---
title: Seedance 2.0 | Runware Docs
url: https://runware.ai/docs/models/bytedance-seedance-2-0
description: Unified multimodal audio-video generation with multi-reference input and physics-aware motion
---
# Seedance 2.0

![Seedance 2.0](https://assets.runware.ai/covers/bytedance-seedance-2-0.jpg)

Seedance 2.0 is a unified multimodal audio-video generation model from ByteDance that accepts text, image, audio, and video inputs in combination, supporting up to 9 images, 3 video clips, and 3 audio clips as reference. It generates multi-shot videos up to 15 seconds with dual-channel synchronized audio including dialogue, ambient sound, and effects. It features physics-aware motion, improved controllability for video extension and editing, and strong instruction following for complex scene composition.

- **Status**: live
- **ID**: `bytedance:seedance@2.0`
- Try in Playground
- **Creator**: ByteDance
- **Release Date**: April 3, 2026
- **Capabilities**: Text to Video, Image to Video, Video to Video, Audio to Video, Edit, Extend, Checkpoint, Audio

## Pricing

$0.07 from, per second · ~2m 56s per request

**Rates** (per second)

- 480p: `$0.07`
- 720p: `$0.16`
- 1080p: `$0.40`
- 4K: `$0.856`
- 720p · video to video: `$0.219`
- 1080p · video to video: `$0.537`
- 4K · video to video: `$1.16`

**4 example generations**

- [text-to-video](https://runware.ai/docs/models/bytedance-seedance-2-0/examples#example-tattoo-machine-colorway-reveal-film) · 720p · 6s · audio: `$0.953` (~2m 3s)
- [first-last-frame](https://runware.ai/docs/models/bytedance-seedance-2-0/examples#example-secretary-bird-habitat-composite-film) · 720p · 8s: `$1.27` (~2m 17s)
- [first-frame](https://runware.ai/docs/models/bytedance-seedance-2-0/examples#example-art-forgery-drama-title-sequence) · 1080p · 5s · audio: `$2.03` (~3m 34s)
- [reference-to-video](https://runware.ai/docs/models/bytedance-seedance-2-0/examples#example-atp-sanitation-meter-demo) · 1080p · 10s · audio: `$4.14` (~5m 25s)

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

## Compatibility & Validation

Either provide `inputs.frameImages`, `inputs.referenceImages`, or `inputs.referenceVideos`, or specify `width/height`.

---

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

---

When `inputs.referenceAudios` is provided, `inputs.frameImages`, `inputs.referenceImages`, or `inputs.referenceVideos` is required.

---

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

---

When `resolution` is provided, `inputs.frameImages`, `inputs.referenceImages`, or `inputs.referenceVideos` is required.

---

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `480p (16:9)` | `864x496` |
| `480p (4:3)` | `752x560` |
| `480p (1:1)` | `640x640` |
| `480p (3:4)` | `560x752` |
| `480p (9:16)` | `496x864` |
| `480p (21:9)` | `992x432` |
| `720p (16:9)` | `1280x720` |
| `720p (4:3)` | `1112x834` |
| `720p (1:1)` | `960x960` |
| `720p (3:4)` | `834x1112` |
| `720p (9:16)` | `720x1280` |
| `720p (21:9)` | `1470x630` |
| `1080p (16:9)` | `1920x1080` |
| `1080p (4:3)` | `1664x1248` |
| `1080p (1:1)` | `1440x1440` |
| `1080p (3:4)` | `1248x1664` |
| `1080p (9:16)` | `1080x1920` |
| `1080p (21:9)` | `2206x946` |
| `4K (16:9)` | `3840x2160` |
| `4K (4:3)` | `3326x2494` |
| `4K (1:1)` | `2880x2880` |
| `4K (3:4)` | `2496x3328` |
| `4K (9:16)` | `2160x3840` |
| `4K (21:9)` | `4398x1886` |

## Notes

Seedance 2.0 supports multiple generation modes:

- **Text-to-Video:** Provide a prompt with `width`/`height`.
- **Image-to-Video:** Provide frame images via `inputs.frameImages` (up to 2, first/last). Dimensions are optional and inherited from the image if not specified.
- **Reference-Guided:** Provide reference images (`inputs.referenceImages`, up to 9) and/or reference videos (`inputs.referenceVideos`, up to 3) for visual guidance.
- **Audio-Guided:** Provide reference audios (`inputs.referenceAudios`, up to 3) to guide audio generation. Requires at least one reference image or reference video.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/bytedance-seedance-2-0#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/bytedance-seedance-2-0#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/bytedance-seedance-2-0#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/bytedance-seedance-2-0#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/bytedance-seedance-2-0#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/bytedance-seedance-2-0#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/bytedance-seedance-2-0#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/bytedance-seedance-2-0#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/bytedance-seedance-2-0#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/bytedance-seedance-2-0#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/bytedance-seedance-2-0#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/bytedance-seedance-2-0#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/bytedance-seedance-2-0#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/bytedance-seedance-2-0#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/bytedance-seedance-2-0#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `9`

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

### [frameImages](https://runware.ai/docs/models/bytedance-seedance-2-0#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/bytedance-seedance-2-0#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/bytedance-seedance-2-0#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).

