Skip to main content
Glama

videos_generate

Generate a short video (5-10s) from a text prompt using BytePlus Seedance. Optionally accepts up to 12 image file IDs from the user's attached files (visible in the [ATTACHMENTS] block) as reference_file_ids for style and composition. Returns immediately with a job_id; the video is delivered back via continuation when the job completes (~30-90s for fast model, ~2-5min for pro). Reference images reach the video provider through short-lived signed links — don't submit confidential references. Seedance runs on the workspace's own GEngen or BytePlus key when one is set in Settings → API keys (no credits charged); otherwise it needs the workspace video opt-in and credits.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "videos_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNoRandom seed for reproducibility (0-2147483647). Omit for random.
modelNoVideo model. 'wan2.6-i2v-flash' (default, cheap, 720p/1080p, optional audio), 'wan2.6-i2v' (premium, always-on audio), 'wan2.6-t2v' (text-only input, 720p/1080p, no audio), 'wan2.2-i2v-flash' (cheapest, 480p/720p, no audio). Legacy BytePlus: 'seedance-2-fast', 'seedance-2-pro' (720p only).wan2.6-i2v-flash
styleNoStyle preset. Seedance models only. OMIT for no style preset.
promptYesText description of the video to generate (3-4000 chars).
durationNoOutput video duration in seconds. Single-clip: 5 or 10. Long-form (chained, i2v models only): 15, 20, 30, 45, or 60. Long-form videos are silent (no audio in v1) and use only reference_file_ids[0] when refs are provided.
shot_typeNoShot mode: 'single' (continuous) or 'multi' (scene cuts). wan2.6-t2v only. OMIT to use the model default.
resolutionNoOutput resolution. '720p' is the safe default; '1080p' is wan2.6 only; '480p' is wan2.2-i2v-flash only. Per-model support enforced by validation.720p
aspect_ratioNoOutput aspect ratio. Wan supports '16:9', '9:16', '1:1'; Seedance also supports '4:3', '3:4', '21:9'. Per-model support enforced by validation.16:9
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
camera_motionNoCamera motion preset. Seedance models only. OMIT for no camera motion.
generate_audioNoWhether the model should produce native audio. For wan2.6-i2v-flash this doubles the per-second rate (e.g., 720p+audio is $0.05/s vs $0.025/s silent) — set False for cheaper silent clips. wan2.6-i2v always produces audio regardless of this flag. wan2.6-t2v / wan2.2-i2v-flash / seedance-2-fast never produce audio.
negative_promptNoOptional text describing what to AVOID in the output. Honored by Wan and Seedance models.
reference_file_idsNoOptional list of up to 12 image file_ids to use as visual references (style, composition). Files must be image MIME types (image/png, image/jpeg, image/webp, image/gif). Get IDs from the [ATTACHMENTS] block, files.search, or search.files.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / in_workspace
      Added value: +{
      +  "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
      +  "type": "integer"
      +}
  2. Added
  3. Removed
  4. Changed1 schema field changed
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "wan2.6-i2v-flash",
      -  "wan2.6-i2v",
      -  "wan2.6-t2v",
      -  "wan2.2-i2v-flash",
      -  "seedance-2-pro"
      -]New value: +[
      +  "wan2.6-i2v-flash",
      +  "wan2.6-i2v",
      +  "wan2.6-t2v",
      +  "wan2.2-i2v-flash",
      +  "happyhorse-1.0-t2v",
      +  "happyhorse-1.0-i2v",
      +  "wan2.2-s2v",
      +  "omnihuman-1.5",
      +  "seedance-2-pro"
      +]
  5. Changed4 schema fields changed
    • changedInput schema / properties / camera_motion / description
      Previous value: -"Camera motion preset. Seedance models only."New value: +"Camera motion preset. Seedance models only. OMIT for no camera motion."
    • changedInput schema / properties / reference_file_ids / description
      Previous value: -"Optional list of up to 12 image file_ids to use as visual references (style, composition). Files must be image MIME types (image/png, image/jpeg, image/webp, image/gif). Get IDs from the [ATTACHMENTS] block, files.search, or workspace.search."New value: +"Optional list of up to 12 image file_ids to use as visual references (style, composition). Files must be image MIME types (image/png, image/jpeg, image/webp, image/gif). Get IDs from the [ATTACHMENTS] block, files.search, or search.files."
    • changedInput schema / properties / shot_type / description
      Previous value: -"Shot mode: 'single' (continuous) or 'multi' (scene cuts). wan2.6-t2v only."New value: +"Shot mode: 'single' (continuous) or 'multi' (scene cuts). wan2.6-t2v only. OMIT to use the model default."
    • changedInput schema / properties / style / description
      Previous value: -"Style preset. Seedance models only."New value: +"Style preset. Seedance models only. OMIT for no style preset."
  6. Changed6 schema fields changed
    • addedInput schema / properties / camera_motion
      Added value: +{
      +  "description": "Camera motion preset. Seedance models only.",
      +  "enum": [
      +    "dolly_in",
      +    "dolly_out",
      +    "pan_left",
      +    "pan_right",
      +    "zoom_in",
