---
title: MiniMax H3 Fast | Runware Docs
url: https://runware.ai/docs/models/minimax-h3-fast
description: Fast multimodal video generation with native audio and image, video, and audio reference control
---
# MiniMax H3 Fast

![MiniMax H3 Fast](https://assets.runware.ai/covers/minimax-h3-fast.jpg)

MiniMax H3 Fast is a speed-optimized H3 video model for generating 5 to 15 second clips at 480p or 768p. It supports text-to-video, first-frame image-to-video, and multimodal reference workflows that combine text with video and audio inputs to preserve visual context, motion, or voice characteristics. It is designed for fast previews, batch generation, and interactive creative workflows that need broader reference control than H3 Max Turbo.

- **Status**: live
- **ID**: `minimax:h3@fast`
- Try in Playground
- **Creator**: MiniMax
- **Release Date**: September 8, 2026
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Video, Image to Video, Video to Video, Audio to Video, Checkpoint

## Pricing

$0.046 from, per second · ~30s per request

**Rates** (per second)

- 480p: `$0.046`
- 768p: `$0.08`
- 480p · uploaded video: `$0.046`
- 768p · uploaded video: `$0.08`

**4 example generations**

- [text-to-video](https://runware.ai/docs/models/minimax-h3-fast/examples#example-couture-apiary-suit-showcase-reel) · 480p · 6s: `$0.276` (~13s)
- [first-frame](https://runware.ai/docs/models/minimax-h3-fast/examples#example-pigeon-anthem-music-video-segment) · 8s: `$0.368` (~34s)
- [first-last-frame](https://runware.ai/docs/models/minimax-h3-fast/examples#example-water-rights-documentary-title-sequence) · 10s: `$0.46` (~25s)
- [reference-to-video](https://runware.ai/docs/models/minimax-h3-fast/examples#example-freeport-crime-series-title-teaser) · 480p · 12s: `$0.884` (~59s)

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

## Compatibility & Validation

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

---

When `inputs.frameImages` is provided, `width/height` cannot be used.

---

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

---

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

---

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `480p (~16:9)` | `864x480` |
| `480p (4:3)` | `640x480` |
| `480p (1:1)` | `480x480` |
| `480p (3:4)` | `480x640` |
| `480p (~9:16)` | `480x864` |
| `480p (21:9)` | `1120x480` |
| `768p (~16:9)` | `1344x768` |
| `768p (4:3)` | `1024x768` |
| `768p (1:1)` | `768x768` |
| `768p (3:4)` | `768x1024` |
| `768p (~9:16)` | `768x1344` |
| `768p (21:9)` | `1792x768` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/minimax-h3-fast#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/minimax-h3-fast#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/minimax-h3-fast#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/minimax-h3-fast#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/minimax-h3-fast#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/minimax-h3-fast#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/minimax-h3-fast#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/minimax-h3-fast#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/minimax-h3-fast#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/minimax-h3-fast#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/minimax-h3-fast#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/minimax-h3-fast#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/minimax-h3-fast#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/minimax-h3-fast#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/minimax-h3-fast#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `9`
- **Size (each)**: `256 px to 5760 px`
- **Aspect ratio (each)**: `1:2.5 to 2.5:1`
- **File size (each)**: `up to 30 MB`

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

### [frameImages](https://runware.ai/docs/models/minimax-h3-fast#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`
- **Size (each)**: `256 px to 5760 px`
- **Aspect ratio (each)**: `1:2.5 to 2.5:1`
- **File size (each)**: `up to 30 MB`

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/minimax-h3-fast#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/minimax-h3-fast#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/minimax-h3-fast#request-inputs-referencevideos)

- **Path**: `inputs.referenceVideos`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`
- **Size (each)**: `256 px to 5760 px`
- **Aspect ratio (each)**: `1:2.5 to 2.5:1`
- **Frame rate (each)**: `23.98 fps to 60 fps`
- **Duration (each)**: `2s to 15s`
- **Duration (total)**: `up to 15s`
- **File size (each)**: `up to 50 MB`

List of reference videos (UUID or URL).

