Skip to main content
Glama

speak

Convert text of any length into speech using a saved or cloned voice, save the audio file, and return its path and exact duration.

Instructions

Turn text of any length into speech in a saved voice (voice_id) or a voice cloned from a public clip (reference_audio_url + its exact words in reference_text, billed at the cheaper 1x rate). Returns the saved file path and its exact duration in seconds. format: mp3, wav, flac, opus, aac. model: 'expressive' (default) or 'standard'. speed: 0.25-4.

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": "speak"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
modelNoexpressive
speedNo
formatNomp3
voice_idNo
output_pathNo
reference_textNo
reference_audio_urlNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses the return values (saved file path and exact duration in seconds), the default model, valid formats, and the speed range. It does not say what happens if output_path points at an existing file, whether voice_id and reference_audio_url are truly exclusive or which wins, or what errors occur on invalid reference_text.

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?

The core capability is front-loaded in the first sentence, with return values second and per-parameter facts condensed into short trailing clauses. The telegraphic fragments ("format: mp3, wav...", "speed: 0.25-4.") are efficient but leave units for speed implicit, and output_path is dropped entirely rather than given a clause.

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 an 8-parameter, no-annotation, no-output-schema generation tool, the description covers capability, both voice paths, return values, defaults and value ranges. The remaining gap is the output_path parameter's effect on where the file lands and overwrite behavior, plus failure modes when both voice inputs are supplied.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must define parameter meaning and it largely does: it supplies the accepted format values, the two model options with the default, the speed bounds, and the required pairing of reference_audio_url with reference_text. Seven of eight parameters gain concrete semantics that the bare schema lacks; only output_path is left unexplained.

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 ("Turn text of any length into speech") and immediately names the two voice sources it accepts. It is clearly a text-to-speech generator, distinct from the sibling 'transcribe' which would do the inverse, and the return value is stated explicitly.

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 clearly presents two mutually exclusive invocation modes: a saved voice via voice_id, or a cloned voice via reference_audio_url plus reference_text. It even adds a cost-based decision signal ("billed at the cheaper 1x rate") for the cloning path. It stops short of routing the agent elsewhere (e.g., telling it to call list_voices to obtain a voice_id, or when to prefer narrate_scenes).

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

Deploy Server

Other Tools