Video Replication

Video Replication uses a source video, reference images of a new character, and your instructions to generate a new version. You can optionally provide a voice sample for that character.

Prepare your inputs

Input	Requirement
Source video	MP4 or MOV, at most 45 seconds.
Character references	One to three JPG, PNG, or WebP images of the same character. Use clear, consistent views.
Instructions	Describe the character change, desired treatment, and the pacing, framing, or actions to retain.
Voice sample	Optional MP3 or WAV containing a voice you are authorized to use. Omitting it does not request a cloned voice.

Provide HTTPS media URLs that remain accessible during processing. Obtain permission for the source footage, character likeness, and any supplied voice.

Describe the new version

For example: “Replace the presenter with the character in the reference images. Keep the kitchen setting, shot sequence, and pacing. Use the supplied voice sample for the new presenter.” A request generates one version for one character. To make several character variants, send separate requests with distinct idempotency keys. For a product placement in the original scene, use Video Editing.

Call the agent

Use POST /v3/agents/video-replication with a Darwin API key carrying tools:execute and an Idempotency-Key. See the API reference for inputs, output, and error codes. Review character consistency, motion, lip synchronization, audio, and rights before distributing the result. The maximum output length is 45 seconds.

Get Started

Navigator

Publish

Agents

Interfaces

Admin

Video Replication

Prepare your inputs

Describe the new version

Call the agent

​Prepare your inputs

​Describe the new version

​Call the agent

Prepare your inputs

Describe the new version

Call the agent