---
title: P-Video-2 | Runware Docs
url: https://runware.ai/docs/models/prunaai-p-video-2
description: Quality-focused multimodal video generation with native audio, stronger lip sync, and consistent subjects
---
# P-Video-2

![P-Video-2](https://assets.runware.ai/covers/prunaai-p-video-2.jpg)

P-Video-2 is Pruna AI's quality-focused successor to P-Video, creating clips from text, images, or audio-conditioned inputs through one model. It produces sharper close-ups and foreground subjects, stronger identity and input-image consistency, improved lip synchronization for natively generated speech, and clearer on-screen text while generating dialogue, music, and sound effects with the video. It supports optional first-and-last-frame guidance, draft iteration, durations up to 20 seconds, 720p or 1080p output, and 24 or 48 FPS.

- **Status**: live
- **ID**: `prunaai:p-video@2`
- Try in Playground
- **Creator**: Pruna AI
- **Release Date**: September 10, 2026
- **Capabilities**: Text to Video, Image to Video, Audio to Video, Checkpoint

## Pricing

$0.015 from, per second · ~1m 9s per request

**Rates** (per second)

- 720p · Standard: `$0.025`
- 720p · Draft: `$0.015`
- 1080p · Standard: `$0.05`
- 1080p · Draft: `$0.03`

**6 example generations**

- [draft-preview](https://runware.ai/docs/models/prunaai-p-video-2/examples#example-tomato-grafting-tool-demo-clip) · 720p · 4s: `$0.0606` (~16s)
- [first-last-frame](https://runware.ai/docs/models/prunaai-p-video-2/examples#example-mechanical-watch-assembly-b-roll) · 720p · 8s: `$0.201` (~20s)
- [first-frame](https://runware.ai/docs/models/prunaai-p-video-2/examples#example-maritime-archaeology-logo-ident) · 1080p · 5s: `$0.252` (~1m 12s)
- [text-to-video](https://runware.ai/docs/models/prunaai-p-video-2/examples#example-arctic-seed-vault-presenter) · 1080p · 6s: `$0.302` (~1m 5s)
- [audio-driven-image-animation](https://runware.ai/docs/models/prunaai-p-video-2/examples#example-lithium-battery-safety-avatar-clip) · 1080p: `$0.802` (~1m 46s)
- [audio-driven](https://runware.ai/docs/models/prunaai-p-video-2/examples#example-doorway-flood-barrier-explainer-clip) · 1080p: `$1.00` (~1m 43s)

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

## Compatibility & Validation

When `inputs.audio` is provided, `duration` cannot be used.

---

`inputs.frameImages` cannot be used with `width/height`.

---

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

---

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `720p (~16:9)` | `1280x704` |
| `720p (~9:16)` | `704x1280` |
| `720p (~4:3)` | `1088x832` |
| `720p (~3:4)` | `832x1088` |
| `720p (3:2)` | `1152x768` |
| `720p (2:3)` | `768x1152` |
| `720p (1:1)` | `960x960` |
| `1080p (~16:9)` | `1920x1088` |
| `1080p (~9:16)` | `1088x1920` |
| `1080p (~4:3)` | `1664x1216` |
| `1080p (~3:4)` | `1216x1664` |
| `1080p (~3:2)` | `1792x1152` |
| `1080p (~2:3)` | `1152x1792` |
| `1080p (1:1)` | `1408x1408` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/prunaai-p-video-2#request-tasktype)

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

Identifier for the type of task being performed

### [taskUUID](https://runware.ai/docs/models/prunaai-p-video-2#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/prunaai-p-video-2#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/prunaai-p-video-2#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/prunaai-p-video-2#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/prunaai-p-video-2#request-webhookurl)

- **Type**: `string`
- **Format**: `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](https://runware.ai/docs/platform/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/prunaai-p-video-2#request-deliverymethod)

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

Determines how the API delivers task results.

**Allowed values**:

- `async` 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](https://runware.ai/docs/platform/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/prunaai-p-video-2#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/prunaai-p-video-2#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/prunaai-p-video-2#request-safety-checkcontent)

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

Enable or disable content safety checking. Increases total generation time.

#### [mode](https://runware.ai/docs/models/prunaai-p-video-2#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/prunaai-p-video-2#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/prunaai-p-video-2#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/prunaai-p-video-2#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.

### [frameImages](https://runware.ai/docs/models/prunaai-p-video-2#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/prunaai-p-video-2#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/prunaai-p-video-2#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).

### [audio](https://runware.ai/docs/models/prunaai-p-video-2#request-inputs-audio)

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

Audio input (UUID or URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/prunaai-p-video-2#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `prunaai:p-video@2`

Identifier of the model to use for generation.

**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/prunaai-p-video-2#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `2048`

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/prunaai-p-video-2#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when width and height are 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/prunaai-p-video-2#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when width and height are 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/prunaai-p-video-2#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**: `720p` `1080p`

### [duration](https://runware.ai/docs/models/prunaai-p-video-2#request-duration)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `20`

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).

