dialogbrain

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 are temporarily re-hosted on a third-party CDN (imgbb) for the duration of generation and deleted on completion — don't submit confidential references. Gated behind a workspace opt-in flag.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`seed`	No	Random seed for reproducibility (0-2147483647). Omit for random.
`model`	No	Video 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
`style`	No	Style preset. Seedance models only. OMIT for no style preset.
`prompt`	Yes	Text description of the video to generate (3-4000 chars).
`duration`	No	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.
`shot_type`	No	Shot mode: 'single' (continuous) or 'multi' (scene cuts). wan2.6-t2v only. OMIT to use the model default.
`resolution`	No	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.	720p
`aspect_ratio`	No	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.	16:9
`in_workspace`	No	Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
`camera_motion`	No	Camera motion preset. Seedance models only. OMIT for no camera motion.
`generate_audio`	No	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.
`negative_prompt`	No	Optional text describing what to AVOID in the output. Honored by Wan and Seedance models.
`reference_file_ids`	No	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.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 6, 2026

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"
+}

AddedSep 29, 2026
RemovedAug 1, 2026

Changed1 schema field changedJun 18, 2026

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"
+]

Changed4 schema fields changedMay 28, 2026

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."

Changed6 schema fields changedMay 26, 2026

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"
+}

Changed9 schema fields changedMay 24, 2026

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"
+}

First observedMay 17, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations: it reveals the async contract (returns immediately with a job_id, delivered via continuation), expected timing for fast vs pro models (~30-90s vs ~2-5min), and a genuine privacy caveat that reference images are re-hosted on a third-party CDN (imgbb) and deleted on completion. The confidentiality warning and gating flag are operational details an agent could not infer.

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-loaded with the core action, then progressively discloses optional inputs, the async return, and the privacy caveat. It is one dense paragraph but nearly every sentence carries decision-relevant information; only minor trimming of the timing detail would tighten it.

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 generation tool with no output schema, the description supplies everything needed to call it correctly: return contract (job_id + continuation), latency expectations, the reference-image constraints, the CDN privacy caveat, and the workspace opt-in requirement.

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 adds real meaning beyond the schema: the [ATTACHMENTS] block as the source of reference_file_ids, the number limit (12), and the confidentiality implication of submission. Other parameter nuance (models, duration, resolution) is fully documented in the schema itself.

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 (Generate) and resource (short video 5-10s) with the upstream provider named (BytePlus Seedance) and the input modality (text prompt). An agent immediately understands what this produces, and no sibling tool competes for this purpose.

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?

Explains when reference images apply ('optionally accepts up to 12 image file IDs... for style and composition') and points to the [ATTACHMENTS] block as the source. It also discloses the workspace opt-in gating, which affects whether the call succeeds. It stops short of naming explicit when-not conditions or a close alternative.

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

All dialogbrain tools Inspect

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.

videos_generate

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources