Skip to main content
Glama

generate_video

Create AI-generated videos from text descriptions using Veo 3.1 technology. Specify duration, aspect ratio, and resolution for custom video production.

Instructions

Generate an AI video from text prompt using VAP (Veo 3.1). Returns a task ID for async tracking. Cost: $1.96. IMPORTANT: Send ONLY the video description. Do NOT include any instructions, guidelines, or meta-text. Just the pure visual description.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesONLY the visual description of the video. Do NOT include instructions or guidelines. Example: 'Cinematic aerial shot of a coastal cliff at golden hour, warm sunlight, gentle waves, camera slowly drifting forward'
durationNoVideo duration in seconds (4, 6, or 8)
aspect_ratioNoVideo aspect ratio. 16:9 for landscape/widescreen, 9:16 for portrait/vertical (TikTok, Reels). Extract from user's prompt if mentioned.16:9
generate_audioNoGenerate audio with the video (costs more)
resolutionNoVideo resolution. 1080p recommended for enterprise (+33% cost)720p
negative_promptNoWhat to avoid in the video generation

Implementation Reference

  • The handler function for the 'generate_video' tool, which creates a video generation task via the V3 API.
    def _handle_generate_video(arguments: Dict) -> Dict:
        """
        Handle generate_video tool call (Directive #242: Veo 3.1).
    
        Creates a video generation task via V3 API.
        """
        prompt = arguments.get("prompt", "")
        duration = arguments.get("duration", 8)
        aspect_ratio = arguments.get("aspect_ratio", "16:9")
        generate_audio = arguments.get("generate_audio", True)
        resolution = arguments.get("resolution", "720p")
        negative_prompt = arguments.get("negative_prompt", "")
    
        if not prompt:
            return {
                "isError": True,
                "content": [{"type": "text", "text": "Error: prompt is required"}]
            }
    
        # Validate duration (Veo 3.1: 4, 6, 8 seconds)
        if duration not in (4, 6, 8):
            duration = 8
    
        # Validate aspect ratio (Veo 3.1: 16:9, 9:16)
        if aspect_ratio not in ("16:9", "9:16"):
            aspect_ratio = "16:9"
    
        # Validate resolution
        if resolution not in ("720p", "1080p"):
            resolution = "720p"
    
        # Create task via V3 API
        logger.info(f"Creating Veo 3.1 video task: duration={duration}s, audio={generate_audio}")
    
        params = {
            "prompt": prompt,
            "duration": duration,
            "aspect_ratio": aspect_ratio,
            "generate_audio": generate_audio,
            "resolution": resolution
        }
        if negative_prompt:
            params["negative_prompt"] = negative_prompt
    
        response = make_v3_request("/v3/tasks", {
            "type": "video",
            "params": params
        })
    
        if "error" in response:
            return {
                "isError": True,
                "content": [{"type": "text", "text": f"Error: {response['error']}"}]
            }
    
        # Format success response
        task_id = response.get("task_id", "unknown")
        cost_table = VIDEO_COSTS_WITH_AUDIO if generate_audio else VIDEO_COSTS_NO_AUDIO
        estimated_cost = response.get("estimated_cost", cost_table.get(duration, 4.80))
    
        return {
            "content": [{
                "type": "text",
                "text": f"Video generation task created (Veo 3.1)!\n\nTask ID: {task_id}\nDuration: {duration} seconds\nAspect Ratio: {aspect_ratio}\nResolution: {resolution}\nAudio: {'Yes' if generate_audio else 'No'}\nEstimated Cost: ${estimated_cost}\n\nUse get_task with this task_id to check status and get the video URL when complete."
            }]
        }
  • Registration/routing for the 'generate_video' tool within the handle_tools_call function.
    if tool_name == "generate_video":
        return _handle_generate_video(arguments)
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively communicates key behavioral traits: the asynchronous nature ('Returns a task ID for async tracking'), cost implications ('Cost: $1.96'), and strict input requirements ('IMPORTANT: Send ONLY the video description...'). It doesn't mention rate limits, authentication needs, or error conditions, but provides substantial operational context.

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

Conciseness5/5

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

The description is perfectly front-loaded with the core purpose, followed by critical behavioral information (async tracking, cost), then essential usage instructions. Every sentence earns its place with zero waste. The structure moves from general to specific in a logical flow.

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

Completeness4/5

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

For a complex video generation tool with 6 parameters and no annotations or output schema, the description provides substantial context about the operation's nature, cost, and input requirements. It effectively compensates for the lack of output schema by explaining the async task ID return. However, it doesn't address potential failure modes, quality expectations, or integration with sibling tools like get_task for tracking.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all 6 parameters thoroughly. The description reinforces the critical constraint for the 'prompt' parameter ('Send ONLY the video description...'), adding some semantic emphasis beyond the schema. However, it doesn't provide additional meaning for other parameters beyond what's already in their schema 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?

The description clearly states the specific action ('Generate an AI video from text prompt') and resource ('using VAP (Veo 3.1)'), distinguishing it from sibling tools like generate_image or generate_music. It provides a complete functional statement beyond just restating the tool name.

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

Usage Guidelines4/5

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

The description provides clear context about when to use this tool ('Generate an AI video from text prompt') and includes important usage instructions ('Send ONLY the video description...'). However, it doesn't explicitly differentiate when to choose this over alternatives like video_merge or video_trim, nor does it mention prerequisites like checking balance first.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/elestirelbilinc-sketch/vap-showcase'

If you have feedback or need assistance with the MCP directory API, please join our Discord server