Skip to main content
Glama

generate_audio_track

Generate AI audio and place it on the edit timeline. Match sourceDuration and modelSettings to the approved quote, pass maxCostUsd and a stable idempotencyKey. Retries reuse the media and original attachment, preserving subsequent timeline edits.

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": {
      "workspaceId": "<workspaceId>",
      "editId": "<editId>",
      "prompt": "<prompt>"
    },
    "name": "generate_audio_track"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoAudio model ID
editIdYesThe edit ID
promptYesTTS/music/SFX prompt
volumeNoInitial volume
voiceIdNoVoice ID for TTS models
durationNoPlaceholder timeline duration until generation metadata updates
startTimeNoTimeline start time in seconds
approvalIdNoCombined production approval ID returned by set_proposal_status.
fadeInTimeNoFade-in length in seconds
maxCostUsdNoMaximum charge for each output. Checked against authoritative pricing before generation.
autoChannelNoPick the first non-overlapping channel automatically
fadeOutTimeNoFade-out length in seconds
stylePromptNoDelivery and accent direction for supported speech models
workspaceIdYesThe workspace ID
approvalJobIdNoExact production jobId covered by that combined approval.
modelSettingsNoModel-specific controls using keys and options from get_model_catalog inputConstraints.slots or variantSelector.
idempotencyKeyNoStable request key. Retries with the same key reuse the existing output and do not start another paid generation.
pinnedToShotIdNoOptional shot ID to pin this audio to
sourceDurationNoGenerated audio source duration in seconds, separate from timeline duration. Match the approved quote.
relativeStartTimeNoOffset in seconds from pinned shot start

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / approvalId
      Added value: +{
      +  "description": "Combined production approval ID returned by set_proposal_status.",
      +  "type": "string"
      +}
    • addedInput schema / properties / approvalJobId
      Added value: +{
      +  "description": "Exact production jobId covered by that combined approval.",
      +  "type": "string"
      +}
    • addedInput schema / properties / idempotencyKey
      Added value: +{
      +  "description": "Stable request key. Retries with the same key reuse the existing output and do not start another paid generation.",
      +  "maxLength": 250,
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / maxCostUsd
      Added value: +{
      +  "description": "Maximum charge for each output. Checked against authoritative pricing before generation.",
      +  "maximum": 10000,
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / modelSettings
      Added value: +{
      +  "additionalProperties": {
      +    "anyOf": [
      +      {
      +        "type": "string"
      +      },
      +      {
      +        "type": "number"
      +      },
      +      {
      +        "type": "boolean"
      +      }
      +    ]
      +  },
      +  "description": "Model-specific controls using keys and options from get_model_catalog inputConstraints.slots or variantSelector.",
      +  "type": "object"
      +}
    • addedInput schema / properties / sourceDuration
      Added value: +{
      +  "description": "Generated audio source duration in seconds, separate from timeline duration. Match the approved quote.",
      +  "exclusiveMinimum": 0,
      +  "maximum": 3600,
      +  "type": "number"
      +}
  2. First observed

TDQS

A3.6/5.0
Behavior4/5

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

With zero annotations the description carries the full burden and does real work: it discloses that this is a paid generation gated by an approved quote, that maxCostUsd is a hard ceiling, and — most valuably — that retries reuse the existing media and original attachment so subsequent timeline edits are preserved. It stops short of saying whether generation is asynchronous, what a failure costs, or what the call returns.

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?

Three front-loaded sentences with no filler; the action and its timeline side effect come first, then the contractual requirements. The second sentence is telegraphic ('pass maxCostUsd and a stable idempotencyKey') without saying why the key matters, which costs a little clarity for the compression.

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

Completeness3/5

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

For a 20-parameter mutation with no annotations, no output schema, and a nested modelSettings object, the description covers the critical path — approval matching, cost cap, idempotency, retry semantics — but is silent on what the call returns (job vs. finished asset), whether it is async, and how autoChannel, pinning, volume, or fades behave. The most consequential omission is the return/follow-up contract, which nothing else in the definition supplies.

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%, so every parameter is already documented, and much of the description's parameter guidance (sourceDuration matching the quote, idempotencyKey reuse, maxCostUsd as a cap) restates what the schema already says. It adds a light cross-parameter constraint by grouping sourceDuration with modelSettings against the quote, but nothing about the 20 params is otherwise under-explained.

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 ('Generate AI audio') plus a concrete side effect ('place it on the edit timeline'), which separates it from a pure add_audio_track-style operation. It does not explicitly name the sibling it supersedes, so an agent must infer the boundary from the placement wording.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the agent learns it must match sourceDuration/modelSettings to an approved quote and supply maxCostUsd and an idempotencyKey, which signals a post-approval paid-generation workflow. There is no explicit 'use this instead of X when…' routing against generate_audio, generate_video_audio, or add_audio_track.

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.