Skip to main content
Glama

speak

Generate ElevenLabs voiceovers for script lines with word-level timing, sync them to shots and captions, and preview character cost before confirming.

Instructions

Make the voice for script lines with ElevenLabs, with the time of every word, and give it to the shots that speak each line (captions follow the words; shots fit the voice unless fit is false). Spends the person's ElevenLabs characters: the first call (without confirm) returns the cost and what's left; ask, then call again with confirm: true. Default: every line without a voice, in the film's voice. Returns what was made and characters left. For the person's own recording (free), use own_voice.

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": "speak"
  }
}

Input Schema

NameRequiredDescriptionDefault
fitNoShots get the voice's length (default true).
againNoMake the voice again even for lines that have one.
linesNoLine ids from get_script. Default: every line without a voice.
modelNoDefault eleven_multilingual_v2. Flash and turbo cost half.
voiceNoAn ElevenLabs voice id (voices). Default: the film's voice.
confirmNotrue only after the person agreed to the cost.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.2
    • addedInput schema / properties / confirm / description
      Added value: +"true only after the person agreed to the cost."
    • addedInput schema / properties / lines / description
      Added value: +"Line ids from get_script. Default: every line without a voice."
    • addedInput schema / properties / voice / description
      Added value: +"An ElevenLabs voice id (voices). Default: the film's voice."
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only flag openWorldHint=true and idempotentHint=false; the description adds the crucial behavioral facts the annotations cannot convey — the call consumes the person's ElevenLabs character balance, requires a cost-confirmation round trip, forces shots to the voice length unless fit is false, and rewrites caption timing. It also covers re-generation via 'again'. It stops short of describing failure modes (insufficient credits, invalid voice id), which keeps it off a 5.

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 and effect, then the cost protocol, defaults, and the alternative. Dense but nearly every clause carries information; the parenthetical asides about captions and fit are slightly run-on but still earn their place.

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?

For a six-parameter, no-output-schema, credit-spending tool, the description covers scope, defaults, cost preview, confirmation, and return contents. The only gap is edge-case behavior when credits are insufficient or a line already has a voice without 'again'.

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, and the description genuinely adds meaning on top: it defines the default population for lines and voice, ties fit to shot/caption behavior, and most importantly explains that confirm must only be true after the person accepts the quoted cost. It adds workflow semantics rather than restating schema 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?

The opening sentence names a specific verb and resource — generate ElevenLabs voice audio for script lines with per-word timings — plus the downstream effect (attach to shots, captions follow words). It explicitly differentiates from the sibling own_voice for free self-recordings, 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?

It states the default scope (every line without a voice, in the film's voice), the exact two-step invocation protocol (first call returns cost and remaining credits, ask the person, then call again with confirm: true), and the explicit alternative for free recordings. When-to-use, when-not, and the required confirmation sequence are all spelled out.

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