Turn One Photo into a Talking Video with Voice and Captions

October 16, 2026
Use Cases

Want to share an idea on Reels, Shorts, or TikTok without filming yourself speaking? With CNAPS Studio, you can combine one photo, a short script, and a background clip to create a vertical talking video with voice and captions.

The prepared Talking Presenter Ad card brings these pieces together. Use it to introduce a product, explain a feature over a screen recording, or share a short announcement. You do not need to build a flow to get started.

You can start with 3 free runs across all CNAPS Studio cards without an account. A free plan is also available after signup. Sign in to download your result.

One photo, a script, and a background clip

You provide three ingredients:

  • A photo of one person. Choose a front-facing portrait in PNG, JPG, or WebP format. The photo’s background is replaced automatically.
  • The words you want spoken. Write a short script. The input area shows an estimated speaking time as you type.
  • A background video. Add a product clip or screen recording. The card recommends vertical footage for this layout.

The result combines a talking presenter, your background footage, and boxed captions in one video. Choose a clip that supports your message and keeps important details visible behind the presenter and text.

See the headphones example

In this example, a portrait of a woman is combined with footage of mint-colored headphones against a peach background. The presenter appears in the lower part of the vertical video, with the headphones above her. White words in black caption boxes accompany the message.

Watch the sample below to see how the photo, script, and background clip become a talking video.

Input portrait of a woman in a lavender cardigan
Presenter photo
Background product clip
Actual card sample: a talking presenter, background footage, and boxed captions.

The sample script reads:

Meet the headphones that block out the noise and keep the music in. Forty hours of battery, one tap to pair, and so light you'll forget they're on. Hear the difference today.

This example is a product promotion, but the same structure can support other messages. Pair a feature walkthrough with a screen recording, introduce a new release over relevant footage, or explain one useful tip with a visual example. Keep the script focused on one idea and end with a clear next step.

How to make your own talking video

  1. Open the card. Go to Talking Presenter Ad.
  2. Add your photo. In Input, remove the sample photo if it is present, then upload a front-facing image of one person.
  3. Write your script. Replace the text in How should we change it? with the words you want spoken. Read it aloud to check that it sounds natural.
  4. Add your background clip. Replace the sample in Background video with your product footage or screen recording.
  5. Run and review. Click Run. The card lists a usual wait of 10–25 minutes. Watch the result with sound and check the speech, captions, and how the presenter sits over your footage.
  6. Download your video. Sign in to download your result, then review it in your chosen platform’s upload preview before posting.

Do I need to record myself speaking?

No. You provide a photo and a written script. The card creates the talking presentation and combines it with your background clip.

Is this only for ads?

No. An ad is one example. You can also use the format for short explainers, feature introductions, and announcements by changing the script and background footage.

Does it include voice and captions?

Yes. The result includes a spoken presentation and boxed captions. Review both before sharing your video.

Turn your photo into a talking video →

Start with one photo, one message, and a background clip for your next short-form video.

Related Posts

Get new posts by email.

New research notes, customer workflows, and model integrations straight from the team.

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form