Skip to main content
Glama
ollama-tts-mcp

ollama-tts-mcp

text_to_speech

Converts any text into spoken audio and saves it as a WAV, M4A, or AIFF file using local Ollama speech models, fully offline. Choose a voice, strip markdown, and write straight to disk without playback.

Instructions

Convert text to speech and save it as an audio file, fully offline. Does not play it.

Args: text: The text to turn into speech. Any length. voice: Voice name, case-insensitive (e.g. "Zoey", "Hugh"). See list_voices. output_path: Where to save. Relative paths are resolved against the output directory (default ~/Desktop). If omitted, a timestamped name is used. format: "wav" (default), "m4a" (AAC, much smaller) or "aiff". If omitted, it is taken from output_path's extension. model: Ollama speech model tag. Defaults to the configured model. strip_markdown: Remove code blocks, links and markdown markers before speaking.

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": "text_to_speech"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
modelNo
voiceNo
formatNo
output_pathNo
strip_markdownNo

Output Schema

NameRequiredDescriptionDefault
resultYes

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 provided, the description carries the burden and does well: it discloses offline operation, that output is written to disk rather than played, the default output directory (~/Desktop) and timestamped fallback naming. It does not say what happens if the target file already exists or what errors to expect when the model or voice is unavailable.

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 two lead sentences front-load the key facts, and the Args block is genuinely necessary given zero schema coverage rather than redundant padding. A few phrases ("Any length", restating defaults) are filler, but nothing is structurally misplaced.

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 file-producing tool with an output schema already covering return values, the description supplies the behavioral context that matters: offline mode, persistence, path resolution, and format inference. The remaining gap is edge-case behavior on overwrite and failure, which is minor for this complexity.

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 this section is the only documentation and it covers all six parameters. It adds real meaning beyond the schema: voice names are case-insensitive with concrete examples, format accepts enumerated values and is inferred from the path extension when omitted, relative paths resolve against the default output directory, and strip_markdown explains exactly what gets removed.

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?

"Convert text to speech and save it as an audio file, fully offline" names a specific verb and resource, and the immediate follow-up "Does not play it" separates it from any playback sibling. The agent knows exactly what this produces (a file) before reading 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?

The negation "Does not play it" tells the agent to look elsewhere for playback, and "See `list_voices`" routes it to the prerequisite tool for voice discovery. It stops short of naming the alternative explicitly (e.g. "use speak to play"), so selection requires a small inference.

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