### [fps](https://runware.ai/docs/models/prunaai-p-video-2#request-fps)

- **Type**: `integer`
- **Default**: `24`

Frames per second for video generation. Higher values create smoother motion but require more processing time.

**Allowed values**: `24` `48`

### [seed](https://runware.ai/docs/models/prunaai-p-video-2#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `2147483647`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Settings**

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

### [audio](https://runware.ai/docs/models/prunaai-p-video-2#request-settings-audio)

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

Include audio in the generated video output.

### [draft](https://runware.ai/docs/models/prunaai-p-video-2#request-settings-draft)

- **Path**: `settings.draft`
- **Type**: `boolean`

Enable draft mode for lower-resolution preview generation.

### [promptUpsampling](https://runware.ai/docs/models/prunaai-p-video-2#request-settings-promptupsampling)

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

Automatically enhance the prompt for improved results.

## Response Parameters

### [taskType](https://runware.ai/docs/models/prunaai-p-video-2#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/prunaai-p-video-2#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/prunaai-p-video-2#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/prunaai-p-video-2#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/prunaai-p-video-2#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/prunaai-p-video-2#response-videodatauri)

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

Data URI of the output video.

### [seed](https://runware.ai/docs/models/prunaai-p-video-2#response-seed)

- **Type**: `integer`

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

### [NSFWContent](https://runware.ai/docs/models/prunaai-p-video-2#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/prunaai-p-video-2#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/prunaai-p-video-2/9a4dd467-da3c-4bd5-89e8-28fbc9accd9a.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "00ec6998-ff55-47ae-8f76-89a603d63b8c",
  "model": "prunaai:p-video@2",
  "positivePrompt": "A polished six-second documentary presenter clip inside an Arctic seed vault in Svalbard. One female crop geneticist in her early forties stands centered in a refrigerated archive aisle, framed in a steady landscape medium close-up from chest level. She wears a practical navy insulated jacket and holds a small silver seed packet. Frosted steel shelving filled with sealed seed boxes recedes behind her. Cool cyan overhead light contrasts with a soft amber utility lamp; visible ventilation gently stirs loose hair and faint cold mist drifts through the background. In one coherent take, she looks directly into the lens, raises the seed packet beside her face as she begins speaking, makes a small natural hand gesture, then finishes with a confident nod. Precise natural lip synchronization, restrained facial animation, credible eye contact. She says exactly: “These sealed seeds preserve crop diversity, giving future farmers options when climate and disease strike.” Subtle refrigeration hum and jacket movement, no music, no other voices, no captions, logos, or on-screen text. Premium science documentary realism, sharp face and foreground detail, natural skin texture, shallow depth of field.",
  "width": 1920,
  "height": 1088,
  "duration": 6
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-2/e1f2375a-10ae-4582-a781-9ac797a56e71.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "f677d46e-b353-45af-9693-57a8d28640af",
  "model": "prunaai:p-video@2",
  "positivePrompt": "The centered PELAGOS ARCHIVE identity holds against a nearly black deep-ocean field. A narrow cyan scanning light sweeps downward across the fragmented terracotta amphora, revealing fine ceramic texture. The individual shards drift apart by a few millimeters with controlled museum-display precision, then settle cleanly back into the amphora silhouette. One luminous sonar ring expands from the emblem, softly illuminating suspended particles before fading into darkness. The typography remains perfectly sharp, stable, and readable throughout. Locked symmetrical camera, premium institutional motion design, restrained movement, crisp edges, subtle dimensional lighting. End on the exact opening composition for a seamless loop. Minimal sound design: one low underwater sonar pulse, delicate ceramic ticks, and a soft sub-bass resolve; no speech.",
  "resolution": "1080p",
  "duration": 5,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/3725b242-fcfd-4690-8efa-2629cc90f835.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-2/3d210179-be20-4a2f-878d-2569add9e0ef.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "b792e31b-5f9a-4507-acde-1b72748e0b1b",
  "model": "prunaai:p-video@2",
  "positivePrompt": "Create a polished eight-second macro b-roll shot using the supplied first and last frames as exact endpoints. In one continuous, physically accurate take, a watchmaker steadily lowers the suspended balance bridge assembly toward the empty mounting point of the mechanical watch movement. The cobalt hairspring flexes subtly from gravity, the balance staff aligns with its jewel, and the bridge settles flush onto the brass mainplate. The tweezers make one minute corrective adjustment, release the bridge cleanly, then withdraw toward the right edge. Once seated, the balance wheel begins a rapid, controlled oscillation that resolves naturally into the supplied final frame. Preserve the exact movement design, holder, hand, tools, bench layout, lighting, scale, and shallow macro depth of field throughout. Camera remains locked with only realistic optical breathing as focus shifts from the tweezers to the seated balance wheel. Premium observational horology footage, restrained cyan and warm brass palette, crisp metal texture, natural hand motion, no cuts, no captions, no logos. Audio is intimate workshop ambience only: faint tweezers contact, a soft metallic click as the bridge seats, delicate ticking, and low room tone; no speech or music.",
  "resolution": "720p",
  "duration": 8,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/7672e162-ab33-43d4-a630-a8cf1843114f.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/b831c66c-6f07-4c1b-ae17-c92e46600063.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

