Skip to main content
Glama

own_voice

Use your own sound recording as a voice for a script line or shot, with optional pause removal, so captions follow the spoken words.

Instructions

Use the person's own recording (a sound file on this computer) as a voice, free: for a script line (line), for a shot (it becomes that shot's line), or as a new line. Its words are heard on this computer when voice text is set up, so captions can follow them. cut_pauses takes out long pauses. One undo step. For an AI voice (paid) use speak; for music use music.

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": {
      "path": "<path>"
    },
    "name": "own_voice"
  }
}

Input Schema

NameRequiredDescriptionDefault
fitNotrue: the shot gets the recording's length.
lineNoA line id from get_script that this recording speaks.
pathYesFull path of the sound file (MP3, WAV, M4A...).
shotNoOr: a shot id; the recording becomes that shot's line.
textNoWhat it says, if known.
cut_pausesNotrue: take out long pauses.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.1.2
    • addedInput schema / properties / cut_pauses / description
      Added value: +"true: take out long pauses."
    • addedInput schema / properties / fit / description
      Added value: +"true: the shot gets the recording's length."
    • addedInput schema / properties / line / description
      Added value: +"A line id from get_script that this recording speaks."
    • addedInput schema / properties / path / description
      Added value: +"Full path of the sound file (MP3, WAV, M4A...)."
    • addedInput schema / properties / shot / description
      Added value: +"Or: a shot id; the recording becomes that shot's line."
  2. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare the mutation/safety profile; the description adds genuinely new behavioral facts: it is free rather than paid, it is 'one undo step' (reversibility), cut_pauses removes long pauses, and the audio plays locally when voice text is configured so captions can follow. It does not cover failure modes (bad path, missing voice text), which is the remaining gap.

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 cost, and the alternatives are bundled at the end. The opening sentence is awkwardly punctuated ('free: for a script line (line), for a shot...'), which slightly impedes parsing, but almost no words are wasted.

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 6-parameter mutation with no output schema, the description covers cost, undo behavior, the three target modes, pause trimming, playback/captions, and the paid/music alternatives. Missing only error-path and prerequisite detail, which is minor relative to what annotations and the fully described schema already supply.

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 coverage is 100%, so every parameter including line, shot, path, text, fit and cut_pauses is already documented. The description adds only modest routing meaning beyond that — the third 'new line' case where neither line nor shot is given — which is correct but thin, so baseline 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?

States a specific verb and resource (use the person's own recording as a voice) and immediately names the three targets: a script line, a shot, or a new line. It also names the two siblings it is not (speak for AI voice, music for music), so an agent can route correctly without opening any schema.

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?

Gives explicit alternatives and the condition that selects each ('For an AI voice (paid) use speak; for music use music') plus the scenario-to-parameter mapping (line vs shot vs new line). It stops short of stating prerequisites such as the file needing to exist or what to do if voice text is not set up, so it is strong but not exhaustive.

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