Skip to main content
Glama

Generate Video

clipform_generate_video
Destructive

Generate a video from images, video clips, or both, synced to an audio track. Use this for narrated question backgrounds, topic visualisations, or any form node that benefits from video. Combine with clipform_generate_tts for narrated audio and clipform_search_media for royalty-free images. Creates 9:16 (720x1280) with Ken Burns pan/zoom effects and transitions. Returns a public URL when complete.

Items: type "image" (Ken Burns motion) or "video" (cover-cropped, muted by default). Duration matches audio_url or set duration_seconds explicitly.

For multi-question builds, pass wait: false on every render: each call returns a job ID immediately, so all renders run in parallel - then collect URLs with clipform_check_render. Sequential waiting renders take 15-120 seconds EACH.

Choosing a render tool: for a recognisable form/quiz beat (guess-the-city, this-or-that, mystery reveal, multiple choice, photo montage...) reach for a video template first (clipform_list_video_templates + clipform_render_video_template) - it is a one-call recipe. Use clipform_generate_video for a narrated or audio-synced media montage (images/clips timed to a voice track). Use clipform_render_composition only when neither fits and you need a custom layer stack. Montage disambiguation: choose clipform_generate_video when the montage is narrated or synced to an audio track; choose the slideshow video template when it is silent (motion + transitions only, no voice-over). A render for a form node is not done until it is attached to that node. Pass node_id (and form_id) so the completed render attaches itself automatically - do not poll clipform_check_render to completion or manually chain clipform_upload_media_asset + clipform_attach_node_media; fire the render and move on.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
waitNotrue (default) blocks until the video is ready and returns its URL. false returns a job ID immediately - fire all renders first, then poll clipform_check_render. Use false whenever rendering more than one video.
itemsYesMedia items (images, video clips, or a mix)
presetNoNamed look driving transition + motion + colour treatment together (default: 'clean'). One of: clean, editorial, punchy, bold-poster. The advanced fields below (transition, style_preset, texture, duotone, background_color, per-item effect) override individual pieces of the chosen look when set.clean
contextYesDescribe the user's underlying goal in one sentence - not the tool you're calling.
duotoneNoAdvanced override: two-tone editorial recolour on image items, overriding the preset look's own duotone - desaturates then maps to a shadow->highlight palette. Pair with a halftone texture for a screen-print poster look.
form_idNoThe form UUID (required when node_id is set).
node_idNoForm node to attach this render to automatically once it completes - skips the manual clipform_upload_media_asset + clipform_attach_node_media steps and republishes the form if it's currently live. Requires form_id.
textureNoAdvanced override: print-style pattern overlay on image items, overriding the preset look's own texture - makes stock imagery read as designed (screen-print dither look)
captionsNoWord-level captions from clipform_generate_tts - carried onto the attached media asset. Only used when node_id is set.
audio_urlNoAudio track URL. Video duration matches audio duration.
transitionNoAdvanced: overrides the preset look's transition
style_presetNoAdvanced override: a raw Ken Burns motion preset, overriding the preset look's own motion.
random_effectsNoShuffle Ken Burns effects across image items (default: true)
background_colorNoAdvanced override: background color, overriding the preset look's own background (default '#000')
duration_secondsNoVideo duration in seconds (required if no audio_url)
background_audio_urlNoAmbience/music bed under the narration (crowd noise, room tone). Loops to fill the video. Find tracks with clipform_search_music.
background_audio_volumeNoBackground bed volume 0-1 (default 0.15 - sits under speech)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
job_idNoPresent when status is 'rendering' - pass to check_render
statusYes'rendering' when wait:false (poll check_render); 'complete' with a public_url when wait:true
attachedNoTrue when node_id was provided and the render was attached to the node automatically (present once the attach outcome is known).
public_urlNoPresent when status is 'complete' - attach via upload_media_asset then attach_node_media (fit_media: true), unless node_id was set (auto-attached)
republishedNoTrue when the form was live and was republished to include this media.
attach_errorNoPresent when node_id was provided but auto-attach failed - the render itself still succeeded.
media_asset_idNoThe workspace media asset created from this render, when attached.
duration_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changed
    • changedInput schema / properties / background_color / description
      Previous value: -"Background color (default '#000')"New value: +"Advanced override: background color, overriding the preset look's own background (default '#000')"
    • changedInput schema / properties / duotone / description
