Skip to main content
Glama

speak

Convert text to a WAV speech file offline on the CPU, optionally adding radio, robotic, or glitch game voice effects without waiting on GPU jobs.

Instructions

Speak a line of text (English) to a WAV file, with an optional game voice effect. Runs on the CPU.

Model: Kokoro-82M (Apache 2.0) in its own venv, offline; ComfyUI and the GPU are not used, so it never waits on image or video jobs. About 10 s to load plus about 1 s per sentence. voice: an installed voice name (see list_voices; default "af_heart"), or a comma separated blend of up to 4 voices with the same accent, averaged ("am_michael,bm_george" is invalid: two accents; "am_michael,am_fenrir" is fine). Prefix a = American, b = British; f = female, m = male. speed: 0.5 to 2.0 (1.0 normal). effect: "none"; "radio" (band limited, compressed, light hiss, like a comms channel); "robotic" (flat buzzing monotone with a metallic echo); "glitch" (a voice struggling on low power: stutters on word onsets, dropouts, bursts of bit crushing). intensity 0 to 1 (default 0.5) scales the effect. seed makes the glitch pattern and noise reproducible (returned in the result either way). name: file name stem for the line (for example "pathfinder_hull_40_lowpower"); an existing file with that name is overwritten. Default: . keep_dry: with an effect, also keep the unprocessed take as _dry.wav. Output: 24 kHz mono 16 bit WAV, plus an OGG Vorbis copy when ffmpeg is installed, in output_dir (default /ai/output/localgen/audio//). Returns the paths, duration, sample rate, RMS and peak level, word timings and the seed. Text up to 2000 characters; one call per line of dialogue.

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
nameNo
seedNo
textYes
speedNo
voiceNo
effectNonone
keep_dryNo
intensityNo
output_dirNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so well: CPU-only in its own venv, offline, never contends with GPU image/video jobs, ~10 s load plus ~1 s per sentence. It also discloses that an existing file with the given name is overwritten, that keep_dry produces a second <name>_dry.wav, and that the seed is returned regardless.

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?

Long but front-loaded and organized by parameter name, so an agent can scan to the field it needs. A few effect descriptions ("a voice struggling on low power") are flavorful rather than load-bearing, but the density of genuinely useful constraints justifies most of the length.

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

Completeness5/5

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

For a 9-parameter file-writing tool with no annotations and no output schema, the description covers execution environment, timing, overwrite risk, and return contents (paths, duration, sample rate, RMS, peak, word timings, seed) plus the OGG copy condition. Nothing an agent needs in order to call it correctly is missing.

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 coverage is 0%, so the description must define all nine parameters, and it effectively does: voice blend rules (up to 4, same accent, with a valid and an invalid example), speed range 0.5-2.0, each effect value explained, intensity 0-1, seed reproducibility, name stem and overwrite semantics, keep_dry, and output_dir default. This is substantially more than the bare schema types.

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 ("Speak a line of text (English) to a WAV file") plus the optional effect layer, which immediately separates it from the generate_image/generate_video siblings. It also names the companion tool (list_voices) that supplies valid voice names, so an agent can place it in the workflow without opening the 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 concrete operating guidance: one call per line of dialogue, text capped at 2000 characters, and "see list_voices" for valid voice values. It stops short of explicit when-not-to-use or exclusion language (e.g. when to prefer a different backend), but the context is unambiguous.

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