### [referenceAudios](https://runware.ai/docs/models/minimax-h3-fast#request-inputs-referenceaudios)

- **Path**: `inputs.referenceAudios`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`
- **Duration (each)**: `2s to 15s`
- **Duration (total)**: `up to 15s`
- **File size (each)**: `up to 15 MB`

List of reference audios (UUID or URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/minimax-h3-fast#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `minimax:h3@fast`

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/minimax-h3-fast#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `7000`

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/minimax-h3-fast#request-width)

- **Type**: `integer`
- **Default**: `864`
- **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/minimax-h3-fast#request-height)

- **Type**: `integer`
- **Default**: `480`
- **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/minimax-h3-fast#request-resolution)

- **Type**: `string`

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

**Allowed values**: `480p` `768p`

### [duration](https://runware.ai/docs/models/minimax-h3-fast#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).

### [seed](https://runware.ai/docs/models/minimax-h3-fast#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.

## Response Parameters

### [taskType](https://runware.ai/docs/models/minimax-h3-fast#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/minimax-h3-fast#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/minimax-h3-fast#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/minimax-h3-fast#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/minimax-h3-fast#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/minimax-h3-fast#response-videodatauri)

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

Data URI of the output video.

### [seed](https://runware.ai/docs/models/minimax-h3-fast#response-seed)

- **Type**: `integer`

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

### [NSFWContent](https://runware.ai/docs/models/minimax-h3-fast#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/minimax-h3-fast#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/minimax-h3-fast/b7a460e6-814a-4c84-9d0f-727d375b3df3.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "c27a0841-1694-4cac-a97a-fc65640bcd89",
  "model": "minimax:h3@fast",
  "positivePrompt": "A polished six-second vertical fashion showcase reel featuring one model in a couture ivory beekeeping suit: structured cotton twill, sculpted shoulders, fitted utility waist, reinforced gloves, tall cream boots, and a geometric mesh veil hood with subtle amber piping. The setting is a minimalist honey-processing room with pale limestone walls, brushed stainless steel equipment, and shallow glass trays of glowing golden honey. Warm late-afternoon light passes through the honey and casts amber reflections across the otherwise cool, quiet space. Begin with a symmetrical full-body portrait as the model stands still, centered and poised like a runway campaign. The model then turns slowly through three quarters, revealing the suit's articulated sleeves, tailored back, utility pockets, and veil profile while the fabric moves naturally. The camera performs one smooth, controlled push-in from full body to waist-up, then gently arcs around the model and finishes on a crisp close view of one gloved hand adjusting the amber-edged cuff. A few bees drift calmly in the distant background without obscuring the garment. Sophisticated protective-workwear editorial, restrained ivory, silver, and honey-gold palette, tactile fabric detail, premium product lighting, realistic human proportions, stable garment construction, elegant measured motion, shallow depth of field, no cuts, no text, no logos, no watermark.",
  "width": 480,
  "height": 864,
  "duration": 6
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/minimax-h3-fast/ee3974b9-2687-4608-aa49-904568e373c4.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "631fa4fc-33be-4c78-abf0-12b8c50060c5",
  "model": "minimax:h3@fast",
  "positivePrompt": "Continue naturally from the supplied opening frame as one uninterrupted eight-second music-video shot. The elderly pigeon fancier holds still for the first half-beat, then snaps open the wicker basket and raises both arms with calm, ceremonial precision. A dense flock of white and charcoal racing pigeons surges upward around him in time with an imagined 128 BPM chorus, wings passing close to the lens before spiraling toward the open cobalt sky. The pigeons waiting at his feet join the release in successive waves. Execute a smooth, fast dolly toward the performer followed by a subtle clockwise orbit, ending in a heroic low-angle medium-wide view as he looks upward and his sulfur-yellow tracksuit ripples in the wing-driven air. Preserve his identity, wardrobe, the velodrome architecture, damp surfaces, weeds, ground fog and sodium lamp throughout. Blue-hour cobalt and concrete-gray palette punctuated by sulfur yellow and warm amber; tactile 16mm grain, slight halation, crisp natural wing motion, realistic flock behavior, dramatic but believable lighting. Ecstatic, dignified and communal rather than comic. Cinematic ultrawide framing with safe central action, no cuts, no slow motion, no captions, no lettering, no logos.",