      Previous value: -"Two-tone editorial recolour on image items - desaturates then maps to a shadow->highlight palette. Pair with a halftone texture for a screen-print poster look."New value: +"Advanced override: two-tone editorial recolour on image items, overriding the preset look's own duotone - desaturates then maps to a shadow->highlight palette. Pair with a halftone texture for a screen-print poster look."
    • changedInput schema / properties / items / items / properties / effect / description
      Previous value: -"Ken Burns effect (image only): pan-left, pan-right, pan-up, pan-down, zoom-in-pan-left, zoom-in-pan-right, zoom-in, zoom-out, static, random"New value: +"Advanced override: a specific Ken Burns effect (image only), overriding the preset look's own effect choice"
    • addedInput schema / properties / items / items / properties / effect / enum
      Added value: +[
      +  "pan-left",
      +  "pan-right",
      +  "pan-up",
      +  "pan-down",
      +  "zoom-in-pan-left",
      +  "zoom-in-pan-right",
      +  "zoom-in",
      +  "zoom-out",
      +  "static",
      +  "random"
      +]
    • addedInput schema / properties / preset
      Added value: +{
      +  "default": "clean",
      +  "description": "Named look driving transition + motion + colour treatment together (default: 'clean'). One of: clean, editorial, punchy, bold-poster. The advanced fields below (transition, style_preset, texture, duotone, background_color, per-item effect) override individual pieces of the chosen look when set.",
      +  "enum": [
      +    "clean",
      +    "editorial",
      +    "punchy",
      +    "bold-poster"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / style_preset / description
      Previous value: -"Ken Burns style preset: cinematic, dramatic, calm, documentary, dreamy, moody, energetic"New value: +"Advanced override: a raw Ken Burns motion preset, overriding the preset look's own motion."
    • changedInput schema / properties / texture / description
      Previous value: -"Print-style pattern overlay on image items - makes stock imagery read as designed (screen-print dither look)"New value: +"Advanced override: print-style pattern overlay on image items, overriding the preset look's own texture - makes stock imagery read as designed (screen-print dither look)"
    • addedInput schema / properties / transition / description
      Added value: +"Advanced: overrides the preset look's transition"
    • removedInput schema / properties / transition / properties / duration / default
      Removed value: -1
    • changedInput schema / properties / transition / properties / duration / description
      Previous value: -"Transition duration in seconds (default: 1)"New value: +"Advanced override: transition duration in seconds"
    • removedInput schema / properties / transition / properties / type / default
      Removed value: -"fade"
    • changedInput schema / properties / transition / properties / type / description
      Previous value: -"Transition: fade, fadeblack, fadewhite, slideleft, slideright, circlecrop, circleopen, circleclose, dissolve, pixelize, radial, smoothleft, smoothright, wipeleft, wiperight, diagtl, diagbr, hblur"New value: +"Advanced override: fade, slide, wipe, none - overrides the preset look's own transition"
    • addedInput schema / properties / transition / properties / type / enum
      Added value: +[
      +  "fade",
      +  "slide",
      +  "wipe",
      +  "none"
      +]
  2. Changed3 schema fields changed
    • changedInput schema / properties / captions / items / properties / words / description
      Previous value: -"Per-word timestamps within the segment"New value: +"Per-word timestamps within the segment. Required - copy the full array from clipform_generate_tts verbatim."
    • addedInput schema / properties / captions / items / properties / words / minItems
      Added value: +1
    • changedInput schema / properties / captions / items / required
      Previous value: -[
      -  "start",
      -  "end",
      -  "text"
      -]New value: +[
      +  "start",
      +  "end",
      +  "text",
      +  "words"
      +]
  3. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / context
      Added value: +{
      +  "description": "Describe the user's underlying goal in one sentence - not the tool you're calling.",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "items"
      -]New value: +[
      +  "items",
      +  "context"
      +]
  4. Changed8 schema fields changed
    • addedInput schema / properties / captions
      Added value: +{
      +  "description": "Word-level captions from clipform_generate_tts - carried onto the attached media asset. Only used when node_id is set.",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "end": {
      +        "description": "Segment end time in seconds",
      +        "type": "number"
      +      },
      +      "start": {
      +        "description": "Segment start time in seconds",
      +        "type": "number"
      +      },
      +      "text": {
      +        "description": "Full segment text",
      +        "type": "string"
      +      },
      +      "words": {
      +        "description": "Per-word timestamps within the segment",
      +        "items": {
      +          "additionalProperties": false,
      +          "properties": {
      +            "end": {
      +              "type": "number"
      +            },
