Skip to main content

Overview

Article to Video reads a web page, turns its text into a narration split into scenes, reads it with a voice and puts a visual under each scene. Use it to repurpose your blog, summarise industry news or turn documentation pages into short explainers. Every request needs sourceUrl (a public https:// page) and voiceId (from GET /v1/voice/list). summaryType is summarize (default), summarize_long or key_as_is; with the first two targetDuration sets the length (default 30 seconds, 10 to 600). mediaType defaults to ai-images.
The create call answers in a few seconds with the projectId and status processing. The article is read and summarised after that, then the video is generated and rendered. If the page cannot be read or summarised, the project becomes failed (the reason is in message), the credits come back and your webhook gets the failure.

A short summary with AI images

customPrompt steers the summary (only with summarize).

The whole article, with AI video clips

key_as_is keeps the article’s content and order; the video is as long as the text needs and targetDuration is ignored.

Over your own footage or gameplay

For your own footage send mediaType: "media" and the library IDs in media.

Getting the video

Wait for the webhook or poll GET /v1/project/{projectId} until video.status is COMPLETED, then download video.url.
Send an Idempotency-Key header to retry safely: if a request times out or answers 5xx, sending it again with the same key and body returns the first answer instead of creating (and charging) the project twice.
Teams in bring-your-own-keys mode are not charged credits, but need OpenRouter, Firecrawl (to read the page) and ElevenLabs (the narration) in Settings → AI keys, and Gemini for the Omni Flash model. A missing key answers 402 missing_credentials with the list in missingProviders, before anything is created.
See the Article to Video reference for every field and error.