---
title: Veo 3.1 | Runware Docs
url: https://runware.ai/docs/models/google-veo-3-1
description: Veo 3.1 cinematic AI video with native audio
---
# Veo 3.1

![Veo 3.1](https://assets.runware.ai/covers/google-veo-3-1.jpg)

Veo 3.1 is a cinematic video generation model for developers. It turns text prompts or reference images into high fidelity scenes with richer native audio, better prompt adherence, and granular shot control. Use it for story driven clips with smoother motion and consistent style.

- **Status**: live
- **ID**: `google:3@2`
- Try in Playground
- **Creator**: Google
- **Release Date**: October 15, 2025
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Video, Image to Video, Video to Video, Edit, Extend, Checkpoint, Audio

## Pricing

$0.20 from, per second · ~1m 20s per request

**Rates** (per second)

- 720p / 1080p · without audio: `$0.20`
- 720p / 1080p · with audio: `$0.40`
- 4K · without audio: `$0.40`
- 4K · with audio: `$0.60`

**5 example generations**

- [text-to-video](https://runware.ai/docs/models/google-veo-3-1/examples#example-ultrasonic-vinyl-cleaning-social-reel) · 1080p · 4s · generateAudio: `$1.60` (~1m 30s)
- [first-last-frame](https://runware.ai/docs/models/google-veo-3-1/examples#example-underwater-camera-housing-colorway-reveal) · 720p · 6s · generateAudio: `$2.40` (~1m 20s)
- [first-frame](https://runware.ai/docs/models/google-veo-3-1/examples#example-oyster-grading-machine-demo) · 720p · 6s · generateAudio: `$2.40` (~58s)
- [video-edit](https://runware.ai/docs/models/google-veo-3-1/examples#example-arborist-helmet-colorway-reveal) · 7s: `$2.80` (~1m 16s)
- [reference-to-video](https://runware.ai/docs/models/google-veo-3-1/examples#example-antique-automaton-background-replacement) · 1080p · 8s · generateAudio: `$3.20` (~1m 32s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Provide at least one of `inputs.frameImages` and `inputs.video`, or `width/height`, but not both.

---

Inside `inputs`, `frameImages` cannot be used with `referenceImages`.

---

When `inputs.referenceImages` is provided, `duration` must be `8`.

---

When `inputs.video` is provided, `width/height`, `seed`, and `resolution` cannot be used.

---

When `inputs.video` is provided, `duration` must be `7`.

---

When `providerSettings.google.resizeMode` is provided, `inputs.frameImages` requires at least 1 item.

---

`resolution` cannot be used with `width/height`.

---

When `resolution` is provided, `inputs.frameImages` is required.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `720p (16:9)` | `1280x720` |
| `720p (9:16)` | `720x1280` |
| `1080p (16:9)` | `1920x1080` |
| `1080p (9:16)` | `1080x1920` |
| `4K (16:9)` | `3840x2160` |
| `4K (9:16)` | `2160x3840` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/google-veo-3-1#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/google-veo-3-1#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

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

### [outputType](https://runware.ai/docs/models/google-veo-3-1#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/google-veo-3-1#request-outputformat)

- **Type**: `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**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/google-veo-3-1#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/google-veo-3-1#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses 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](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/google-veo-3-1#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/google-veo-3-1#request-uploadendpoint)

- **Type**: `string`
- **Format**: `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.

```text
// 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](https://runware.ai/docs/models/google-veo-3-1#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/google-veo-3-1#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/google-veo-3-1#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/google-veo-3-1#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/google-veo-3-1#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/google-veo-3-1#request-numberresults)

- **Type**: `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.

### [referenceImages](https://runware.ai/docs/models/google-veo-3-1#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`

List of reference images (UUID, URL, Data URI, or Base64).

### [frameImages](https://runware.ai/docs/models/google-veo-3-1#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`

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 position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. 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.
- **2 images**: First and last frames.

**Examples**:

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

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

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

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

**First and last frames:** With two images, they automatically become the first and last frames of the video sequence. You can mix shorthand and object formats.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "frame": "last"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

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

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/google-veo-3-1#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

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

#### [frame](https://runware.ai/docs/models/google-veo-3-1#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `object`

Target frame position for the image. Supports first and last frame.

**Allowed values**:

- `first` First frame of the video.
- `last` Last frame of the video.
- `0` Frame index 0 (first frame).
- `-1` Frame index -1 (last frame).

### [video](https://runware.ai/docs/models/google-veo-3-1#request-inputs-video)

- **Path**: `inputs.video`
- **Type**: `string`

Video input (UUID or URL). Source video for extension.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/google-veo-3-1#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `google:3@2`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/google-veo-3-1#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `3000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/google-veo-3-1#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.video are not provided
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/google-veo-3-1#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.video are not provided
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [resolution](https://runware.ai/docs/models/google-veo-3-1#request-resolution)

- **Type**: `string`

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

**Allowed values**: `720p` `1080p` `4K`

### [duration](https://runware.ai/docs/models/google-veo-3-1#request-duration)

- **Type**: `integer`
- **Default**: `4`

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).

**Allowed values**: `4` `6` `7` `8`

### [seed](https://runware.ai/docs/models/google-veo-3-1#request-seed)

- **Type**: `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.

### [enhancePrompt](https://runware.ai/docs/models/google-veo-3-1#request-providersettings-google-enhanceprompt)

- **Path**: `providerSettings.google.enhancePrompt`
- **Type**: `boolean`
- **Value**: `true`

Enable automatic prompt enhancement. Affects reproducibility. Always active for Veo 3.1.

### [generateAudio](https://runware.ai/docs/models/google-veo-3-1#request-providersettings-google-generateaudio)

- **Path**: `providerSettings.google.generateAudio`
- **Type**: `boolean`
- **Default**: `true`

Generate video with synchronized audio including ambient sounds and music.

### [resizeMode](https://runware.ai/docs/models/google-veo-3-1#request-providersettings-google-resizemode)

- **Path**: `providerSettings.google.resizeMode`
- **Type**: `string`

Resize mode for the input media.

**Allowed values**: `crop` `pad`

## Response Parameters

### [taskType](https://runware.ai/docs/models/google-veo-3-1#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/google-veo-3-1#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/google-veo-3-1#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/google-veo-3-1#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/google-veo-3-1#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/google-veo-3-1#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [seed](https://runware.ai/docs/models/google-veo-3-1#response-seed)

- **Type**: `integer`

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

### [NSFWContent](https://runware.ai/docs/models/google-veo-3-1#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/google-veo-3-1#response-cost)

- **Type**: `float`

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