      +    "zoom_out",
      +    "static"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "wan2.6-i2v-flash",
      -  "wan2.6-i2v",
      -  "wan2.6-t2v",
      -  "wan2.2-i2v-flash",
      -  "seedance-2-fast",
      -  "seedance-2-pro"
      -]New value: +[
      +  "wan2.6-i2v-flash",
      +  "wan2.6-i2v",
      +  "wan2.6-t2v",
      +  "wan2.2-i2v-flash",
      +  "seedance-2-pro"
      +]
    • changedInput schema / properties / negative_prompt / description
      Previous value: -"Optional text describing what to AVOID in the output. Honored by Wan models; rejected for Seedance (which doesn't accept negative prompts)."New value: +"Optional text describing what to AVOID in the output. Honored by Wan and Seedance models."
    • addedInput schema / properties / seed
      Added value: +{
      +  "description": "Random seed for reproducibility (0-2147483647). Omit for random.",
      +  "type": "integer"
      +}
    • addedInput schema / properties / shot_type
      Added value: +{
      +  "description": "Shot mode: 'single' (continuous) or 'multi' (scene cuts). wan2.6-t2v only.",
      +  "enum": [
      +    "single",
      +    "multi"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / style
      Added value: +{
      +  "description": "Style preset. Seedance models only.",
      +  "enum": [
      +    "cinematic",
      +    "anime",
      +    "realistic",
      +    "3d_render"
      +  ],
      +  "type": "string"
      +}
  7. Changed9 schema fields changed
    • changedInput schema / properties / aspect_ratio / description
      Previous value: -"Output aspect ratio."New value: +"Output aspect ratio. Wan supports '16:9', '9:16', '1:1'; Seedance also supports '4:3', '3:4', '21:9'. Per-model support enforced by validation."
    • changedInput schema / properties / aspect_ratio / enum
      Previous value: -[
      -  "16:9",
      -  "9:16",
      -  "4:3",
      -  "3:4",
      -  "21:9"
      -]New value: +[
      +  "16:9",
      +  "9:16",
      +  "1:1",
      +  "4:3",
      +  "3:4",
      +  "21:9"
      +]
    • changedInput schema / properties / duration / description
      Previous value: -"Output video duration in seconds. Must be 5 or 10. 10s costs 2x the 5s price."New value: +"Output video duration in seconds. Single-clip: 5 or 10. Long-form (chained, i2v models only): 15, 20, 30, 45, or 60. Long-form videos are silent (no audio in v1) and use only reference_file_ids[0] when refs are provided."
    • changedInput schema / properties / generate_audio / description
      Previous value: -"Whether the model should produce native audio (Pro only — Fast ignores the flag)."New value: +"Whether the model should produce native audio. For wan2.6-i2v-flash this doubles the per-second rate (e.g., 720p+audio is $0.05/s vs $0.025/s silent) — set False for cheaper silent clips. wan2.6-i2v always produces audio regardless of this flag. wan2.6-t2v / wan2.2-i2v-flash / seedance-2-fast never produce audio."
    • changedInput schema / properties / model / default
      Previous value: -"seedance-2-fast"New value: +"wan2.6-i2v-flash"
    • changedInput schema / properties / model / description
      Previous value: -"Seedance model variant. 'seedance-2-fast' (~30-90s, lower cost) or 'seedance-2-pro' (~2-5min, cinematic quality, native audio). Default: 'seedance-2-fast'."New value: +"Video model. Recommended: 'wan2.6-i2v-flash' (default, cheap, 720p/1080p, optional audio), 'wan2.6-i2v' (premium, always-on audio), 'wan2.6-t2v' (text-only input, 720p/1080p, no audio), 'wan2.2-i2v-flash' (cheapest, 480p/720p, no audio). Legacy BytePlus: 'seedance-2-fast', 'seedance-2-pro' (720p only)."
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "seedance-2-fast",
      -  "seedance-2-pro"
      -]New value: +[
      +  "wan2.6-i2v-flash",
      +  "wan2.6-i2v",
      +  "wan2.6-t2v",
      +  "wan2.2-i2v-flash",
      +  "seedance-2-fast",
      +  "seedance-2-pro"
      +]
    • addedInput schema / properties / negative_prompt
      Added value: +{
      +  "description": "Optional text describing what to AVOID in the output. Honored by Wan models; rejected for Seedance (which doesn't accept negative prompts).",
      +  "type": "string"
      +}
    • addedInput schema / properties / resolution
      Added value: +{
      +  "default": "720p",
      +  "description": "Output resolution. '720p' is the safe default; '1080p' is wan2.6 only; '480p' is wan2.2-i2v-flash only. Per-model support enforced by validation.",
      +  "enum": [
      +    "480p",
      +    "720p",
      +    "1080p"
      +  ],
      +  "type": "string"
      +}
  8. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations only declare the mutation/idempotency profile; the description adds the crucial behavior the agent needs: returns immediately with a job_id, delivery via continuation, ~30-90s vs ~2-5min latency per model, and the confidentiality caveat that reference images travel through short-lived signed links. The billing inset ('runs on the workspace's own key ... otherwise needs the workspace video opt-in and credits') is exactly the kind of cost/precondition disclosure annotations cannot carry.

