From obul-media
USE THIS SKILL WHEN: the user wants to generate AI videos or images. Provides pay-per-use video generation with OpenAI Sora 2, xAI Grok Imagine, and GPT Image via Genbase through the Obul proxy.
How this skill is triggered — by the user, by Claude, or both
Slash command
/obul-media:genbaseThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate AI videos and images via Genbase's x402-enabled platform. Supports multiple generation models including
Generate AI videos and images via Genbase's x402-enabled platform. Supports multiple generation models including OpenAI Sora 2 for high-quality video, xAI Grok Imagine for fast and flexible video, and GPT Image for AI image generation. Through the Obul proxy, each generation is paid individually — no Genbase account or API key required.
All requests use the obulx CLI, which handles proxy routing and authentication automatically.
Install and log in (one-time setup):
npm install -g @obul.ai/obulx
obulx login
Base URL: https://www.genbase.fun
Generate high-quality AI video using OpenAI's Sora 2 model. Supports multiple durations and resolutions including landscape, portrait, wide, and tall formats. Generation takes 3-15 minutes depending on the model tier.
Pricing: $0.20
obulx -X POST -H "Content-Type: application/json" \
-d '{"prompt": "A drone shot flying over a misty mountain valley at sunrise, cinematic lighting", "model": "sora-2", "seconds": "10", "size": "1280x720"}' \
"https://www.genbase.fun/api/video/create-sora2"
Parameters:
| Parameter | Type | Required | Options | Description |
|---|---|---|---|---|
prompt | string | yes | — | Video description |
model | string | no | sora-2, sora-2-pro | Model tier (pro supports 25s) |
seconds | string | no | 10, 15, 25 (pro only) | Video duration |
size | string | no | 1280x720, 720x1280, 1792x1024, 1024x1792 | Output resolution |
Response:
{
"video_id": "task-uuid",
"status": "pending",
"model": "sora-2",
"seconds": "10",
"size": "1280x720"
}
Generate AI video using xAI's Grok Imagine model. Supports text-to-video, image-to-video, and video-to-video modes with flexible duration (1-15 seconds) and multiple aspect ratios. Generation takes 2-5 minutes.
Pricing: $0.01 per second of video (1-15 seconds)
obulx -X POST -H "Content-Type: application/json" \
-d '{"prompt": "A cat playing piano in a jazz club, warm ambient lighting", "duration": 10, "aspectRatio": "16:9", "resolution": "720p", "mode": "text-to-video"}' \
"https://www.genbase.fun/api/video/create-xai"
Parameters:
| Parameter | Type | Required | Options | Description |
|---|---|---|---|---|
prompt | string | yes | — | Video description |
duration | integer | no | 1-15 | Video length in seconds |
aspectRatio | string | no | 16:9, 9:16, 1:1, 4:3, 3:4 | Output aspect ratio |
resolution | string | no | 480p, 720p | Output resolution |
mode | string | no | text-to-video, image-to-video, video-to-video | Generation mode |
referenceImage | string | no | — | URL for image/video reference modes |
Response:
{
"request_id": "req-uuid",
"status": "pending",
"provider": "xai",
"duration": 10
}
Generate an AI image using GPT Image. Supports text-to-image and image-to-image with an optional base64-encoded reference image. Generation takes 30-90 seconds.
Pricing: $0.02
obulx -X POST -H "Content-Type: application/json" \
-d '{"prompt": "A minimalist logo design for a tech startup, clean lines, blue and white color scheme"}' \
"https://www.genbase.fun/api/image/create"
Parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | yes | Image description |
referenceImage | string | no | Base64-encoded image for image-to-image mode |
Response:
{
"image_id": "img-uuid",
"status": "completed",
"url": "https://..."
}
Poll the status of a Sora 2 video generation task. Free endpoint — no payment required.
Pricing: $0.00
obulx "https://www.genbase.fun/api/video/query?id={video_id}"
Response:
{
"video_id": "task-uuid",
"status": "Ready",
"progress": 100,
"url": "https://...video_url..."
}
Status values: pending (20%), processing (50%), video_upsampling (80%), Ready (100%), failed
Poll the status of an xAI Grok Imagine video generation task. Free endpoint — no payment required.
Pricing: $0.00
obulx "https://www.genbase.fun/api/video/query-xai?id={request_id}"
Response:
{
"request_id": "req-uuid",
"status": "completed",
"url": "https://...video_url..."
}
Status values: pending, completed, failed
| Endpoint | Price | Purpose |
|---|---|---|
POST /api/video/create-sora2 | $0.20 | Generate video with OpenAI Sora 2 |
POST /api/video/create-xai | $0.01/sec | Generate video with xAI Grok Imagine |
POST /api/image/create | $0.02 | Generate image with GPT Image |
GET /api/video/query | $0.00 | Poll Sora 2 generation status |
GET /api/video/query-xai | $0.00 | Poll xAI generation status |
GET /api/image/query | $0.00 | Poll image generation status |
mode: "image-to-video" and a reference image URL to animate a still image.Ready or completed.1280x720 for landscape, 720x1280 for portrait/vertical
content, 1792x1024 for widescreen, and 1024x1792 for tall formats.| Error | Cause | Solution |
|---|---|---|
402 Payment Required | Payment not processed or insufficient | Verify your account has sufficient balance at my.obul.ai. Run obulx login if not authenticated. |
400 Bad Request | Missing or invalid request body | Ensure prompt is present. Check that model, seconds, and size are valid values. |
422 Content Policy Violation | Prompt violates content policy | Revise prompt to comply with guidelines. Contact support for refund if charged. |
404 Not Found | Invalid video/image ID in query | Verify the ID matches the one returned from the creation endpoint. |
429 Too Many Requests | Rate limit exceeded | Add delays between requests. Video generation is resource-intensive. |
500 Internal Server Error | Upstream Genbase service issue | Wait and retry. If persistent, the service may be experiencing downtime. |
failed status | Generation failed (model or content issue) | Check prompt for content policy violations. Try a simpler prompt or different model. |
npx claudepluginhub polymerdao/pay-plugin --plugin obul-mediaGenerates AI videos from text descriptions or images using Google Veo 3.1 (default) or OpenAI Sora. Supports dialogue/audio, reference images, image-to-video animation, and interactive requirement gathering.
Generates videos from text prompts via fal.ai models like Kling 2.6 Pro, Sora 2, LTX-2 Pro, Runway Gen-3 Turbo, Luma Dream Machine; supplies endpoints, durations, aspect ratios, prompt structures, TypeScript/Python code.
Generates AI video using Veo (MCP tools) or Sora (API) for text-to-video, image-to-video, video extension, and styled generation. Includes provider selection and draft-to-final workflow.