Speak

dev.kanekyPublished by kaneky.devOfficial publisherv0.1.1Updated Oct 26, 2026

Text to natural speech as MP3: 38 voices, 7 languages, 1,000 chars per call. Paid per call, x402.

The publisher's own server: Canonsheet

VerifiedStreamable HTTPWeb executableMedia & DesignAI & ML

Overview

AI-generated overview

Remote MCP server that turns text into natural-sounding MP3 speech with 38 voices across 7 languages, paid per call.

What you can do
  • Convert text to speech: turn up to 1,000 characters into an MP3 (64 kbit/s, mono, base64) using the Kokoro 82M model
  • Choose a voice and language: 38 voices covering American and British English, Spanish, French, Hindi, Italian and Brazilian Portuguese, where the voice determines the language
  • Adjust speaking rate between 0.5 and 2.0
  • Handle longer passages by splitting text at sentence boundaries across several calls
When to use it
Useful when an assistant needs to produce spoken audio from written text — narration, voiceovers, accessibility reads or quick audio versions of short documents — without running a local TTS model.
Requirements
A remote MCP endpoint at speak.kaneky.dev over streamable HTTP; no packages, environment variables or headers are declared. Calls are paid per use via x402, so a payment-capable client or wallet setup is implied.
Before you install
Each call is billed through x402, so usage costs money and repeated or long-text calls add up. Text sent for synthesis goes to a third-party service. Output is capped at 1,000 characters per call, so longer documents must be split.

Installation

In SourceWeft

  1. Open Speak in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/dev.kaneky%2Fspeak/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "speak": {
      "type": "http",
      "url": "https://speak.kaneky.dev/mcp"
    }
  }
}

Tools

1

speak

Turn up to 1,000 characters of text into natural speech (Kokoro 82M) and return it as an MP3 (64 kbit/s, mono, base64). 38 voices in American and British English, Spanish, French, Hindi, Italian and Brazilian Portuguese; the voice picks the language. Speed 0.5 to 2.0. Longer text: split it at sentence ends and call once per part.

Parameterstextrequiredspeedvoice

Version history

1
  1. v0.1.1LatestOct 23, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Kaneky integrations

Canonsheet

dev.kanekyOfficial publisher

Canonsheet builds a consistent prompt set for one human character — canonical image prompt, negative prompts, video prompt and optional contact sheet — for use.

Streamable HTTPWeb executable
Media & Design1 toolOct 24, 2026

Pagemd

dev.kanekyOfficial publisher

Pagmd is a remote MCP server that fetches a public web page and returns its main content as clean Markdown with metadata, billed per call.

Streamable HTTPWeb executable
Web Search & Scraping1 toolOct 27, 2026

Depcheck

dev.kanekyOfficial publisher

A remote MCP server that looks up known vulnerabilities for exact package versions in the public OSV database, with fixes, paid per call.

Streamable HTTPWeb executable
Developer Tools1 toolOct 24, 2026

Imagemeta

dev.kanekyOfficial publisher

Lets an assistant write SEO metadata such as title, alt text, keywords and copyright into JPEG, PNG or WebP images and get the modified image back.

Streamable HTTPWeb executable
Developer Tools1 toolOct 24, 2026