### audio-driven (audio-driven)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-2/e2196303-a765-4dab-9693-5aa261fdaf7e.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "0d9708ff-d9cd-4776-bce0-288bffd76fc6",
  "model": "prunaai:p-video@2",
  "positivePrompt": "Finished portrait product explainer for a removable commercial doorway flood barrier, synchronized precisely to the supplied narration. Set in a clean municipal utility storeroom with pale concrete walls, polished floor, cobalt-blue pipes and safety-yellow details. The product remains consistent throughout: brushed-aluminum interlocking barrier panels, gray doorway side rails, two black compression handles and a continuous blue rubber gasket. Open on a low, urgent push toward shallow floodwater nearing the open doorway. At “three steps,” cut to a centered full-height view with a uniformed facilities technician ready to install the barrier. On “One,” show a sharp close-up as she slides each aluminum panel smoothly down between the rails. On “Two,” alternate macro shots of both black handles rotating and clamping firmly. On “Three,” track one gloved finger along the uninterrupted blue seal. At “Release the test water,” cut outside to a dramatic low angle as a controlled wave surges against the barrier with a strong splash. End inside on the perfectly dry threshold while water churns beyond it; slow, confident pullback. Crisp industrial cinematography, cool cyan and silver palette with yellow accents, realistic water physics, clear mechanical action, brisk instructional pacing, clean hard cuts, no captions, logos or interface graphics.",
  "width": 1088,
  "height": 1920,
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/4001ff95-c23a-4cdc-9b3f-18b83f93e4fc.mp3"
  }
}
```

---

### draft-preview (draft-preview)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-2/a6bd4366-49cd-4825-a24d-2b0931e54b80.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "cb465b50-0a56-4667-a8d5-6b5793ebf30a",
  "model": "prunaai:p-video@2",
  "positivePrompt": "A four-second, single-shot product demonstration for a commercial horticulture supplier. On a matte cobalt-blue nursery workbench, compose two young tomato seedlings diagonally: sturdy rootstock entering from lower left, leafy scion from upper right, with compact stainless-steel grafting shears centered between them. Hands in vivid chartreuse nitrile gloves squeeze the shears; the polished blades cut clean matching omega-shaped profiles, tiny stem offcuts spring aside, then the hands fit the two cut stems together and secure the joint with a translucent silicone grafting clip. Begin in a crisp three-quarter overhead view, then make a conspicuous fast 25-degree camera arc and smooth macro push-in that lands on the perfectly aligned graft union. Strong directional studio light, hard graphic shadows, fresh green leaves, tactile metal and plant textures, clean agricultural training-film art direction, precise realistic hand movement, sharp foreground detail, shallow depth of field at the finish. Crisp mechanical snip and subtle leaf rustle, no speech, no logos, no captions, no on-screen text.",
  "resolution": "720p",
  "duration": 4,
  "settings": {
    "draft": true
  }
}
```

---

### audio-driven-image-animation (audio-driven-image-animation)

[Watch video](https://assets.runware.ai/examples/prunaai-p-video-2/0d3cc20b-dec1-48c7-9959-a4bf074a2bba.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "1862a99a-0ff2-492c-b29c-07d96e516109",
  "model": "prunaai:p-video@2",
  "positivePrompt": "Animate the supplied first frame into a polished municipal safety presenter clip driven by the supplied speech audio. Preserve the handcrafted felt badger's identity, costume, props, set, lighting, and framing. Create precise, natural lip synchronization with subtle jaw, cheek, ear, brow, and eye movement. He maintains direct eye contact with the viewer and speaks with calm authority. Coordinate gestures to the dialogue: lift the used vape slightly on “old vape,” pause and become serious on “stop,” indicate the conveyor behind him when mentioning fires in trucks and sorting lines, demonstrate placing tape across the battery terminals, then gesture clearly toward the collection tray on “drop-off point instead.” Natural blinks, restrained head nods, small breathing motion, and tactile stop-motion character movement with smooth professional timing. Locked eye-level camera with only a very gentle push-in, shallow depth of field, sharp presenter and props, no cuts, no added characters, no captions, no logos, no visible text, and no music.",
  "resolution": "1080p",
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/dfb729ef-7c8f-4e2e-8a5d-9edb0be04364.jpg",
        "frame": "first"
      }
    ],
    "audio": "https://assets.runware.ai/assets/inputs/52b3f91d-f3e5-4092-88b2-35a3cee71deb.mp3"
  }
}
```