Skip to main content
Glama

Generate Voiceover

generation_voiceover_create
DestructiveIdempotent

Queue a text-to-speech voiceover into the BlitzReels media library. Spends AI credits and returns a job to poll with generation_jobs_get.

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": {
      "text": "<text>"
    },
    "name": "generation_voiceover_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesScript to read aloud (3-8000 characters).
speedNoSpeaking rate between 0.5 and 1.6.
voiceIdNoCatalog voice ID (generation_options_list with kind voiceover) or a workspace voice ID (voices_list), such as a cloned voice.pNInz6obpgDQGcFmaJgB
voiceStyleNoDelivery emotion.neutral
workspaceIdNoOptional workspace ID. Defaults to the user's default workspace. UUID string.
idempotencyKeyNoRetry key. Reuse only with identical inputs.

Output Schema

NameRequiredDescriptionDefault
generationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / generation / properties / app_url
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / voiceId / description
      Previous value: -"Voice ID. Call generation_options_list with kind voiceover for the catalog."New value: +"Catalog voice ID (generation_options_list with kind voiceover) or a workspace voice ID (voices_list), such as a cloned voice."
    • removedInput schema / properties / voiceId / enum
      Removed value: -[
      -  "pNInz6obpgDQGcFmaJgB",
      -  "TX3LPaxmHKxFdv7VOQHJ",
      -  "FGY2WhTYpPnrIDTdsKH5",
      -  "IKne3meq5aSn9XLyUdCD",
      -  "cgSgspJ2msm6clMCkdW9",
      -  "bIHbv24MWmeRgasZH58o",
      -  "nPczCjzI2devNBz1zQrb",
      -  "JBFqnCBsd6RMkjVDRZzb",
      -  "SOYHLrjzK2X1ezoPC6cr",
      -  "N2lVS1w4EtoT3dr4eOWO",
      -  "S9EGwlCtMF7VXtENq79v",
      -  "VhxAIIZM8IRmnl5fyeyk",
      -  "hpp4J3VqNfWAUOO0d1Us",
      -  "EXAVITQu4vr4xnSDxMaL",
      -  "pFZP5JQG7iQjIQuC4Bku",
      -  "SAz9YHcvj6GT2YYXdXww",
      -  "Xb7hH8MSUJpSbSDYk0k2",
      -  "XrExE9yKIg1WjnnlVkGX",
      -  "onwK4e9ZLuTAKqWW03F9",
      -  "pqHfZKP75CvOlQylNhV4",
      -  "CwhRBWXzGAHq8TQ4Fs17",
      -  "cjVigY5qzO86Huf0OWal",
      -  "iP95p4xoKVk53GoZ742B"
      -]
  3. Changed2 schema fields changed
    • changedInput schema / properties / voiceId / default
      Previous value: -nullNew value: +"pNInz6obpgDQGcFmaJgB"
    • addedInput schema / properties / voiceId / enum
      Added value: +[
      +  "pNInz6obpgDQGcFmaJgB",
      +  "TX3LPaxmHKxFdv7VOQHJ",
      +  "FGY2WhTYpPnrIDTdsKH5",
      +  "IKne3meq5aSn9XLyUdCD",
      +  "cgSgspJ2msm6clMCkdW9",
      +  "bIHbv24MWmeRgasZH58o",
      +  "nPczCjzI2devNBz1zQrb",
      +  "JBFqnCBsd6RMkjVDRZzb",
      +  "SOYHLrjzK2X1ezoPC6cr",
      +  "N2lVS1w4EtoT3dr4eOWO",
      +  "S9EGwlCtMF7VXtENq79v",
      +  "VhxAIIZM8IRmnl5fyeyk",
      +  "hpp4J3VqNfWAUOO0d1Us",
      +  "EXAVITQu4vr4xnSDxMaL",
      +  "pFZP5JQG7iQjIQuC4Bku",
      +  "SAz9YHcvj6GT2YYXdXww",
      +  "Xb7hH8MSUJpSbSDYk0k2",
      +  "XrExE9yKIg1WjnnlVkGX",
      +  "onwK4e9ZLuTAKqWW03F9",
      +  "pqHfZKP75CvOlQylNhV4",
      +  "CwhRBWXzGAHq8TQ4Fs17",
      +  "cjVigY5qzO86Huf0OWal",
      +  "iP95p4xoKVk53GoZ742B"
      +]
  4. Changed1 schema field changed
    • changedInput schema / properties / voiceId / default
      Previous value: -"pNInz6obpgDQGcFmaJgB"New value: +null
  5. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=true, and destructiveHint=true. The description adds two things annotations cannot convey: the operation consumes AI credits and is asynchronous, returning a job handle rather than finished media. It does not reconcile why a queue-style create carries destructiveHint=true, which leaves a small behavioral ambiguity.

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 sentences with zero filler. The cost and async-polling facts, which are the most decision-relevant details, are front-loaded and stated compactly.

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

Completeness4/5

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

An output schema exists, so return values need not be explained, and the description covers the essential operational facts: credit spend and the job-polling workflow via generation_jobs_get. The only real gap is any note about where the resulting asset lands or whether reusing an idempotency key differs behaviorally, which the schema partially handles.

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 the schema already explains text, speed, voiceId, voiceStyle, workspaceId, and idempotencyKey in detail, including range limits and the catalog-versus-cloned-voice distinction. The description adds no parameter-level meaning beyond the generic 'text-to-speech' framing, so the baseline of 3 applies.

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?

The description opens with a specific verb and resource: 'Queue a text-to-speech voiceover into the BlitzReels media library.' The phrase 'text-to-speech voiceover' cleanly separates it from siblings like generation_music_create, generation_image_create, or generation_video_create without needing their schemas.

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?

It tells the agent the precondition (spends AI credits) and the required follow-up: poll the returned job with generation_jobs_get. That is clear operational context, but there are no exclusions or comparison points to alternative creation tools for cases where a different media type is needed.

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