Conecto

Turn text into speech

speech_synthesize

An MP3 of the text read aloud by one of the voices (speech_list_voices), saved in the file store with a download link. Up to 5,000 characters a call; it reads the language the text is written in. The file carries a machine-readable mark that the speech is AI-generated (ID3: AIGenerated, IPTC digital source type). Costs $0.07 per 1,000 characters, rounded up (at most $0.35 a call); nothing if it fails.

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": "speech_synthesize"
  }
}

Input Schema

Name	Required	Description
`name`	No	File name for the MP3.
`text`	Yes
`voice`	No	A voice from speech_list_voices; the first one when left out.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 28, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Goes well beyond the annotations: discloses output format (MP3 in file store with download link), char limit, auto language detection, embedded AI-generated watermark metadata (ID3/IPTC), and a precise cost model ($0.07/1k chars, max $0.35, free on failure). This is rich behavioral context an agent needs before spending money.

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?

Front-loaded with the output artifact, then limits, language behavior, provenance marking, and cost. Dense but every sentence earns its place with distinct operational facts.

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?

With no output schema, the description correctly explains the return value (MP3 file + download link), and covers limits, cost, and provenance. Nothing essential for correct invocation is missing.

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

Parameters4/5

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

Schema coverage is 67% and the one undocumented param (text) is compensated by the description's character limit and auto-language behavior. Voice selection is tied to speech_list_voices, and the per-character cost informs the text param, adding value beyond the schema.

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?

Specific verb+resource: produces an MP3 of text read aloud, saved to the file store. It distinguishes itself from siblings by naming speech_list_voices for voice selection and clearly differing from speech_transcribe (speech-to-text). An agent can tell exactly what it produces.

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?

Notes the 5,000-char limit per call and points to speech_list_voices for choosing a voice, giving clear context for use. However, it doesn't explicitly state when to prefer this over alternatives (e.g., when text exceeds 5,000 chars must be split) or any exclusions.

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

All Conecto tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?