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?

Front-loads purpose and the async return model, then layers privacy and billing caveats; every sentence carries operational weight. The final billing sentence is dense and grabs several facts at once, but nothing is redundant with the annotations or schema.

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 an async, 13-parameter, no-output-schema generation tool, the description covers what an agent most needs: that the call does not return the artifact directly, how the result is delivered, expected latency, and the cost/permission preconditions. Nothing essential for correct invocation is missing.

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% and per-parameter docs are already rich (model tradeoffs, duration tiers, resolution support, audio pricing), so the schema does the heavy lifting. The description adds only the reference_file_ids sourcing detail, which is already present in the schema text; it contributes no additional meaning for seed, duration, or model selection.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource ('Generate a short video ... from a text prompt') and names the provider, so the agent knows this is a text-to-video (plus optional reference-image) generation tool. The framing is slightly narrower than reality: it says 'BytePlus Seedance' and '5-10s' while the schema defaults to a Wan model and supports 15-60s chained output, so the opening line is not fully accurate about scope.

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?

Gives clear conditions for the optional reference-image path ('up to 12 image file IDs from the user's attached files (visible in the [ATTACHMENTS] block)'), plus model/cost steering ('set False for cheaper silent clips'). It does not route the agent between this and a sibling like images_generate, nor state any when-not-to-use case beyond the confidentiality caution.

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.