Veo 3.1
PopularPremiumGoogle · Video · Text → Video
4K video with built-in audio — voices, music, and effects match every scene.
veo-3.1Workflow: veo-t2vOverview
Alongside the unified model APIs, we expose compatibility APIs that take each vendor's original parameters exactly as the vendor defines them — nothing renamed, nothing reshaped on the way through.
That makes them the shortest path onto Picsart if you already work with the vendor directly: the request bodies you've already written keep working as they are. You keep their parameter names and defaults, and you get the vendor's full parameter set rather than the subset that is shared across every model.
The cost is that a request is written for one vendor — switching models later means rewriting it, and results come back in the vendor's own shape. When you'd rather write once and change models freely, use the unified API.
Make a request
Call the workflow with ai.apis.run() in TypeScript, or hit /workflows/{workflow}/execute directly — params is passed through untouched either way.
These endpoints are addressed by workflow name rather than model id: the one in this model's header, since one model runs as one workflow. Authentication is unchanged — your Picsart API key as a bearer token (see Authentication).
import { createClient, ApiRunMode } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY,
apiUrl: 'https://api.green-salad-4efd.toolsminati.workers.dev',
});
// Calls the 'veo-t2v' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('veo-t2v', {
prompt: "A serene mountain lake at golden hour, ultra detailed"
}, {
mode: ApiRunMode.SYNC,
});
console.log(result); // workflow-specific output
console.log(usage?.credits); // credits chargedAsync (submit & poll)
This model can run longer than the sync limit (~20s). In TypeScript, ai.apis.run(…, { mode: ApiRunMode.ASYNC }) polls for you; over HTTP, submit and poll yourself.
import { createClient, ApiRunMode } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY,
apiUrl: 'https://api.green-salad-4efd.toolsminati.workers.dev',
});
// mode: ASYNC submits the job and polls under the hood — you just await.
const { result } = await ai.apis.run('veo-t2v', {
prompt: "A serene mountain lake at golden hour, ultra detailed"
}, {
mode: ApiRunMode.ASYNC,
});
console.log(result);Parameters
10 parameters, sent inside params. These are the vendor's own names, so they line up one-for-one with the vendor's documentation. Required ones must be supplied; the rest fall back to their defaults.
| Parameter | Type | Required | Default | Details |
|---|---|---|---|---|
promptIt is required for text-to-video, and optional if an input image is provided. Provide a clear description of the desired video in english. | string | no | — | — |
imageOptional input image to guide video generation. The video will be based on this image + your prompt. Use for image-to-video generation | object | no | — | — |
└ urlPublic URL of the input image for image-to-video generation. Use either this OR bytesBase64Encoded, not both. Must be accessible from Google Cloud | string | no | — | — |
└ bytesBase64EncodedBase64-encoded image data for image-to-video generation. Use either this OR url, not both. Format: raw base64 string without "data:image/..." prefix | string | no | — | — |
└ mimeTypeMIME type of the input image. Accepted image types: image/jpeg, image/png | string | yes | — | image/pngimage/jpeg |
lastFrameAn image of the first frame of a video to fill the space between. Can be bytesBase64Encoded or url. Supported by models: ["veo-2.0-generate-001","veo-3.1-generate-001","veo-3.1-fast-generate-001","veo-3.1-generate-preview","veo-3.1-fast-generate-preview"] | object | no | — | — |
└ bytesBase64EncodedBase64-encoded last frame data for video continuation. Use either this OR url, not both. Format: raw base64 string without "data:image/..." prefix | string | no | — | — |
└ urlGoogle Cloud Storage URI of the last frame for video continuation. Use either this OR bytesBase64Encoded, not both. Must be accessible from Google Cloud | string | no | — | — |
└ mimeTypeMIME type of the last frame image. Accepted image types: image/jpeg, image/png | string | yes | — | image/pngimage/jpeg |
videoInput video for video extension. Only supports 7 seconds duration. See: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/video/extend-a-veo-video | object | no | — | — |
└ bytesBase64EncodedBase64-encoded video data for video-to-video generation. Use either this OR url, not both. Format: raw base64 string | string | no | — | — |
└ urlGoogle Cloud Storage URI of the input video for video-to-video generation. Use either this OR bytesBase64Encoded, not both. Must be accessible from Google Cloud | string | no | — | — |
└ mimeTypeMIME type of the input video. Accepted video types: video/mp4 | string | yes | — | video/mp4 |
referenceImagesGenerate a video where a specific subject remains consistent with provided reference images, for style or content guidance (optional). Only supported by models: ["veo-2.0-generate-001","veo-3.1-generate-001","veo-3.1-generate-preview"] | VeoReferenceImage[] | no | — | — |
└ imageImage asset for style or content reference. Only supported by models: ["veo-2.0-generate-001","veo-3.1-generate-001","veo-3.1-generate-preview"] | object | yes | — | — |
└ urlPublic URL of the input image for image-to-video generation. Use either this OR bytesBase64Encoded, not both. Must be accessible from Google Cloud | string | no | — | — |
└ bytesBase64EncodedBase64-encoded image data for image-to-video generation. Use either this OR url, not both. Format: raw base64 string without "data:image/..." prefix | string | no | — | — |
└ mimeTypeMIME type of the input image. Accepted image types: image/jpeg, image/png | string | yes | — | image/pngimage/jpeg |
└ referenceTypeType of reference, available values are: "asset" - the reference image provides assets for the generated video, such as: the scene, an object, or a character; or "style" - the reference image provides style information for the generated videos, such as: scene colors, lighting, or texture. Important: "style" references are not supported. They were only available on veo-2.0-generate-001, which is discontinued (2026-06-30); Veo 3.1 supports only "asset" references. | string | yes | — | styleasset |
countNumber of video variations to generate (1-4). Maps to sampleCount in the Veo API. More videos = more options but longer processing time and higher cost | number | no | 1 | 1–4 |
negativePromptWhat to avoid in the video. Helps prevent unwanted content. Example: "blurry, low quality, distorted faces, text overlays" | string | no | — | — |
modelVeo model to use for video generation. Available values are:
- **veo-2.0-generate-001**: Discontinued on 2026-06-30 - mapped to veo-3.1-generate-001
- **veo-3.0-generate-001**: Discontinued on 2026-06-30 - mapped to veo-3.1-generate-001
- **veo-3.0-fast-generate-001**: Discontinued on 2026-06-30 - mapped to veo-3.1-fast-generate-001
- **veo-3.0-generate-preview**: Discontinued on 2026-06-30 - mapped to veo-3.1-generate-001
- **veo-3.1-generate-001**: Default. Latest stable model with enhanced capabilities and audio support (4, 6, 8s)
- **veo-3.1-fast-generate-001**: Latest fast model optimized for speed with audio support (4, 6, 8s)
- **veo-3.1-lite-generate-preview**: Lite model, cheapest option, 720p/1080p only, no 4K/video extension/lastFrame/referenceImages (4, 6, 8s) | string | no | veo-3.1-generate-001 | veo-2.0-generate-001veo-2.0-generate-expveo-3.0-generate-001veo-3.0-fast-generate-001veo-3.0-generate-previewveo-3.1-generate-001veo-3.1-fast-generate-001veo-3.1-generate-previewveo-3.1-fast-generate-previewveo-3.1-lite-generate-preview |
parametersAdvanced generation settings. Fine-tune aspect ratio, duration, creativity levels, and safety settings for precise control over output | object | no | — | — |
└ aspectRatioDefines the aspect ratio of the generated video. Available values: ["16:9","9:16"] | string | no | 16:9 | 16:99:16 |
└ resolutionVideo resolution quality. Optional, Veo 3 models only. The resolution of the generated video has available values: ["720p","1080p","4k"]. Default is 720p for better performance. | string | no | 720p | 720p1080p4k |
└ compressionQualityOptional. Specifies the compression quality of the generated videos. Accepted values: ["optimized","lossless"]. Default is "optimized" | string | no | optimized | optimizedlossless |
└ personGenerationThe safety setting that controls whether people or face generation is allowed. Available values: ["dont_allow","allow_adult","allow_all"] | string | no | allow_all | dont_allowallow_adultallow_all |
└ seedA number to request to make generated videos deterministic. Adding a seed number with your request without changing other parameters will cause the model to produce the same videos, if missing will be randomized. | number | no | — | 0–4294967295 |
└ durationSecondsVideo length in seconds. Defaults to 8s; supported values are 4, 6, 7, 8s (validated against the served Veo 3.1 model). When using referenceImages only 8s is supported. Auto-selected based on model if not specified. | number | no | — | 4–8 |
└ enhancePromptAutomatically improve your prompt using Gemini AI. Recommended for better results unless you need exact prompt control | boolean | no | true | — |
└ generateAudioGenerate video with synchronized audio track (VEO 3.0+ models only: ["veo-3.0-generate-001","veo-3.0-fast-generate-001","veo-3.0-generate-preview","veo-3.1-generate-001","veo-3.1-fast-generate-001","veo-3.1-generate-preview","veo-3.1-fast-generate-preview"]). Defaults to ON; pass false to disable. Enabling audio increases generation time and credit cost. | boolean | no | true | — |
└ resizeModeA string that represents the resize mode to use. | string | no | crop | croppad |
optionsOptions controlling safety checks and drive integration | object | no | — | — |
└ safety_checksSafety check settings | object | no | — | — |
└ enabledWhether to run content moderation. Defaults to true. | boolean | no | — | — |
└ driveSave result to Picsart Drive | object | no | — | — |
└ nameFile name in Picsart Drive | string | yes | — | — |
└ attributesCustom attributes to attach to the file | object | no | — | — |
└ folderTarget folder in Picsart Drive | object | no | — | — |
└ inputs_transformationInput transformation settings | object | no | — | — |
└ downscale_oversized_imagesWhether to downscale oversized input images. Defaults to false. | boolean | no | — | — |
Response
Over HTTP the output arrives inside a status envelope, at response.result. ai.apis.run() unwraps that envelope for you and resolves to { result, usage } instead. Either way the resultitself is the vendor's own shape.
{
"result": [
{
"progress": 0,
"url": "https://cdn.green-salad-4efd.toolsminati.workers.dev/…/result.mp4",
"gcsUri": "…",
"encoding": "…",
"mimeType": "video/mp4",
"driveFile": {}
}
],
"usage": {
"credits": 6
}
}