## Examples

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/google-veo-3-1/563ad614-32e4-4aec-8a6a-0f3c369b1434.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "72d3cad0-f9c2-4040-bbc1-754406323614",
  "model": "google:3@2",
  "positivePrompt": "Create a polished four-second landscape social video ad for a professional ultrasonic vinyl-record cleaning service. One continuous extreme-macro shot inside a refined record-cleaning studio with a retro 1970s hi-fi aesthetic: brushed aluminum, smoked acrylic, warm cream highlights, deep burgundy shadows. A dusty translucent red vinyl record rotates vertically through a narrow ultrasonic bath. Begin tight on lint and fingerprints clinging to the illuminated grooves as the camera tracks smoothly alongside the spinning surface. At one second, the record enters the liquid; perfectly synchronized concentric ripples shimmer across the bath, microscopic dust blooms away from the grooves, and a slim metal cleaning arm glides into frame. Follow the rotation as the vinyl emerges visibly spotless, glossy, and jewel-like, catching a sharp ribbon of warm light. End on the pristine grooves sweeping past the lens with confident commercial polish. Shallow depth of field, tactile photorealism, precise mechanical movement, restrained premium color grade, no people, no text, no logos. Synchronized sound: faint dusty record crackle at the opening, a crisp mechanical click as the cleaner engages, soft ultrasonic hum and liquid fizz during cleaning, then the crackle resolves into one rich, clean soul-jazz chord on the spotless reveal.",
  "width": 1920,
  "height": 1080,
  "duration": 4,
  "providerSettings": {
    "google": {
      "generateAudio": true
    }
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/google-veo-3-1/ddd4b8e3-acad-4112-8ba4-13607431504e.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "2e56a6d2-f9a8-4a48-8262-1d259110acb5",
  "model": "google:3@2",
  "positivePrompt": "Create a polished single-shot product demonstration for an aquaculture equipment supplier. Begin from the provided first frame exactly, preserving the worker, oyster basket, stainless-steel grader, seafoam rollers, coral collection crates, lighting, spatial layout, and three-quarter camera angle. The worker smoothly tips the basket forward and wet oysters tumble into the feed hopper. The motor starts; rollers rotate steadily and carry the oysters toward camera-right. Small oysters drop first into the nearest crate, medium oysters fall into the center crate, and the largest continue to the final crate, clearly demonstrating progressive size grading. Keep the sorting physically accurate: shells roll and jostle with believable weight, occasional seawater droplets catch the light, and each oyster falls only when it reaches the appropriate roller gap. Use a subtle slow dolly forward while keeping the entire sorting path and all three crates visible. Bright, practical coastal workshop atmosphere; cool silver and seafoam palette with restrained coral accents; premium industrial documentary realism rather than an advertisement. End with several oysters still moving through the rollers and visibly separated batches accumulating below. Native synchronized audio: gentle electric motor hum, rhythmic clatter of shells on steel rollers, shells landing in plastic crates, faint gulls and harbor ambience through the open bay. No speech, music, text, logos, graphics, cuts, time-lapse, slow motion, extra limbs, or camera shake.",
  "resolution": "720p",
  "duration": 6,
  "providerSettings": {
    "google": {
      "resizeMode": "crop",
      "generateAudio": true
    }
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/c9155a93-c15d-4ecb-badf-b7ffdd435529.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

### first-last-frame (first-last-frame)

[Watch video](https://assets.runware.ai/examples/google-veo-3-1/26124164-b63b-4a39-984d-1c0f012463d1.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "1a737e8e-6035-48da-9dd4-9da95455e6e5",
  "model": "google:3@2",
  "positivePrompt": "Create a polished six-second colorway reveal for a professional underwater cinema-camera housing. Begin exactly from the supplied first frame: the safety-orange housing centered on its volcanic-stone slab inside the dark navy test tank. Preserve the product's precise identity, proportions and components throughout, including the glass dome, handles, controls, fasteners and monitor mount.\n\nThe camera makes one smooth, slow arc from the front-left view toward the front-right view, traveling consistently to the right with subtle parallax. At the same time, a controlled curtain of aerated water enters from the left and sweeps across the housing toward the right. As this opaque ribbon of bubbles crosses each exterior aluminum panel, use it as a seamless practical wipe: the panel emerges behind it in the new matte kelp-green colorway. The recolor must progress continuously from left to right rather than flashing or morphing. Only the orange aluminum shell changes color; the black handles and controls, steel hardware, transparent dome glass, stone slab and environment remain unchanged. Keep the housing rigid and mechanically accurate with no warping, replacement parts or extra controls.\n\nAs the bubble curtain clears, reduce the turbulence to a few rising microbubbles and let cyan caustic highlights travel naturally over the new green finish. Complete the camera arc and settle exactly into the supplied last frame, holding the finished kelp-green product clearly for the final moment. Maintain premium commercial-product sharpness, deep navy negative space, restrained cyan illumination and realistic underwater refraction. No people, hands, logos, captions or on-screen text.\n\nSynchronized native audio only: a soft underwater rush moving left to right with the bubble curtain, delicate bubble crackle, a subdued waterproof camera-rig motor hum during the arc, then calm filtered tank ambience at the finish. No speech and no music.",
