# Vimmerse Video Generation

> Vimmerse Video Generation is a paid API for AI agents from agents.vimmerse.co, paid per call via x402, $1.2/call, status healthy (last checked 2026-11-04, last successful call 2026-11-03).

Queues an AI video generation job from a text prompt (with optional reference media and audio), returning immediately with a media object to poll for completion.

## Facts

- Endpoint: POST https://agents.vimmerse.co/v2/media?utm_source=zero.xyz
- Price: $1.2/call
- Payment: x402
- Status: healthy
- Last checked: 2026-11-04
- Last successful call: 2026-11-03
- Success rate: 100% of calls made through Zero
- Activations on Zero: 1
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vimmerse-video-generation-a0983284
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_DMSBU0NFpHZ0f_nBHOAAn

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability vimmerse-video-generation-a0983284 -d '<json body>'
```

Example prompt: Generate me a 10-second looping video of a sunset over a mountain lake using the Veo model, in 16:9 aspect ratio, with soft background music — I want 1 clip.

## When to prefer this

Use this endpoint when you need to generate one or more AI video clips from a text prompt, optionally grounded in reference images or videos, with support for narration and background music. It is particularly valuable when you need fine-grained control over the AI model (e.g. choosing Veo, RunwayML, KlingPro, or Seedance), duration, aspect ratio, loop count, and audio. Prefer it over image generation siblings when the output must be a video. Use the /v2/media/estimate-credits route first if you need to budget accurately before submitting.

## Known failure modes

- Insufficient credits — job queued but fails if account balance is too low
- Invalid video_tool enum value returns a validation error
- Reference media URLs that are inaccessible or non-public cause generation failure
- Prompt content that violates content policies results in rejection
- Polling timeout if generation takes longer than expected for complex prompts
- Invalid aspect_ratio string may cause unexpected output dimensions or an error

## How this service works

Queues a video generation job from a text prompt, optional reference media and an optional audio track, and returns the media object at once. Poll GET /v2/media/{media_id} until processing_status is success and read the URLs in result. Credits depend on the tool tier, the duration, the quantity and the audio options, and the estimate route returns the exact number.

## Output

Returns a media object immediately upon queuing, including a media_id and initial processing_status. The agent must poll GET /v2/media/{media_id} until processing_status is 'success', at which point the response contains result URLs pointing to the generated video clip(s). Credits consumed depend on the chosen video_tool tier, duration, quantity, and audio options.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "loop": {
   "type": "integer",
   "default": 1,
   "description": "Loop count applied in post-processing."
  },
  "title": {
   "type": "string",
   "default": "",
   "description": "Media title."
  },
  "prompt": {
   "type": "string",
   "default": "",
   "description": "Text prompt for the video."
  },
  "duration": {
   "type": "integer",
   "default": 5,
   "description": "Clip length in seconds."
  },
  "quantity": {
   "type": "integer",
   "default": 1,
   "description": "Number of clips."
  },
  "video_tool": {
   "enum": [
    "Auto",
    "AutoT3",
    "AutoT1",
    "HappyHorse",
    "Grok",
    "KlingAI",
    "KlingT3",
    "KlingPro",
    "GoogleOmni",
    "VeoLite",
    "VeoFast",
    "Veo",
    "RunwayML",
    "MinimaxHailuo",
    "MinimaxTurbo",
    "Seedance",
    "SeedanceFast",
    "SeedanceT6",
    "Pixverse",
    "PixverseT3",
    "Hunyuan",
    "Vidu",
    "PVideo",
    "StaticMotion",
    "Wan",
    "TryOnVideo"
   ],
   "type": "string",
   "default": "Auto",
   "description": "Video tool. Auto picks one; AutoT1 and AutoT3 pick within a tier. The choice sets the credits per call; POST /v2/media/estimate-credits returns the exact number for this body."
  },
  "description": {
   "type": "string",
   "default": "",
   "description": "Media description."
  },
  "media_items": {
   "type": "array",
   "items": {
    "type": "object",
    "additionalProperties": true
   },
   "description": "Optional input media items (objects carrying a public image, video or audio URL) for image-to-video or reference-based generation."
  },
  "webhook_url": {
   "type": "string",
   "format": "uri",
   "description": "Optional callback URL that receives status updates."
  },
  "aspect_ratio": {
   "type": "string",
   "description": "Output aspect ratio."
  },
  "audio_option": {
   "type": "object",
   "properties": {
    "narrator": {
     "type": "string",
     "description": "Voice for narration: AutoV, Rachel, Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily or Bill."
    },
    "narration": {
     "type": "string",
     "description": "Text to speak with the narrator."
    },
    "bg_music_url": {
     "type": "string",
     "format": "uri",
     "description": "External background music URL."
    },
    "native_audio": {
     "type": "boolean",
     "description": "Native audio from the video model."
    },
    "narr
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vimmerse-video-generation-a0983284/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.vimmerse.co](https://www.zero.xyz/host/agents.vimmerse.co/llms.txt)