wan-mcp

speech_to_video

Create a video by animating a source image to match provided speech audio, guided by a text prompt. Returns task ID, status, and output URLs.

Instructions

Create a Wan task on RunAPI (speech to video). Returns a task id, status, and output URLs.

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": {
      "source_image_url": "<source_image_url>",
      "source_audio_url": "<source_audio_url>",
      "prompt": "<prompt>"
    },
    "name": "speech_to_video"
  }
}

Input Schema

Name	Required	Description
`seed`	No	Declared type: integer.
`wait`	No	Poll until the task reaches a terminal status.
`model`	No	RunAPI model slug for this model line.
`shift`	No	Declared type: number.
`prompt`	Yes	Declared type: string.
`num_frames`	No	Declared type: integer.
`timeout_ms`	No
`callback_url`	No	Declared type: string.
`guidance_scale`	No	Declared type: number.
`negative_prompt`	No	Declared type: string.
`poll_interval_ms`	No
`source_audio_url`	Yes	Declared type: string.
`source_image_url`	Yes	Declared type: string.
`frames_per_second`	No	Declared type: integer.
`output_resolution`	No	Declared type: string. Known values: "480p", "580p", "720p".
`num_inference_steps`	No	Declared type: integer.
`enable_safety_checker`	No	Declared type: boolean.

Schema Changelog

Changes observed during successful MCP inspections.

Changed22 schema fields changedv0.2.0Oct 7, 2026
- changedInput schema / additionalProperties
```
Previous value: -falseNew value: +{}
```
- addedInput schema / properties / callback_url / description
```
Added value: +"Declared type: string."
```
- addedInput schema / properties / enable_safety_checker / description
```
Added value: +"Declared type: boolean."
```
- addedInput schema / properties / frames_per_second / description
```
Added value: +"Declared type: integer."
```
- changedInput schema / properties / frames_per_second / type
```
Previous value: -"number"New value: +"integer"
```
- addedInput schema / properties / guidance_scale / description
```
Added value: +"Declared type: number."
```
- removedInput schema / properties / model / enum
```
Removed value: -[
-  "wan-2.2-a14b-speech-to-video-turbo"
-]
```
- addedInput schema / properties / negative_prompt / description
```
Added value: +"Declared type: string."
```
- addedInput schema / properties / num_frames / description
```
Added value: +"Declared type: integer."
```
- changedInput schema / properties / num_frames / type
```
Previous value: -"number"New value: +"integer"
```
- addedInput schema / properties / num_inference_steps / description
```
Added value: +"Declared type: integer."
```
- changedInput schema / properties / num_inference_steps / type
```
Previous value: -"number"New value: +"integer"
```
- addedInput schema / properties / output_resolution / description
```
Added value: +"Declared type: string. Known values: \"480p\", \"580p\", \"720p\"."
```
- removedInput schema / properties / output_resolution / enum
```
Removed value: -[
-  "480p",
-  "580p",
-  "720p"
-]
```
- addedInput schema / properties / poll_interval_ms / maximum
```
Added value: +9007199254740991
```
- addedInput schema / properties / prompt / description
```
Added value: +"Declared type: string."
```
- addedInput schema / properties / seed / description
```
Added value: +"Declared type: integer."
```
- changedInput schema / properties / seed / type
```
Previous value: -"number"New value: +"integer"
```
- addedInput schema / properties / shift / description
```
Added value: +"Declared type: number."
```
- addedInput schema / properties / source_audio_url / description
```
Added value: +"Declared type: string."
```
- addedInput schema / properties / source_image_url / description
```
Added value: +"Declared type: string."
```
- addedInput schema / properties / timeout_ms / maximum
```
Added value: +9007199254740991
```
Changed13 schema fields changedv0.1.9Jul 31, 2026
- addedInput schema / properties / callback_url
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / enable_safety_checker
```
Added value: +{
+  "type": "boolean"
+}
```
- addedInput schema / properties / frames_per_second
```
Added value: +{
+  "type": "number"
+}
```
- addedInput schema / properties / guidance_scale
```
Added value: +{
+  "type": "number"
+}
```
- addedInput schema / properties / negative_prompt
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / num_frames
```
Added value: +{
+  "type": "number"
+}
```
- addedInput schema / properties / num_inference_steps
```
Added value: +{
+  "type": "number"
+}
```
- addedInput schema / properties / prompt / type
```
Added value: +"string"
```
- addedInput schema / properties / seed
```
Added value: +{
+  "type": "number"
+}
```
- addedInput schema / properties / shift
```
Added value: +{
+  "type": "number"
+}
```
- addedInput schema / properties / source_audio_url / type
```
Added value: +"string"
```
- addedInput schema / properties / source_image_url / type
```
Added value: +"string"
```
- addedInput schema / required
```
Added value: +[
+  "source_image_url",
+  "source_audio_url",
+  "prompt"
+]
```
First observedv0.1.6Jul 13, 2026

TDQS

C2.9/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose the return shape (task id, status, output URLs), which is useful, but says nothing about async/long-running generation, polling behavior implied by the 'wait' default, timeouts, cost, or auth requirements for the RunAPI call.

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

Conciseness5/5

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

Two short sentences, front-loaded with the action and immediately followed by the return shape. Nothing is padded or redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 17-parameter media-generation tool with no annotations and no output schema, the description is too thin. It should cover the async task lifecycle, polling/timeout semantics, and the fact that generated video output is the payoff, none of which appear.

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 88%, so the schema itself already documents the parameters and the baseline is 3. The description adds no parameter meaning at all – notably it doesn't mention that both a source image and a source audio URL are required.

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 specific verb and resource – 'Create a Wan task ... (speech to video)' – and the parenthetical modality distinguishes it from image_to_video and text_to_video. However it never says what inputs drive the generation (image + audio), leaving the agent to infer the distinction from the schema rather than the description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance and no reference to any alternative sibling tool. An agent cannot tell from the description why it would pick speech_to_video over animate or image_to_video.

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

Deploy Server