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)

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/Media-infrastructure'

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