### [referenceVideos](https://runware.ai/docs/models/bytedance-seedance-2-0#request-inputs-referencevideos)

- **Path**: `inputs.referenceVideos`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`
- **Size (each)**: `300 px to 6000 px`
- **Aspect ratio (each)**: `1:2.5 to 2.5:1`

List of reference videos (UUID or URL).

### [referenceAudios](https://runware.ai/docs/models/bytedance-seedance-2-0#request-inputs-referenceaudios)

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

List of reference audios (UUID or URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/bytedance-seedance-2-0#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `bytedance:seedance@2.0`

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/bytedance-seedance-2-0#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `10000`

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/bytedance-seedance-2-0#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.referenceImages and inputs.referenceVideos 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/bytedance-seedance-2-0#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.referenceImages and inputs.referenceVideos 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/bytedance-seedance-2-0#request-resolution)

- **Type**: `string`
- **Default**: `720p`

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

**Allowed values**: `480p` `720p` `1080p` `4k`

### [duration](https://runware.ai/docs/models/bytedance-seedance-2-0#request-duration)

- **Type**: `integer`
- **Min**: `4`
- **Max**: `15`
- **Default**: `5`

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).

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [audio](https://runware.ai/docs/models/bytedance-seedance-2-0#request-settings-audio)

- **Path**: `settings.audio`
- **Type**: `boolean`
- **Default**: `true`

Generate synchronized audio.

## Response Parameters

### [taskType](https://runware.ai/docs/models/bytedance-seedance-2-0#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/bytedance-seedance-2-0#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/bytedance-seedance-2-0#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/bytedance-seedance-2-0#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/bytedance-seedance-2-0#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/bytedance-seedance-2-0#response-videodatauri)

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

Data URI of the output video.