  "resolution": "720p",
  "duration": 6,
  "providerSettings": {
    "google": {
      "generateAudio": true
    }
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/daa8b042-aff3-47c1-b5e5-e041a526b815.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/e83b9d23-45fb-46a2-87aa-ed3b1ff854ed.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

### reference-to-video (reference-to-video)

[Watch video](https://assets.runware.ai/examples/google-veo-3-1/30c65ecc-5380-4dc9-bd34-a4967a765900.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "9a47544c-5b21-4c09-bcca-bcda87ecb082",
  "model": "google:3@2",
  "positivePrompt": "Create a finished 8-second vertical auction-house showcase using all three reference images only as identity and design references for the same antique singing-bird automaton; none of the references is a first frame. Preserve the exact kingfisher proportions, iridescent teal feathers, rust-orange breast, black beak and glass eyes, gilt branch, winding key, engraved fern motifs, dark green enamel panels, porcelain water lily, age patina, and mechanical construction throughout.\n\nReplace the plain studio surroundings completely with a refined Belle Époque conservatory at early morning. The automaton stands naturally on a slim veined-cream-marble pedestal among out-of-focus palms, wrought-iron window frames, pale condensation on glass panes, and restrained botanical shadows. Warm low sunlight passes through the foliage, creating soft moving highlights across the brass and enamel. Use an elegant palette of verdigris, cream, aged gold, dusty coral, and fresh leaf green. The result should feel like a premium provenance-film insert for a specialist mechanical-arts auction, not fantasy.\n\nOne continuous cinematic shot composed for 9:16. Begin with a close full view of the automaton centered in the lower two-thirds, then perform a very slow clockwise camera arc and subtle push-in. After two seconds, the mechanism activates: the bird turns its head once, opens its beak, gently flutters its wings, and flicks its tail while remaining securely attached to the branch. Keep motion precise, delicate, and mechanically plausible. A faint breeze moves only the conservatory leaves and shifting sunlight in the replacement background. Maintain clean, believable contact shadows on the marble, accurate reflections, stable object geometry, and crisp separation around every feather and winding key. Shallow depth of field, polished 35mm commercial cinematography, realistic materials, no people, no lettering, no logos, no borders. Synchronized audio: quiet glasshouse room tone, distant morning birds, tiny clockwork clicks and whirs, followed by two delicate mechanical bird chirps.",
  "width": 1080,
  "height": 1920,
  "duration": 8,
  "providerSettings": {
    "google": {
      "generateAudio": true
    }
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/7b2556e1-31aa-4832-8281-cb43dd19fc39.jpg",
      "https://assets.runware.ai/assets/inputs/5da88154-aa2c-4ccd-b71b-06ac3092115d.jpg",
      "https://assets.runware.ai/assets/inputs/5e73dfd0-ed7c-44f9-9df0-a17a56f002f9.jpg"
    ]
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/google-veo-3-1/7511c633-0382-4463-8d0d-562506826630.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "148bd2ca-3405-4dae-aa78-a2c1e936ceaf",
  "model": "google:3@2",
  "positivePrompt": "Create a seamless seven-second continuation from the source clip. Preserve the exact arborist helmet geometry, proportions, materials, turntable speed, clockwise rotation, camera height, slow rightward dolly, warm-gray cyclorama, lighting direction, exposure, and temporal rhythm. Continue the narrow vertical band of light sweeping smoothly from left to right across the helmet. As the band crosses the rigid burnt-orange outer shell, reveal the production-ready alternate colorway behind it: a refined muted eucalyptus green with the same satin polymer finish. Recolor only the rigid outer shell. Keep the matte-black earmuffs, suspension hardware, straps, vents, raised stainless-steel mesh visor, shadows, highlights, and reflections unchanged. The transition must be crisp and physically coherent, with no morphing, added parts, logos, lettering, hands, or camera cuts. After the sweep completes, continue the measured rotation and dolly long enough to present the fully green helmet in a premium three-quarter hero angle, ending with stable motion that could continue into another shot. Native audio: quiet turntable motor, subtle studio room tone, and one soft precision click as the new colorway is fully revealed; no speech and no music.",
  "duration": 7,
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/c5b7c799-6c8b-4a83-bfb5-545ee1c5c22d.mp4"
  }
}
```