Ever wish you could bring a photo to life? With HeyGen's new Avatar IV model, it's easier than ever. Just upload a photo, type in a script, choose a voice, and watch it turn into a lifelike talking video. Create fun content or build something for your brand. With HeyGen, you can magically transform your imagination into reality without having any video editing skills.
In this tutorial, you’ll learn how to convert photos into talking videos. All you need is a script and a voice to make it happen. We will discuss how to upload your photo, add script and voice, and finally generate the talking video.
By the end of this tutorial, you’ll learn how to:
- Set up HeyGen for the talking video
- Upload a photo
- Add a script and voice
- Generate the video
Let’s get right into it!
Step 1 - Set up HeyGen for the talking video
Navigate to HeyGen. Log in to an account or create a new one.

You’ll see the main dashboard after logging in. Click home. Look for ‘Photo to Video with Avatar IV’ in the main dashboard. Click it to access the tool.

Click ‘Create Video.’

You’ll be taken to a simple, intuitive interface.

Step 2 - Upload a photo
When you get to the upload section, you’ll see a message saying, “Upload photo or drag and drop here.” Pick a good-quality image where the face is easy to see—ideally something that’s 720p or higher. The clearer the face, the better the AI works.

Once you upload your photo, it pops up in the preview window, all set to turn into a talking avatar.
Step 3 - Add a script and voice
In the script box, just type or paste what you want your avatar to say—or upload an audio file if that's more your style.

There is a limit to the number of characters you can write in the script box. You have to buy a subscription to increase the time limit. Once the time limit is increased, you can add more words to your script.
Next up, pick a voice by clicking “Select voice.” You've got a few options:
Use one from HeyGen's voice library:
- Clone a voice with a 2-minute audio clip
- Create a brand new voice from a text description
- Or connect a voice from a third-party service like ElevenLabs
Click the ‘Select Voice’ box.

After selecting a voice or recording your own, it’s time to click ‘Generate video.’

Step 4 - Generate the video
Heygen will take a few minutes to an hour to generate a video, depending on the number of videos it has in its pipeline. You can also change the orientation of the video by clicking the portrait or landscape icon at the bottom of the uploaded image. It depends on where you want the video to feature. If it’s Instagram, you can use the portrait mode for your video.

You'll get a notification as soon as it's ready. Here are the results.
That's it for this tutorial. For the best results, choose a high-resolution photo that’s well-lit and clearly shows your face. When writing your script, keep it casual and engaging to bring your avatar to life.