kokoro-tts-mcp

speak

Converts text into spoken audio and plays it through local audio output using Kokoro TTS, requiring no API key; supports per-request voice and speed overrides.

Instructions

Convert text to speech and play it through speakers using Kokoro TTS (local, free, no API key needed). IMPORTANT: If auto-speak is enabled (check via tts_config), you MUST call this tool with your full response text for EVERY response, no exceptions. Never skip calling speak when auto-speak is ON.

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

Name	Required	Description
`text`	Yes	The text to speak aloud
`speed`	No	Override speed for this call (0.5 to 2.0)
`voice`	No	Override voice for this call. Prefix guide: af/am=American English, bf/bm=British English, ef/em=Spanish, ff=French, hf/hm=Hindi, if/im=Italian, jf/jm=Japanese, pf/pm=Portuguese, zf=Mandarin.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 14, 2026

TDQS

A3.8/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full burden and it does cover real behavior: the output is played aloud through speakers, runs locally, and needs no API key. It omits failure modes (no audio device, invalid voice), whether text is truncated or queued, and what the call returns, which matters for a side-effecting tool. The mandatory-call policy is useful context, but the disclosure is incomplete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, both earning their place: the first states capability and backend, the second states the invocation policy. The usage condition is front-loaded in caps. Minor redundancy between 'no exceptions' and 'Never skip' does not undermine the structure.

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 simple three-parameter, single-side-effect tool with no output schema, the definition covers purpose, backend, safety of use (local, free, no key), and the triggering condition. What is missing is error and return behavior, which is the only gap for an agent deciding whether a failed call needs retry.

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 description coverage is 100%, and the schema already documents text, speed bounds, and the full voice-prefix guide, so the description need not repeat them. The description adds no parameter meaning beyond the schema, which is acceptable at baseline but no more.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a concrete verb and resource ('Convert text to speech and play it through speakers') and names the concrete backend (Kokoro TTS, local, no API key), so the agent knows exactly what the tool does and that it produces audible output. It does not explicitly contrast itself with the only sibling, tts_config, beyond telling the agent to consult that tool first, so it falls just short of full sibling differentiation.

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 conditional is stated explicitly: if auto-speak is ON (checkable via tts_config), call this tool with full response text for every response, and never skip it. That is unusually clear when-to-use guidance with a named companion tool for the prerequisite check. The when-not-to-use case (auto-speak OFF) is only implied, not stated.

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

speakA
tts_configA