Skip to main content
Glama

AetherWave Studio

by com.aetherwavestudio.mcp
OverviewDiscussionsAdmin

Generate video (Grok Imagine, Wan 2.7, Hailuo 02, Seedance, Kling 2.6, VEO 3.1, Happy Horse)

aetherwave_generate_video

Generates a short-form video from a text prompt (T2V) or a text prompt + starting image (I2V). Submits, polls, and returns the final video URL. Default model is 'grok-imagine-t2v' (fast, 4-6 cr/s, with built-in KIE -> fal.ai fallback). Use list_video_models for the full lineup with credit cost per second. I2V models (e.g. 'grok-imagine-i2v', 'seedance-pro-i2v') require a public imageUrl. Video generation can take 30s to several minutes; this tool polls with up to an 8-minute budget.

Model selection guide for videos (when the user does not specify a model)

Default: grok-imagine-t2v (4-6 cr/s, fast, has KIE -> fal.ai fallback for redundancy. Best general-purpose).

Pick a different model when the prompt has these signals:

  • "highest quality" / "premium" / broadcast / commercial -> veo3.1-quality or veo3-quality (Google's flagship, fixed 350-560 cr for 8s, 3-5 min)

  • "fast premium" / quick high-quality -> veo3-fast or veo3.1-fast (84 cr fixed for 8s)

  • Cinematic camera moves / dolly / pan -> seedance-pro-t2v (3-10 cr/s) or kling-3.0-pro-t2v (26 cr/s)

  • Realistic human motion / faces -> hailuo-2.3-pro-i2v (I2V, supply imageUrl)

  • Talking head / lip sync -> kling-avatar-pro (23 cr/s) or infinitalk (5-17 cr/s)

  • Anime / stylized / fantasy -> wan-2.7-t2v

  • NSFW / adult -> wan-22-nsfw-i2v (I2V only; auto-tags adult)

  • Animate this exact image -> any I2V variant (grok-imagine-i2v, seedance-pro-i2v, hailuo-2.3-pro-i2v)

  • First + last frame interpolation -> seedance-pro-i2v with both imageUrl + endImageUrl

  • Cheapest test -> hailuo-2.0-standard @ 512p (3 cr/s, ~18 cr for 6s) or grok-imagine-t2v @ 480p (4 cr/s, ~24 cr for 6s)

  • Clip 12-15s -> grok-imagine-t2v (accepts up to 15s)

  • True 4K -> kling-3.0-4k-t2v (94 cr/s, expensive but native 4K)

Audio in generated video: grok-imagine-t2v, seedance-pro-t2v, and the VEO 3.x family include audio at base cost (no surcharge). Kling 2.6 and Kling 3.0 are the outliers — they price audio as a +50-100% surcharge (Kling 2.6 doubles the cost, Kling 3.0 Pro adds ~46%). Default to Grok / Seedance / VEO when sound matters and you don't want to think about audio pricing.

Cost framing: resolution and duration drive cost more than model choice. A 6-second 480p Grok generation costs ~24 cr; the same prompt at 1080p Seedance 2 is ~858 cr (35x more). Pick the lowest acceptable resolution + duration first.

For I2V models: imageUrl is required. For first+last-frame models, pass endImageUrl too.

Consistent characters

If the user names a person they already have ("my Amy character"), call aetherwave_list_characters FIRST, append that character's identityBlock verbatim to the prompt, and pass their referenceImages. Do NOT use imageUrl for this - a starting frame switches the engine to first-frame mode and drops the reference images, which is the opposite of what a consistent character needs.

Writing dialogue

duration is authoritative: the engine honours the seconds you ask for to within ~0.1s and then fits the line to that length by changing pace, rather than finishing early. So write the line to the clip length - do NOT estimate the clip length from the line. Measured on a 22-clip production: ~2 words per second of clip. A words-per-minute figure from a voice description describes the character, not the engine, and budgeting by it overran by 35%.

Pass generateAudio: true for any clip with dialogue, and spell hard words the way they should be spoken ("super intelligence" rather than "superintelligence") - the engine reads the text literally and mangles unfamiliar compounds.

⚠️ A take can come back saying the WRONG WORDS and still report success. Re-rendering the identical prompt produced one clean take and one that dropped a whole sentence. For anything that will be assembled unattended, verify the rendered speech against the script before using the clip.

Ask the user only when:

  • Single generation would cost more than 100 credits and they haven't confirmed

  • They asked for "the best" with no other signal; surface 2-3 options with cost ranges

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoModeration mode for Grok Imagine. Defaults to 'normal'.
asyncNoSubmit and return a taskId IMMEDIATELY instead of waiting for the render. Video takes 1-8 minutes and most MCP clients abandon a call at 60s, so a synchronous video call usually fails from the client side even though the render succeeds. Pass true, then poll aetherwave_get_job(taskId). Strongly recommended for video.
modelNoModel ID. Defaults to 'grok-imagine-t2v'. Use list_video_models for the full list.
promptYesText description of the video scene.
durationNoDuration in seconds. Grok Imagine accepts 6-15; other models have their own ranges (see list_video_models).
imageUrlNoPublic URL of starting image. Required for I2V models.
resolutionNoOutput resolution. Default depends on model.
aspectRatioNoAspect ratio (e.g. '16:9', '9:16', '1:1').
endImageUrlNoPublic URL of ending image. Supported by some I2V models (first+last frame).
generateAudioNoRender native speech and sound WITH the video. Off by default, so a clip is SILENT unless you pass true. Free on Seedance 2.x at every resolution (measured: the sounded and silent runs bill identically) and included at base cost on Grok Imagine and VEO 3.x; Kling 2.6/3.0 surcharge for it. Pass true whenever the prompt contains dialogue - a talking head with no audio is not what the caller asked for.
referenceImagesNoUp to 9 image URLs used as identity anchors held consistent ACROSS the whole clip. THIS is the parameter for a consistent character - pass the character's referenceImages from aetherwave_list_characters. Mutually exclusive with imageUrl: a supplied first frame switches the engine to first-frame mode and DROPS these, disabling the only no-drift mechanism there is. Platform https URLs are fetched and encoded for you.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / async
      Added value: +{
+  "description": "Submit and return a taskId IMMEDIATELY instead of waiting for the render. Video takes 1-8 minutes and most MCP clients abandon a call at 60s, so a synchronous video call usually fails from the client side even though the render succeeds. Pass true, then poll aetherwave_get_job(taskId). Strongly recommended for video.",
+  "type": "boolean"
+}
    • addedInput schema / properties / generateAudio
      Added value: +{
+  "description": "Render native speech and sound WITH the video. Off by default, so a clip is SILENT unless you pass true. Free on Seedance 2.x at every resolution (measured: the sounded and silent runs bill identically) and included at base cost on Grok Imagine and VEO 3.x; Kling 2.6/3.0 surcharge for it. Pass true whenever the prompt contains dialogue - a talking head with no audio is not what the caller asked for.",
+  "type": "boolean"
+}
    • addedInput schema / properties / referenceImages
      Added value: +{
+  "description": "Up to 9 image URLs used as identity anchors held consistent ACROSS the whole clip. THIS is the parameter for a consistent character - pass the character's referenceImages from aetherwave_list_characters. Mutually exclusive with imageUrl: a supplied first frame switches the engine to first-frame mode and DROPS these, disabling the only no-drift mechanism there is. Platform https URLs are fetched and encoded for you.",
+  "items": {
+    "format": "uri",
+    "type": "string"
+  },
+  "maxItems": 9,
+  "type": "array"
+}
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

The description goes well beyond the annotations (readOnlyHint: false, openWorldHint: true, idempotentHint: false, destructiveHint: false). It discloses polling behavior (up to 8-minute budget), the async option with reasoning about client timeouts, the risk of wrong words despite success status, audio surcharge differences across models, and credit cost framing. This is rich behavioral disclosure that an agent needs to handle a long-running, fallible generation tool safely.

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?

The description is long but structured with sections and bullet points, and the core purpose is front-loaded. Most sentences add value—credit costs, fallback behavior, audio pricing, and pitfalls are all actionable. However, it includes a fairly extensive model selection guide that could arguably be condensed to shorter hints, and the cost framing examples ('35x more') are illustrative but verbose. It earns a 4 for being well-organized but slightly over-stuffed.

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?

Given the tool has 11 parameters, no output schema, and significant operational complexity, the description covers all needed aspects: return value (final video URL), async flow, polling budget, model selection, audio handling, consistent-character workflow, and dialogue writing guidelines. It also links to sibling tools like aetherwave_get_job and aetherwave_list_characters. Nothing essential for an agent to invoke this correctly is missing.

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?

Even though schema description coverage is 100%, the description adds substantial semantic depth for parameters. It explains that imageUrl is required for I2V, endImageUrl for first+last frame, referenceImages is mutually exclusive with imageUrl and drops reference images when imageUrl is supplied, generateAudio should be true for dialogue, and duration is authoritative with pace adjustment. These insights are not present in the schema and directly affect parameter selection and invocation.

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 opens with a precise statement: 'Generates a short-form video from a text prompt (T2V) or a text prompt + starting image (I2V). Submits, polls, and returns the final video URL.' This clearly identifies the verb (generate), resource (short-form video), and flow. It distinguishes from sibling tools like aetherwave_generate_image and aetherwave_edit_image by making video the explicit focus, and mentions the default model to disambiguate further.

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?

The description is exemplary on usage guidance. It provides a detailed model selection guide with explicit conditions: 'highest quality' → veo3.1-quality, 'cinematic camera moves' → seedance-pro-t2v, 'NSFW' → wan-22-nsfw-i2v, and so on. It names the alternative tool list_video_models for full lineup, and gives explicit 'ask the user only when' conditions. It also distinguishes when to use I2V vs T2V and when to call aetherwave_list_characters for consistent characters. No ambiguity remains.

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

All AetherWave Studio toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources