Sign in
Tools

Generate video clip

Generate a single short video clip (up to 30 seconds) from a text prompt, optionally guided by an opening-frame still, reference images, videos, and audio. At least one of prompt, startFrameFileId, imageFileIds, videoFileIds, audioFileIds, or spokenDialogue must be provided. VideoGen automatically routes each request to the most effective state-of-the-art video model for your inputs and settings, so you don't pick a model. This endpoint returns one standalone clip. For longer, higher-quality, professionally edited videos with narration, captions, music, and multiple scenes, use a video workflow such as Script to video (POST /v1/workflows/script-to-video) instead.

post/v1/tools/generate-video-clip

Request body

promptstring

Text prompt describing the video to generate. Optional when reference media, startFrameFileId, or spokenDialogue is provided. Describe the video in plain language; any reference media you provide is incorporated automatically.

startFrameFileIdstring

Optional file id of the opening-frame still (e.g. vg_file_...). Upload first via POST /v1/files/upload. When set, this image is the first frame of the clip. If the same id also appears in imageFileIds, it is used only as the opening frame and dropped from the reference list. Can be the only input (prompt optional).

imageFileIdsstring[]

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 images are used as visual guidance. To animate a specific still as the opening frame, pass it as startFrameFileId instead.

videoFileIdsstring[]

Optional file ids of reference videos (e.g. ["vg_file_..."]). Upload files first via POST /v1/files/upload, then pass the returned ids here. They are used as motion or style guidance for the generated video.

audioFileIdsstring[]

Optional file ids of reference audio clips (e.g. ["vg_file_..."]) used for lip-sync from that recording. Upload files first via POST /v1/files/upload, then pass the returned ids here. To have the model speak a line it generates itself, pass spokenDialogue instead (or in addition).

spokenDialoguestring

Optional exact line the subject should speak as native, lip-synced speech in the generated clip. The model synthesizes the voice from this text. Can be the only input. Combine with a visual prompt, startFrameFileId, or reference media. Combine with audioFileIds when you also have a reference recording.

voiceDescriptionstring

Optional natural-language description of the voice that speaks spokenDialogue (for example, a warm, confident young man's voice). Used when spokenDialogue is set. When omitted, a clear natural voice is used.

generateAudioboolean

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

suppressBackgroundMusicboolean

When true, the generated clip will not include a musical soundtrack. Spoken dialogue and environmental sound are still allowed. Use this when you will add background music separately (for example at the project level). Defaults to false.

durationSecondsinteger nullable

Desired clip length in seconds. A whole number between 1 and 30. Defaults to 6 when omitted. The generated clip is clamped to the selected quality's supported range. This endpoint produces a single short clip. For longer, multi-scene, professionally edited videos, use a video workflow such as POST /v1/workflows/script-to-video.

quality'LOW' | 'STANDARD' | 'HIGH' | 'MAX'

AI generation quality tier, shared across every generative feature (image, video, text, and so on). LOW is fastest and cheapest, STANDARD balances quality and cost, HIGH is higher quality, and MAX is the highest quality.

When a request omits the quality field, VideoGen falls back to your account's Default AI quality for that feature, which you can change at Account settings. Not every feature supports every tier; unsupported tiers are rejected with an error (see each field's description).

watermarkMode'NONE' | 'VIDEO_GEN' | 'AUTO'

Controls whether the VideoGen watermark is applied to the output. AUTO applies the watermark unless you have a Pro plan. VIDEO_GEN always applies it. NONE removes the watermark (requires Pro; returns an error if you don't have it).

numResultsinteger

Number of output results to generate. Defaults to 1.

isOutputTemporaryboolean

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.

hideFromUiboolean

When true, generated files are hidden from the VideoGen Media page by default. They remain accessible through the API. Defaults to false.

Example request

{
  "prompt": "A golden retriever running through a sunlit meadow in slow motion, cinematic"
}

Response

Execution accepted; poll until complete.

toolExecutionIdstring required

Execution id (e.g. vg_tool_...).

Changes

No recorded changes to this endpoint across all 1 revision of this API.