcast scene, avatars, and episode details? Click Create Podcast to render your final AI podcast video. Before you continue, the button will displays the number of credits required. For example, the screenshots show a cost of 30 credits for an approximately one-minute podcast video rendered in 1080p.

Once rendering is complete, your HeyGen video podcast is ready to download, publish, and share with your audience!


How Podcast Credits Work

HeyGen uses credits at two separate stages of the Video Podcast process:

  1. Preview: A fixed number of credits is charged when you generate the preview.

  2. Final video: An additional per-minute charge is applied when you generate the final video. The rate depends on your selected resolution.

In other words:

Total credit cost = preview charge + final video charge

The final video will use more credits if it is longer or generated at a higher resolution. To make the most of your credits, use the preview to carefully review your script, avatars, and scene before creating the final video.


Frequently Asked Questions

What does HeyGen Video Podcast create?

It brings your podcast to life as a polished video, featuring a scripted back-and-forth between Host and Guest avatars. Every episode includes a generated podcast scene, dynamic close-up speaker shots, and a ready-to-use episode description.

Do I have to write the script myself?

Not at all! Simply enter a topic or prompt—or upload a document—and HeyGen will create the conversation for you. Want complete control over every word? Turn on Use My Own Script and paste your full script. HeyGen will format it exactly as written, without rewriting your content.

Can I use a real person's avatar as a guest?

Yes! You can feature one of your own avatars or click Invite a Guest to bring another HeyGen user’s avatar into your podcast. Simply enter their email and send the invitation. Once they approve your access request, their avatar will be ready to join your episode!

How many avatars can be in a Video Podcast?

Two: one Host and one Guest.

What's the longest an episode can be?

Choose a target length of 1, 2, or 3 minutes. The final podcast may run slightly shorter or longer than your selection, allowing the conversation to follow the script with a smooth, natural pace.

How do I add more than two people to the podcast?

You can feature up to two people at a time—but the possibilities don’t stop there! Create your podcast in segments and introduce different guests throughout the episode for a more dynamic, engaging conversation.

Can I change the scene if I don't like it?

Yes. The preview includes a regenerate icon that creates a new version of the setting.

Can I preview the audio before rendering?

Yes. In the script view, every line has its own play button, so you can listen line by line.

Did this answer your question?