### [NSFWContent](https://runware.ai/docs/models/bytedance-seedance-2-0#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/bytedance-seedance-2-0#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/bytedance-seedance-2-0/d21e564a-9c0d-4821-a4ec-f15cae6b7e4f.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "b7cbee6c-27b0-44a5-90d3-a67f36cd9755",
  "model": "bytedance:seedance@2.0",
  "positivePrompt": "Create a polished six-second landscape product colorway reveal for a premium cordless rotary tattoo machine. Single continuous macro shot in a pristine, contemporary tattoo studio: the machine stands upright on a small brushed stainless-steel pedestal, centered against a softly blurred background of white ceramic tile and frosted glass. Begin with the product finished in matte graphite-black anodized aluminum. The camera performs a slow, precise 30-degree clockwise orbit with a subtle push-in, preserving the machine’s exact silhouette, proportions, grip texture, seams, buttons, needle cartridge, and metallic details throughout. At two seconds, a crisp band of new finish travels smoothly from the base to the top, physically recoloring only the graphite housing into rich sea-glass green anodized aluminum; this is a genuine material color transition, not colored lighting. Fine machined highlights and realistic reflections update naturally as the finish changes. The black rubber grip, polished steel hardware, and transparent cartridge remain unchanged. Hold on the completed sea-glass green colorway for the final two seconds as the machine makes one restrained quarter-turn on the pedestal. Clinical high-key lighting with a narrow white rim light, realistic contact shadow, premium industrial-design cinematography, shallow depth of field, no hands, no labels, no logo, no text, no extra products, and no alteration to the product geometry. Synchronized sound: quiet sterile room tone, a soft precision-machined click as the recolor begins, a delicate rising metallic shimmer following the moving color band, then a muted turntable stop at the final hero angle; no speech and no music.",
  "width": 1280,
  "height": 720,
  "duration": 6,
  "settings": {
    "audio": true
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/bytedance-seedance-2-0/aa07beb8-537e-4959-bad3-4c646025d4eb.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "2f90d3e7-3499-40a5-a56d-32a8f4222b1f",
  "model": "bytedance:seedance@2.0",
  "positivePrompt": "Continue naturally from the supplied first frame as one uninterrupted cinematic macro shot. The conservator steadily rolls the cotton swab from left to right across the cracked painting with precise, believable hand pressure. A thin wake of cloudy amber varnish loosens behind it, exposing a vivid vermilion underpainting and subtle oxidized-green details; tiny varnish flakes flex, catch the cyan task light, and settle naturally. The camera makes a slow, controlled pullback while maintaining razor-sharp focus on the advancing cleaned edge. As more of the hidden layer is uncovered, painted uppercase Roman capitals are revealed within the artwork itself, forming the exact title “PENTIMENTO” across the center of frame. The title must look physically embedded in the concealed paint layer, elegant and historically plausible, not digitally overlaid. End on a balanced full title composition with the gloved hand paused at frame right, drifting dust visible in the light, and the surrounding portrait still mostly lost in warm darkness. Old-Master chiaroscuro, amber brown, deep burgundy, oxidized green, restrained surgical cyan highlights, tactile photorealistic conservation detail, prestige psychological-drama mood. No cuts, no additional words, no subtitles, no logos, no interface elements. Synchronized sound: intimate cotton drag over varnish, faint brittle crackle, low museum ventilation, and a single uneasy viola harmonic that resolves as the title becomes fully visible.",
  "resolution": "1080p",
  "duration": 5,
  "settings": {
    "audio": true
  },
  "inputs": {
    "frameImages": [
      "https://assets.runware.ai/assets/inputs/d686c3c1-bdd1-441f-9030-c444e78da4a4.jpg"
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/bytedance-seedance-2-0/16b3c26f-f336-4e12-94d8-beab7ce47a13.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "7b0a9ee6-8c7a-4daa-bacb-6297b47f2a14",
  "model": "bytedance:seedance@2.0",
  "positivePrompt": "Create a polished wildlife sanctuary campaign shot demonstrating an invisible background replacement. Use the secretary bird in both endpoint images as the retained foreground subject and preserve its exact identity throughout: silver-gray body, black wing feathers, swept crest with one bent feather, orange-red facial skin, long pink legs and natural anatomy. The original controlled-studio surroundings have been completely removed and replaced for the entire shot by the same photorealistic semi-arid African reserve shown in the endpoint images. Maintain exceptionally clean feather-edge extraction, believable warm sunrise rim light, soft ochre bounce light, grounded foot contact and physically accurate moving shadows on the termite mound.\n\nOne continuous shot with no cuts: the bird calmly takes two deliberate steps from the left side of the mound toward center-right, its head and crest responding subtly to each footfall. Dry grass bends in a light breeze while distant acacias and hazed hills show restrained, coherent parallax from an almost imperceptible slow camera slide to the right. Preserve the endpoint composition, eye-level 50mm perspective and shallow natural depth of field. Keep the replacement landscape spatially stable with no warping, flicker, duplicated limbs or changes to the bird's markings. Natural documentary realism, refined conservation-film color grade, muted straw gold, ochre and dusty sage palette. Synchronized location sound: quiet grassland wind, soft grass rustle, two muted footfalls on dry earth and sparse distant bird calls; no narration and no music.",
  "resolution": "720p",
  "duration": 8,
  "settings": {
    "audio": false
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/6c483fd0-ca60-4022-bf03-568b5578d849.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/cad51ea0-1a41-453c-94ed-0adc3f75b1b3.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/bytedance-seedance-2-0/82624207-6b51-48fb-94ce-4d005a0fad8c.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "b2bdb9eb-4bd5-43fd-86b9-0287a2a944ab",
  "model": "bytedance:seedance@2.0",
  "positivePrompt": "Create a polished portrait product demonstration for a food-safety equipment supplier. Use the reference image as the authoritative appearance guide for the ATP luminometer: preserve its matte deep-green rounded body, recessed display, circular button, silver sample chamber, proportions, materials, and white swab vial consistently in every shot. Use the reference video only to guide the precise blue-gloved hand choreography, macro documentary cinematography, restrained match-cut editing, and cool stainless-steel quality-control-room art direction; do not copy the generic device appearance from that video. Use the reference audio as the exact narration and timing spine, synchronizing the demonstrated action to each spoken phrase while retaining the clear female voice.\n\nOpen on a pristine stainless-steel preparation table in a working food-production facility, framed vertically with generous depth above and below the hands. On “Swab the surface,” show an extreme close-up of a blue-gloved technician drawing the white swab across the steel in one smooth zigzag pass, with visible realistic friction and a soft swab rasp. Match cut on “seal the test” to the swab entering its vial and the cap closing with a tactile snap. On “insert the vial,” show the vial sliding cleanly into the luminometer’s silver sample chamber and locking with a precise click. Finish on a controlled three-quarter hero close-up of the device in the technician’s hand as its indicator gives a calm green confirmation glow, followed by a subtle electronic chime; keep the display abstract and legible as a success state without requiring readable numbers or words.\n\nLighting is clean, cool, and technical rather than medical: brushed steel, pale gray walls, deep-green product shell, blue gloves, and one fresh lime-green confirmation accent. Realistic hand anatomy, physically accurate swab and cap interaction, stable product geometry, convincing reflections, premium industrial product photography, shallow depth of field, concise instructional clarity. Add low food-facility room tone, soft ventilation, swab friction, cap snap, insertion click, and confirmation chime in the narration gaps. No logos, captions, floating labels, split screens, website or app interface, extra devices, contamination imagery, dramatic advertising spectacle, or unreadable on-screen text.",
  "width": 1080,
  "height": 1920,
  "duration": 10,
  "settings": {
    "audio": true
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/e192f7ab-8717-4cf4-ba76-d2c0b1fbbb27.jpg"
    ],
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/ee417114-3bff-46bc-b522-8de9d1d01bad.mp4"
    ],
    "referenceAudios": [
      "https://assets.runware.ai/assets/inputs/5a8423d4-0f17-4caa-9ebe-10f78cc148da.mp3"
    ]
  }
}
```