MODEL ID google:3@0

live

Veo 3

by Google May 20, 2025

Veo 3 is a state of the art generative video model with native audio. It supports text prompts and image prompts, produces short HD clips with dialogue, sound effects and music, and delivers realistic motion with strong prompt adherence for cinematic video generation.

API Options

Platform-level options for task execution and delivery.

taskType string required value: videoInference: Identifier for the type of task being performed

taskUUID string required UUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

outputType string default: URL: Video output type.

Allowed values 1 value

outputFormat string default: MP4

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

`MP4`: Widely supported video container (H.264), recommended for general use.
`WEBM`: Optimized for web delivery.
`MOV`: QuickTime format, common in professional workflows (Apple ecosystem).

Allowed values 3 values

outputQuality integer min: 20 max: 99 default: 95: Compression quality of the output. Higher values preserve quality but increase file size.

webhookURL string URI

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Learn more 1 resource

Webhooks
PLATFORM

deliveryMethod string default: async

Determines how the API delivers task results.

Allowed values 1 value

: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. Required for long-running tasks like video generation.

Learn more 1 resource

Task Polling
PLATFORM

uploadEndpoint string URI

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

Common use cases:

Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
CDN integration: Upload to content delivery networks for immediate distribution.

// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg

The content data will be sent as the request body to the specified URL when generation is complete.

safety object

Content safety checking configuration for video generation.

Properties 2 properties

safety » checkContent checkContent boolean default: false: Enable or disable content safety checking. When enabled, defaults to fast mode.

safety » mode mode string default: none

Safety checking mode for video generation.

Allowed values 3 values

: Disables checking.
: Checks key frames.
: Checks all frames.

ttl integer min: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost boolean default: false: Include task cost in the response.

numberResults integer min: 1 max: 4 default: 1: Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

Inputs

Input resources for the task (images, audio, etc). These must be nested inside the inputs object.

inputs » frameImages frameImages array of strings or objects items: 1

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target frame position.

The frameImages parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. This is different from referenceImages, which provide overall visual guidance without constraining specific timeline positions.

When the frame parameter is omitted, automatic distribution rules apply:

1 image: Used as the first frame.

Examples 2 examples

Shorthand format: When you don't need to specify a frame position, you can pass a plain image input directly.

"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]

Object format: When you need to specify a frame position, use an object with image and frame.

"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]

Format 1: string[]

string: Image input (UUID, URL, Data URI, or Base64).

Format 2: object[] 2 properties

inputs » frameImages » image image string required: Image input (UUID, URL, Data URI, or Base64).

inputs » frameImages » frame frame object

Target frame position for the image. This model only supports the first frame.

Allowed values 2 values

: First frame of the video.
: Frame index 0 (first frame).

Generation Parameters

Core parameters for controlling the generated content.

model string required value: google:3@0

Identifier of the model to use for generation.

Learn more 3 resources

positivePrompt string required min: 2 max: 3000

Text prompt describing elements to include in the generated output.

Learn more 2 resources

width integer paired with height

Width of the generated media in pixels.

Learn more 2 resources

height integer paired with width

Height of the generated media in pixels.

Learn more 2 resources

resolution string: Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.

Allowed values 2 values

duration float value: 8: Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

seed integer min: 0 max: 4294967295: Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

Provider Settings

Parameters specific to this model provider. These must be nested inside the providerSettings.google object.

providerSettings » google » enhancePrompt enhancePrompt boolean value: true: Enable automatic prompt enhancement. Affects reproducibility. Always active for Veo 3.

providerSettings » google » generateAudio generateAudio boolean default: true: Generate video with synchronized audio including ambient sounds and music.

providerSettings » google » resizeMode resizeMode string: Resize mode for the input media.

Allowed values 2 values

taskType string required value: videoInference: Type of the task.

taskUUID string required UUID v4: UUID of the task.

videoUUID string required UUID v4: UUID of the output video.

videoURL string URI: URL of the output video.

videoBase64Data string: Base64-encoded video data.

videoDataURI string URI: Data URI of the output video.

seed integer: The seed used for generation. If none was provided, shows the randomly generated seed.

NSFWContent boolean: Flag indicating if NSFW content was detected.

cost float: Task cost in USD. Present when includeCost is set to true in the request.