  "duration": 8,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/bcc0fe87-5fd6-4d22-b93c-183313ee5543.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/minimax-h3-fast/12333fdc-38df-469c-9502-ce2f80d31ea7.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "2dc9962b-25a0-4bbd-bd99-6dea6afb8989",
  "model": "minimax:h3@fast",
  "positivePrompt": "Create a single coherent 10-second cinematic title sequence transitioning between the supplied first and last frames. Keep the camera completely locked, preserving the intake tower, canyon contours, horizon, lens perspective, and centered composition. Begin in near silence visually: a drained reservoir at cold dawn, cracked mud and survey stakes motionless under drifting dust. Fine cracks slowly darken as moisture travels through them. Water then wells up naturally from the lowest channels and spreads across the basin in an elegant accelerated-time transition, lifting small ripples and dissolving the dust without a cut. The water level rises around the survey stakes and intake tower while the palette shifts gradually from dry ochre and faded sage to deep cobalt and silver-blue. Submerged survey lines become luminous hydrographic contours beneath the surface. During the final three seconds, those pale contour lines align and resolve cleanly into the exact centered title from the last frame: “THE LAST ALLOCATION,” with “A DOCUMENTARY SERIES” beneath it. Finish on calm water with subtle reflections, a slow break of dawn light, and perfectly stable, legible typography matching the final image. Prestige investigative documentary tone, restrained and ominous rather than apocalyptic, photorealistic 35mm cinematography, natural atmospheric depth, smooth physically coherent water movement, no camera cut, no camera shake, no extra text, no logos, no people.",
  "duration": 10,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/01c38747-8aec-453c-bb61-e77e7e324639.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/4a64fb0d-a217-46b9-89b5-8489b89fcbb3.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/minimax-h3-fast/83b777ec-467e-4ad1-8663-e0abbc3a624a.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "f538015a-8ccc-4806-afe5-3a4db70b9ebb",
  "model": "minimax:h3@fast",
  "positivePrompt": "Create a finished 12-second cinematic title teaser for a prestige crime series titled FREEPORT, set inside the secretive world of customs-free fine-art storage. Use all three references as complementary guidance. The reference image defines the central subject, production design and palette: raw museum crate, old-master portrait eye behind translucent conservation film, steel shelving, customs seals, graphite shadows and oxidized amber light. Preserve its tactile realism and sense of concealed cultural wealth. The reference video defines the continuous camera language and physical motion: a slow, precise lateral tracking move through monumental warehouse crates, narrow-gap parallax, subtle lens breathing, drifting dust and gently shifting plastic sheeting. Match its restrained speed and high-security atmosphere rather than cutting like an action trailer. The reference audio controls pacing and visual accents: security lights faintly pulse with the sub-bass, the metallic impact near the midpoint motivates a sharp inspection-light sweep, the rising scrape builds visual tension, and the final resonant strike lands exactly with the title reveal.\n\nBegin in extreme macro darkness on splintered plywood fibers and a waxy customs seal, with a razor-thin amber beam crawling across the surface. The camera glides past a crate seam and peers through a narrow opening, revealing the painted eye from the referenced old-master portrait under rippling translucent conservation film. Keep the painting clearly an artwork, not a living face. Continue the same impossible but physically convincing tracking move outward into a vast, immaculate warehouse aisle where anonymous art crates recede into blackness. At the midpoint metallic hit, an automated inspection bar sweeps once across the aisle, briefly exposing inventory marks, steel mesh and suspended dust without making any small label readable. Shadows close in as the camera approaches a matte-black crate at the end of the aisle. During the final two seconds, the amber scan resolves into centered, widely tracked uppercase title lettering: FREEPORT. The title should be clean, elegant, sharp and fully legible, warm ivory against near-black, with no subtitle, credits, logos or additional words. End on a composed title card with only slight floating dust and a dying amber reflection. Premium European crime-thriller tone, forensic rather than violent, photorealistic materials, deep blacks, restrained tarnished-gold highlights, subtle 2.39:1 cinematic composition within the landscape frame, controlled anamorphic flare, fine film grain, no people, no UI, no watermarks.",
  "width": 864,
  "height": 480,
  "duration": 12,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/d0469207-0f52-43ee-bb77-516835e68c46.jpg"
    ],
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/9a7a956a-225b-4691-a867-39e8867c904a.mp4"
    ],
    "referenceAudios": [
      "https://assets.runware.ai/assets/inputs/78d2f6dd-e02c-4b11-af5e-654a08271c10.mp3"
    ]
  }
}
```