For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
DashboardAPI PricingGet an API key
  • Guides
    • Introduction
    • Getting started
    • Use with AI agents
    • Examples
    • Authentication
    • Handling async tasks
    • File uploads
    • File hydration
    • Embedding videos
    • Errors
    • Rate limits
    • Libraries & SDKs
  • REST API Reference
    • Overview
    • Workflows
        • POSTGenerate image
        • POSTGenerate video clip
        • POSTText to speech
        • POSTGenerate sound effect
        • POSTGenerate avatar clip
        • POSTVectorize image
        • POSTRemove background from an image
        • POSTRemove background from a video
        • POSTUpscale an image
        • POSTUpscale a video
        • POSTCancel tool execution
        • GETGet tool execution info
        • GETList files
        • POSTSearch files
        • GETGet file
        • POSTCreate file upload
        • POSTHydrate file
        • POSTArchive file
        • POSTEnable public preview
        • POSTDisable public preview
        • GETList avatar presenters
        • GETList TTS voices
        • GETList webhooks
        • POSTCreate webhook
        • DELDelete webhook
  • Webhook events
    • Overview
    • Changelog
LogoLogo
DashboardAPI PricingGet an API key
REST API ReferenceEndpointsTools

Generate video clip

POST
https://api.videogen.io/v1/tools/generate-video-clip
POST
/v1/tools/generate-video-clip
1import { VideoGenClient } from "@videogen/sdk";
2
3const client = new VideoGenClient({ token: "YOUR_TOKEN" });
4await client.tools.generateVideoClip();
202Accepted
1{
2  "toolExecutionId": "string"
3}

Generate a video clip from a text prompt, optionally guided by reference images or an input video. At least one of prompt, imageFileIds, or videoFileId must be provided.

Was this page helpful?
Previous

Text to speech

Next
Built with

Authentication

AuthorizationBearer

API key from app.videogen.io/developers. The full key is only shown once when you create it.

Request

This endpoint expects an object.
promptstringOptional
Text prompt describing the video to generate. Optional when reference images or a video are provided.
imageFileIdslist of stringsOptional

Optional file ids of reference images (e.g. ["vg_file_..."]). Upload files first via POST /v1/files/upload, then pass the returned ids here. When provided, the model animates or uses these images as guidance.

videoFileIdstringOptional

Optional file id of a source video (e.g. vg_file_...). Upload a file first via POST /v1/files/upload, then pass the returned id here. When provided, the model restyles or transforms the input video.

generateAudiobooleanOptionalDefaults to false
When true, the generated video is guaranteed to include audio. When false, audio may still be present. Defaults to false.
aspectRatioobjectOptional

Aspect ratio for the generated video. Defaults to 16:9 when omitted.

watermarkModeenumOptionalDefaults to AUTO

Controls whether the VideoGen watermark is applied to the output. AUTO applies the watermark unless you have the Production API add-on. VIDEO_GEN always applies it. NONE removes the watermark — requires the Production API add-on; returns an error if you don’t have it.

Allowed values:
numResultsintegerOptional1-100Defaults to 1
Number of output results to generate. Defaults to 1.
isOutputTemporarybooleanOptionalDefaults to false

When true, generated files are temporary. Temporary files are guaranteed to be available for 24 hours, after which they may be archived at any time. Temporary files are not analyzed (no description, transcript, or embedding will be generated), so they will not appear in search results. Defaults to false.

Response

Execution accepted; poll until complete.

toolExecutionIdstring

Execution id (e.g. vg_exec_...).