Skip to main content
Glama

generate_video

Destructive

Create AI videos from text prompts, images (first/last frame), or by extending reference videos, with adjustable duration, resolution, and model.

Instructions

Generate a video using AI via MeiGen platform. Supports text-to-video, image-to-video (first/last frame), and reference-video continuation (Seedance 2.0 only — pass referenceVideo URL + referenceVideoDuration together, and prompt must explicitly say "extend / continue"). Available models include Seedance 2.0 (fast/pro tiers, 4-15s), Happyhorse 1.0 (cost-effective, 3-15s), and Veo 3.1 (fast/pro tiers, 4/6/8s, native audio). Pricing varies — seedance/happyhorse are per-second, veo is per-generation by tier × duration. See https://www.meigen.ai/model-comparison for the current schedule. With a reference video (seedance only), billable seconds = max(reference_duration + duration, min_billable[duration]); total often higher than direct generation. Generation typically takes 1–5 minutes (veo at 4k can take up to ~8 min).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesThe video generation prompt. Describe motion, scene, and style — not just the still image.
modelYesVideo model ID. Use list_models to see available video models. Common (as of writing): "seedance-2-0" (multi-tier general purpose), "happyhorse-1.0" (cost-effective i2v/t2v), "veo-3.1" (Google Veo with two tiers, 4/6/8s, native audio).
tierNoQuality tier — only for models that support tiers. seedance-2-0 and veo-3.1 currently accept "fast" (default, cheaper) or "pro" (higher fidelity). Tiers may be added by the platform — call list_models to see what each model exposes.
durationNoVideo duration in seconds. seedance-2-0 / happyhorse-1.0 currently accept ~3–15s (any integer in range). veo-3.1 accepts exactly 4, 6, or 8 (default 4) — other values will be rejected. Defaults to the model's default duration. Call list_models for the current allowed values per model.
resolutionNoOutput resolution. Common: "480p" / "720p" / "1080p" (model-dependent). Use list_models to see what each model supports. Higher resolutions cost more credits per second.
aspectRatioNoAspect ratio: "16:9", "9:16", "1:1", "4:3", "3:4", "21:9", "auto", "adaptive" (model-dependent). Defaults to "auto" when omitted.
firstFrameNoOptional first-frame image to control where the video starts. Accepts public URL or local file path (auto-uploaded). Highly recommended for image-to-video; with no first frame the model does pure text-to-video.
lastFrameNoOptional last-frame image to also control where the video ends. Used by seedance-2-0 and veo-3.1; happyhorse-1.0 ignores this field. Accepts public URL or local file path. Requires firstFrame to also be provided — passing lastFrame alone is rejected.
referenceVideoNoOptional reference video URL for Seedance 2.0 "video continuation". Must be a publicly accessible HTTPS URL (typically a previous generation result `videoUrl`); local paths are not supported. Only seedance-2-0 accepts this — passing it with other models will fail. IMPORTANT — prompt requirement: to make the new clip semantically continue the reference, the `prompt` MUST explicitly say "extend" / "continue" (e.g. prefix with "Extend this video with the following plot:"). Without that, the model treats the video as visual reference only and the new clip may drift from a true continuation. Output behavior: the output is ONLY your `duration` seconds (4-15s) of new content — the reference video is NOT concatenated into the output. To get a single "original + new" clip the user must stitch them locally. Billing: credits are charged at the With-reference-video rate, with `billable_seconds = max(reference_duration + duration, min_billable[duration])`. Total cost is often higher than direct generation of the same output length. Always pass `referenceVideoDuration` alongside this field — omitting it causes underbilling and broken continuation behavior.
referenceVideoDurationNoDuration of the reference video in seconds (typically 2–15 — backend validates the current allowed range). REQUIRED whenever `referenceVideo` is set; if omitted the backend treats it as 0, leading to undercharged credits and misconfigured generation. Pass the actual duration of the clip at `referenceVideo`.
Behavior5/5

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

Annotations already mark destructiveHint=true, but the description adds critical behavioral context: generation time (1-5 minutes, up to 8 min for 4k), billing implications for reference video ('billable_seconds = max(reference_duration + duration, min_billable[duration])'), and output behavior ('the output is ONLY your duration seconds of new content'). No contradiction with annotations.

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

Conciseness3/5

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

The description is verbose, especially the reference video billing explanation and model details. While well-structured, it could be more concise without losing clarity. The key information is front-loaded but the length may overwhelm an agent.

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?

The description covers the multi-modal usage, model selection, parameter constraints, and behavioral outcomes. However, it does not describe the return value format (e.g., a video URL or download link), which is a gap given the lack of an output schema.

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

Parameters5/5

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

All 10 parameters have schema descriptions (100% coverage). The description adds significant meaning: for referenceVideo, it explains the 'extend'/'continue' prompt requirement and the non-concatenated output; for prompt, it advises to describe motion and scene; for lastFrame, it notes the dependency on firstFrame. This goes beyond the schema's bare definitions.

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 'Generate a video using AI via MeiGen platform' and lists three modes: text-to-video, image-to-video, and reference-video continuation. It distinguishes the tool's scope from sibling tools like generate_image by specifying it's for video generation, though it doesn't explicitly contrast with them.

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 guidelines on when to use different models (Seedance 2.0, Happyhorse, Veo 3.1) and the special usage for reference video continuation ('pass referenceVideo URL + referenceVideoDuration together, and prompt must explicitly say extend/continue'). It lacks explicit guidance on when to choose this tool over siblings, but the context is clear for parameter usage.

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/jau123/MeiGen-AI-Design-MCP'

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