      +            "start": {
      +              "type": "number"
      +            },
      +            "word": {
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "word",
      +            "start",
      +            "end"
      +          ],
      +          "type": "object"
      +        },
      +        "type": "array"
      +      }
      +    },
      +    "required": [
      +      "start",
      +      "end",
      +      "text"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / form_id
      Added value: +{
      +  "description": "The form UUID (required when node_id is set).",
      +  "format": "uuid",
      +  "type": "string"
      +}
    • addedInput schema / properties / node_id
      Added value: +{
      +  "description": "Form node to attach this render to automatically once it completes - skips the manual clipform_upload_media_asset + clipform_attach_node_media steps and republishes the form if it's currently live. Requires form_id.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / attach_error
      Added value: +{
      +  "description": "Present when node_id was provided but auto-attach failed - the render itself still succeeded.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / attached
      Added value: +{
      +  "description": "True when node_id was provided and the render was attached to the node automatically (present once the attach outcome is known).",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / media_asset_id
      Added value: +{
      +  "description": "The workspace media asset created from this render, when attached.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / public_url / description
      Previous value: -"Present when status is 'complete' - attach via upload_media_asset then attach_node_media (fit_media: true)"New value: +"Present when status is 'complete' - attach via upload_media_asset then attach_node_media (fit_media: true), unless node_id was set (auto-attached)"
    • addedOutput schema / properties / republished
      Added value: +{
      +  "description": "True when the form was live and was republished to include this media.",
      +  "type": "boolean"
      +}
  5. Changed1 schema field changed
    • changedOutput schema / properties / public_url / description
      Previous value: -"Present when status is 'complete' - attach via upload_node_media (fit_media: true)"New value: +"Present when status is 'complete' - attach via upload_media_asset then attach_node_media (fit_media: true)"
  6. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": false,
      +  "properties": {
      +    "duration_seconds": {
      +      "type": "number"
      +    },
      +    "job_id": {
      +      "description": "Present when status is 'rendering' - pass to check_render",
      +      "type": "string"
      +    },
      +    "public_url": {
      +      "description": "Present when status is 'complete' - attach via upload_node_media (fit_media: true)",
      +      "type": "string"
      +    },
      +    "status": {
      +      "description": "'rendering' when wait:false (poll check_render); 'complete' with a public_url when wait:true",
      +      "enum": [
      +        "rendering",
      +        "complete"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "status"
      +  ],
      +  "type": "object"
      +}
  7. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag a destructive, non-idempotent, open-world write, and the description adds substantial context on top: fixed 9:16 720x1280 output, Ken Burns motion, public URL return, 15-120s per sequential render, and that passing node_id/form_id auto-attaches and republishes a live form. This is real behavioral disclosure beyond the annotation flags.

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 purpose is front-loaded and every section carries signal, but the parallel-render advice is restated in both the main body and elsewhere, making it somewhat denser than necessary. Structure is otherwise clean and scannable.

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 17-parameter, nested-schema, output-schema-bearing tool, the description covers the workflow (generate, check, attach), the alternatives, and the cost characteristics. Nothing an agent needs to call this correctly appears to be 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 baseline is 3, but the description goes further by explaining orchestration semantics for wait (fire all renders, then poll clipform_check_render), the auto-attach behavior of node_id/form_id, and the media-type distinction for items. It reinforces rather than merely repeats the schema.

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 ('Generate a video from images, video clips, or both, synced to an audio track') and explicitly distinguishes itself from the two sibling render tools. An agent can identify exactly what this produces without opening the 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?

Contains a dedicated 'Choosing a render tool' block that gives when-to-use for this tool versus clipform_render_video_template and clipform_render_composition, plus a montage disambiguation rule (narrated/audio-synced here vs silent slideshow template). It also prescribes wait:false for multi-question builds and warns against polling to completion.

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.