Speak MCP

An MCP server that converts text into natural speech MP3 files using the Kokoro 82M model. It supports 38 voices across six languages (English, Spanish, French, Hindi, Italian, Portuguese) with configurable speed. The service processes up to 1,000 characters per call and returns base64-encoded audio.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Kaneky

You need:paid with x402

MCP endpoint (Streamable HTTP)

https://speak.kaneky.dev/mcp

Vendor documentation

What you can do with it

Convert text snippets into natural speech audio
Generate MP3 files in multiple languages
Create voiceovers for content using specific voices

Source and maintenance

Vendor evidenceRegistry 0.1.1

mcp-registry: dev.kaneky/speak@0.1.1 Project website

Protocol and capabilities

Server: speak 0.1.1
MCP protocol: 2025-06-18
Tools: 1 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

speak is paid per call over x402: the first attempt answers HTTP 402 with the price (v1 in the body, v2 in the PAYMENT-REQUIRED header); retry with X-PAYMENT (v1) or PAYMENT-SIGNATURE (v2). Text that is refused, or speech that cannot be generated, is not charged.

Tools

1 advertised

speak

Advertised by the server during the last successful anonymous check.

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.

speak input schema

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 1000,
      "minLength": 1,
      "description": "What to say, in the voice's language. At most 1,000 characters."
    },
    "speed": {
      "type": "number",
      "default": 1,
      "maximum": 2,
      "minimum": 0.5
    },
    "voice": {
      "enum": [
        "af_heart",
        "af_alloy",
        "af_aoede",
        "af_bella",
        "af_jessica",
        "af_kore",
        "af_nicole",
        "af_nova",
        "af_river",
        "af_sarah",
        "af_sky",
        "am_adam",
        "am_echo",
        "am_eric",
        "am_fenrir",
        "am_liam",
        "am_michael",
        "am_onyx",
        "am_puck",
        "bf_alice",
        "bf_emma",
        "bf_isabella",
        "bf_lily",
        "bm_daniel",
        "bm_fable",
        "bm_george",
        "bm_lewis",
        "ef_dora",
        "em_alex",
        "ff_siwis",
        "hf_alpha",
        "hf_beta",
        "hm_omega",
        "hm_psi",
        "if_sara",
        "im_nicola",
        "pf_dora",
        "pm_alex"
      ],
      "type": "string",
      "default": "af_heart",
      "description": "Voice id. a/b = American/British English, e = Spanish, f = French, h = Hindi, i = Italian, p = Brazilian Portuguese; second letter f/m = female/male."
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 1727 ms
95th percentile latency: 1727 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 8:51 AM UTC · probe · passed · 1727 ms · metadata changed · 1 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http speak-mcp https://speak.kaneky.dev/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add speak-mcp --url https://speak.kaneky.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable speak-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "speak-mcp": {
      "url": "https://speak.kaneky.dev/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "speak-mcp": {
      "type": "streamableHttp",
      "url": "https://speak.kaneky.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start speak-mcp and inspect its tools.

VS Code configuration

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

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http speak-mcp https://speak.kaneky.dev/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "speak-mcp": {
      "url": "https://speak.kaneky.dev/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "speak-mcp": {
      "serverUrl": "https://speak.kaneky.dev/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Speak MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 4,357

Do you run Speak MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing