Skip to main content
Glama

Create a video

create_video

Create (enqueue) a new AI faceless video from a topic. Returns immediately with a video id and status "PENDING"; the render runs asynchronously — poll get_video every 20-30 seconds until status is "COMPLETED" (playable videoUrl) or "FAILED". Costs 40 credits with the default voice (+25 for a language only ElevenLabs speaks, e.g. Persian); art style does not change the price. A short balance is refused up front with 402 INSUFFICIENT_CREDITS stating credits needed, available and a top-up URL. A new account with no credits that has not had its free first video gets it here instead of an error: watermarked, labelled AI-generated, up to 30 seconds, standard voice, one per account, subject to the day's availability. (Standard 30-second style; niche, art style and motion do not apply to it.) Set prompt_handling to "as_written" to use my words exactly. If the model refuses a scene, it fails instead of being reworded. Requires the "video:create" scope on the API key. OPTIONAL AI MOTION: pass motion_scenes (0-3, default 0 = a normal video) to turn that many scenes, starting with the first, into a 5-second AI video clip instead of a still image. Price: 115 credits per motion scene EXTRA (so 1 scene = 155 credits in total with the default voice). Call quote_video first and tell the user the price before creating. Any account with enough credits can use it: there is no plan or trial limit. A clip that cannot be made falls back to the still image and its 115 credits are refunded. Content is checked first: children, real people, sexual content, protected characters and lip-sync/deepfakes are refused (422 PROMPT_BLOCKED, nothing charged). For a pasted cinematic video prompt (camera, lens, lighting, one shot) use generate_motion_clip instead: it sends the prompt as written and makes one silent clip, with no script or voice.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "topic": "<topic>"
    },
    "name": "create_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
nicheNoOptional content niche. Call list_niches for the authoritative list with labels.
topicYesWhat the video is about. The full script is AI-generated from this. e.g. "3 tiny habits that quietly change your life".
artStyleNoOptional visual art style. Defaults to AUTOSHORTS (cinematic). Call list_niches for the full list.
durationNoTarget length in seconds for the multi-scene faceless video: 30, 60 or 90 (default 30).
languageNoOptional BCP-47 language code (e.g. "en", "vi", "es"). Defaults to "auto".
motion_scenesNoOptional. How many scenes (from the first) to animate as AI clips. 115 credits each, on top of the video price. Default 0.
prompt_handlingNo"as_written": Use my words exactly. If the model refuses a scene, it fails instead of being reworded. Scenes the user wrote nothing for are still generated. "assist" (default): the product may reword picture text, as before.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / prompt_handling
      Added value: +{
      +  "description": "\"as_written\": Use my words exactly. If the model refuses a scene, it fails instead of being reworded. Scenes the user wrote nothing for are still generated. \"assist\" (default): the product may reword picture text, as before.",
      +  "enum": [
      +    "assist",
      +    "as_written"
      +  ],
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / motion_scenes / description
      Previous value: -"Optional. How many scenes (from the first) to animate as AI clips. 40 credits each, on top of the video price. Default 0."New value: +"Optional. How many scenes (from the first) to animate as AI clips. 115 credits each, on top of the video price. Default 0."
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only say the tool is a non-idempotent, open-world write; the description adds the async render contract (PENDING, poll every 20-30s), exact credit costs including the +25 language and 115/scene motion surcharges, the 402 INSUFFICIENT_CREDITS response fields, the 422 PROMPT_BLOCKED content policy, the watermarked free-first-video behavior, the refund-on-fallback rule, and the required video:create scope. This is substantial behavior beyond structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is dense and front-loaded, opening with purpose, then async behavior, then pricing and alternatives. Every major sentence carries actionable information, though the long single paragraph and the extended free-first-video parenthetical make it heavier than necessary; bullet-style structure would improve scanability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, priced, asynchronous, content-moderated mutation tool with no output schema, the description covers return shape (video id and PENDING status), polling, error codes, cost, scope requirements, and the sibling alternative. Nothing essential for a correct first call is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents the parameters, but the description adds real meaning: prompt_handling='as_written' changes failure behavior rather than rewording, motion_scenes costs 115 credits each and animates scenes from the first, and language pricing depends on ElevenLabs availability. That goes beyond the schema's field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Create (enqueue) a new AI faceless video from a topic.' It distinguishes the tool from generate_motion_clip explicitly at the end, so an agent can pick correctly without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use guidance ('Call quote_video first and tell the user the price'), the polling workflow with get_video, and a clear exclusion routing pasted cinematic prompts to generate_motion_clip. It also explains the free-first-video path and its constraints, leaving little to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources