AI Audiobook Video Generator

Show the narrator while an excerpt plays. Upload one narrator photo and one audiobook passage you have the rights to use, and generate a video of that narrator speaking it.

Input: Narrator photo + audiobook excerpt · Output: MP4, 4–120 seconds

Start generating See pricing

Sample: Podcast host · Host photo + voice clip. Generated with OmniHuman 2.

How it works

Step 1
Upload a photo of the narrator — yourself, someone who consented, or an original fictional narrator.
Step 2
Add a short excerpt as WAV or MP3. You are responsible for the rights to that recording.
Step 3
Generate a clip of the narrator performing that excerpt and download the MP4.

Why use it

Excerpt-sized clips

A chapter is usually too long for one file. Pick a passage. Each video is 4 to 120 seconds long.

The recording you already have

Bring the produced audiobook audio. A generated speech voice is a stock synthetic voice, not a clone of the book narrator.

Same narrator across excerpts

Reuse one consented photo so a series of clips looks consistent.

Rights stay with you

Uploading a commercial audiobook you do not have a license to use is not allowed.

Example direction prompts

Optional text you can add in the studio to guide the scene, movement and camera.

“Narrator in a quiet library, even pace, minimal movement, eyes on a point just past the camera.”
“Narrator in a reading chair, warm sweater, soft expression, small breaths between sentences.”
“Close narrator portrait, neutral background, calm delivery of a dramatic paragraph.”
“Narrator at a wooden table with a closed book beside them, steady posture, low light.”

Frequently asked questions

Can I upload a published audiobook?

Only if you own the recording or have a license that allows this use. You are responsible for the audio you upload.

Can the video use the original narrator's face?

Only with that person's explicit consent. Otherwise use your own photo or an original fictional narrator. Impersonating the narrator is prohibited.

Will a generated voice match the book narrator?

No. Text-to-voice offers stock synthetic voices only. It does not clone or imitate a real narrator.

Can I visualize the story's scenes?

No. The video is the narrator in the photo you provided, performing the audio. It does not illustrate the book's settings or characters.

How long is one excerpt video?

Each video is 4 to 120 seconds long. Make several excerpt clips if you need more than two minutes.

Make your first video

Plans start at $9.99/month. 1 credit = 1 second of video, and failed generations are refunded.

Open the studio Pricing