How to Create AI Voice Over Videos using an API

Description and use

Generate voice‑over videos with ElevenLabs and Creatomate: a single API call creates the voice, subtitles, and final video.

Creating professional voice‑over videos with realistic AI speech was time‑consuming and required multiple tools.

A fully automated pipeline that turns text and image URLs into a polished voice‑over video with subtitles, all via a single API call.

1. Sign up for ElevenLabs and obtain an API key and voice ID.
2. Log in to Creatomate, enable ElevenLabs integration in Project Settings, and paste the API key.
3. Create or select a voice‑over template in Creatomate (e.g., Short‑Form Voice Over).
4. In the template editor, set the Audio property of each Voiceover element to the chosen ElevenLabs voice (or custom voice ID).
5. Ensure Subtitle elements source from the corresponding Voiceover elements.
6. Prepare image URLs and voice‑over text for each scene.
7. Construct a POST request to https://api.creatomate.com/v2/renders with API key, template_id, and modifications mapping image and voice‑over placeholders to actual content.
8. Send the request via cURL, Postman, or a custom script.
9. Receive a render ID and status; poll or wait for completion to retrieve the final video URL.

All voiceovers and subtitles will be generated through the API request we’ll talk about later.

The API is accessible using a simple REST interface. So you don’t have to install any software or libraries; just send a request over HTTP.