Skip to main content
Glama

Runway MCP Server by useapi.net (third-party)

Lip sync a face

runway_lipsync

Make the face in an image or video asset speak: either an audio asset, or voice_text read by one of Runway's voices (voiceId from runway_list_lipsync_voices). Give exactly one of image_assetId / video_assetId and exactly one of audio_assetId / voiceId. To swap the voice of a whole video use runway_act_two_voice. Waits up to ~50 s, then returns the video url and assetId, the failure reason or the taskId for runway_get_task. Uses credits, or none with exploreMode. POST /lipsync/create.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "runway_lipsync"
  }
}

Input Schema

NameRequiredDescriptionDefault
waitNoWait up to ~50 s for the task to finish (default true); false returns the taskId at once.
maxJobsNoOverride the account's maxJobs (Runway tasks at once) for this request, 1-10. Default: the account's own setting.
voiceIdNoA Runway voice (voiceId from runway_list_lipsync_voices) that reads voice_text; instead of audio_assetId.
model_idNoThe voice model, only with voiceId: eleven_multilingual_v1 (default) or eleven_multilingual_v2 (28+ languages).
replyRefNoYour own reference id, stored and returned with the task.
replyUrlNoA callback URL the API calls with the task (the runway_get_task shape) when it completes or fails. Default: the replyUrl of your useapi.net account.
voice_textNoThe text the voice reads; required with voiceId and only used with it.
exploreModeNoExplore Mode: true spends no credits and runs at lower priority; only for accounts on a Runway Unlimited plan. Omit or false: Credits Mode.
audio_assetIdNoaudio_assetId, the speech to sync to (or use voiceId with voice_text): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts). The task runs on the Runway account that holds the asset.
image_assetIdNoimage_assetId, the face image (or use video_assetId): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts). The task runs on the Runway account that holds the asset.
video_assetIdNovideo_assetId, the face video (or use image_assetId): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts). The task runs on the Runway account that holds the asset.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.7/5.0
Behavior4/5

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

Beyond the annotations (which only say it is a non-read-only, non-idempotent, open-world call), the description discloses the ~50 s wait, the dual return shapes (result vs. taskId for runway_get_task), the failure-reason return, and that calls consume credits unless exploreMode is set. These are exactly the operational traits annotations cannot express. It does not mention permission or asset-ownership implications explicitly beyond the 'account that holds the asset' note in the schema.

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?

Front-loaded with the purpose, then constraints, then the sibling routing, then async/return behavior, then cost. Every clause carries information an agent needs before calling; there is no filler or restatement of the tool name.

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 11-parameter async generation tool with no output schema, the description covers the missing pieces: return values, the taskId handoff path, the wait window, and cost behavior. An agent has enough to invoke it correctly and interpret the response without further context.

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 would be 3, but the description adds real semantics the schema cannot encode: the mutual-exclusion constraint between image_assetId/video_assetId and between audio_assetId/voiceId, which matters because no parameters are marked required. It also clarifies the credits-vs-exploreMode tradeoff, going beyond the schema's per-property text.

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?

Opens with a concrete verb and resource: "Make the face in an image or video asset speak," then enumerates the two input modes (audio asset vs. voice_text/voiceId). It explicitly distinguishes itself from the sibling runway_act_two_voice, so an agent can separate the two without opening either 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?

States hard selection rules — "exactly one of image_assetId / video_assetId and exactly one of audio_assetId / voiceId" — and names the alternative tool with its selecting condition ("To swap the voice of a whole video use runway_act_two_voice"). It also names runway_list_lipsync_voices as the prerequisite for obtaining a voiceId.

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.

Resources