Text to Video

Treetop Library Ropeway Arrival

Request

{
  "taskType": "videoInference",
  "taskUUID": "23c298ba-bb4d-4893-9295-7ecedff08b78",
  "model": "google:3@0",
  "positivePrompt": "A sweeping cinematic aerial approach to a vast library built among colossal banyan trees, connected by rope bridges and gliding pulley cabins above a misty green canopy at daybreak. The camera follows a weathered wooden ropeway cabin as it arrives at a branch platform crowded with hanging book satchels, fluttering index cards, carved signs, and stacks of maps under woven awnings. A young archivist in a saffron windbreaker jumps out holding a brass tube of documents while two children roll a ladder on bamboo wheels toward the docking point. Leaves stir, ropes creak, birds burst from the branches, distant waterfalls rumble, and hundreds of paper tags rustle softly in the breeze. Naturalistic motion, detailed textures, expressive faces, cinematic depth of field, subtle lens breathing, richly layered atmosphere. Include synchronized native audio: pulley wheels rattling, wood thumping, parrots calling, soft orchestral strings with hand percussion. One line of clear dialogue from the archivist as she steps onto the platform: \"If the atlas made it before the storm, we still have a chance.\"",
  "width": 1920,
  "height": 1080,
  "duration": 8,
  "seed": 98062,
  "providerSettings": {
    "google": {
      "enhancePrompt": true,
      "generateAudio": true
    }
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "23c298ba-bb4d-4893-9295-7ecedff08b78",
  "videoUUID": "05faed1c-53ee-428a-b53e-e58dba9d92c3",
  "videoURL": "https://vm.runware.ai/video/os/a11d13/ws/5/vi/05faed1c-53ee-428a-b53e-e58dba9d92c3.mp4",
  "seed": 98062,
  "cost": 3.2
}

Image to Video

Volcanic Glassblower Workshop Escape

Request

{
  "taskType": "videoInference",
  "taskUUID": "deeb00c3-f8af-4706-8244-a92920883b09",
  "model": "google:3@0",
  "positivePrompt": "Starting from the provided first-frame image, create an 8-second cinematic sequence in a volcanic glassblowing workshop. The craftswoman stumbles backward as the ground trembles, steadies the blowpipe, and shapes the molten glass while sparks scatter across the floor. A deep rumble grows, fine ash drifts through the cracked archway, hanging tools rattle, and waves of heat distortion ripple through the air. The camera makes a subtle handheld push-in, then tracks sideways as she turns toward the opening. She says with tense urgency, 'If the vent opens now, get the apprentices out.' Layer synchronized audio: roaring furnace, stone creaks, metallic clinks, hiss of molten glass, distant eruption, falling grit, and a low pulse of suspenseful orchestral music. Realistic motion, expressive face, physically plausible firelight, rich textures, dramatic but grounded filmmaking.",
  "width": 1280,
  "height": 720,
  "duration": 8,
  "seed": 75429,
  "providerSettings": {
    "google": {
      "enhancePrompt": true,
      "generateAudio": true,
      "resizeMode": "crop"
    }
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/03ad311f-5ef1-4cdf-ba33-acac03f4723f.jpg",
        "frame": "first"
      }
    ]
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "deeb00c3-f8af-4706-8244-a92920883b09",
  "videoUUID": "633a9b30-58cd-48fd-b0c8-1a84282fd027",
  "videoURL": "https://vm.runware.ai/video/os/a24d12/ws/5/vi/633a9b30-58cd-48fd-b0c8-1a84282fd027.mp4",
  "seed": 75429,
  "cost": 3.2
}

Text to Video

Submerged Cathedral Choir Rehearsal

Request

{
  "taskType": "videoInference",
  "taskUUID": "19ad3801-e2ca-4e8d-8959-a2d68773c1d2",
  "model": "google:3@0",
  "positivePrompt": "Inside a vast flooded cathedral beneath the sea, shafts of green-gold sunlight filter through cracked stained glass and ripple across worn stone columns covered in soft kelp. A small choir of divers in elegant patched diving garments hovers weightlessly between pews, holding waterproof sheet music. As the camera glides slowly forward and arcs upward, the lead singer removes her regulator for a brief trained vocal line into a bubble helmet mic, then smiles as the group answers in layered harmony. Tiny fish weave through the aisles, loose pages drift, candles inside sealed glass lanterns flicker, and a conductor taps a brass tuning fork that resonates through the water. Realistic fluid motion, expressive faces, drifting fabric, cinematic depth, highly detailed environment, natural light caustics, immersive sound design with choral singing, bubbling water, muffled creaks, distant whale-like tones, and subtle orchestral underscoring.",
  "width": 1920,
  "height": 1080,
  "duration": 8,
  "seed": 15197,
  "providerSettings": {
    "google": {
      "enhancePrompt": true,
      "generateAudio": true
    }
  }
}

Response

{
  "taskType": "videoInference",
  "taskUUID": "19ad3801-e2ca-4e8d-8959-a2d68773c1d2",
  "videoUUID": "3fbbe7c4-1453-49ef-bbc0-3c3dab83bc0d",
  "videoURL": "https://vm.runware.ai/video/os/a07d11/ws/5/vi/3fbbe7c4-1453-49ef-bbc0-3c3dab83bc0d.mp4",
  "seed": 15197,
  "cost": 3.2
}

Parameter Dependencies

Dimensions

The following dimension combinations are supported:

Configuration	Dimensions
`720p (16:9)`	`1280x720`
`720p (9:16)`	`720x1280`
`1080p (16:9)`	`1920x1080`
`1080p (9:16)`	`1080x1920`

Pricing

Each generation will cost $0.2/s for 720p, or $0.4/s for 720p with audio.

720p · 8s $1.6

720p · 8s (with audio) $3.2