Skip to main content
Glama

Why This Package?

@runapi.ai/elevenlabs-mcp is a focused Model Context Protocol server for the ElevenLabs model line on RunAPI. It gives MCP-compatible assistants direct access to 2 endpoints and 3 model variants without loading the full RunAPI catalog.

Use this per-model server when an agent should stay scoped to ElevenLabs. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.

audio-isolation was retired on 2026-10-09T00:00:00Z. New requests return HTTP 410 before task creation or balance deduction. Existing tasks can still be queried. This model ID is not mapped to another model.

sound-effect-v2 was retired on 2026-10-14T00:00:00Z. New requests return HTTP 410 before task creation or balance deduction. Existing tasks can still be queried. This model ID is not mapped to another model.

speech-to-text was retired on 2026-10-14T00:00:00Z. New requests return HTTP 410 before task creation or balance deduction. Existing tasks can still be queried. This model ID is not mapped to another model.


Related MCP server: ElevenLabs MCP Server

Install

Add it to Claude Code:

claude mcp add elevenlabs -s user -- npx -y @runapi.ai/elevenlabs-mcp

Use project scope when the server should be shared with a repository:

claude mcp add elevenlabs -s project -- npx -y @runapi.ai/elevenlabs-mcp

Codex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:

{
  "mcpServers": {
    "elevenlabs": {
      "command": "npx",
      "args": ["-y", "@runapi.ai/elevenlabs-mcp"]
    }
  }
}

check_pricing works before sign-in. For task creation and status polling, ask your assistant to call the login tool. It opens a browser login and saves credentials to ~/.config/runapi/config.json, the same file used by runapi login. Headless and CI hosts can still set RUNAPI_API_KEY before starting the MCP host.

Ready-made examples are in examples/ for Claude, Cursor, Windsurf, VS Code, and Roo Code.


Tools

Tool

Auth

Purpose

text_to_dialogue

Yes

Create an ElevenLabs text to dialogue task and optionally wait for a terminal status. Returns the task id, status, and output URLs.

text_to_speech

Yes

Create an ElevenLabs text to speech task and optionally wait for a terminal status. Returns the task id, status, and output URLs.

get_task

Yes

Fetch the current status and latest payload for an existing task.

check_pricing

No

Look up current pricing for a ElevenLabs model and endpoint.


Models

ElevenLabs covers 3 model variants across 2 endpoints. Each tool accepts the models listed for it:

Tool

Models

text_to_dialogue

text-to-dialogue-v3

text_to_speech

text-to-speech-multilingual-v2, text-to-speech-turbo-v2.5

Model availability can change between releases. Use check_pricing or the ElevenLabs model page for the current catalog view.


Agent Prompts

Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.

Create a task

Run an ElevenLabs text to dialogue task with RunAPI.

The assistant can call check_pricing, then text_to_dialogue, and return the task id, status, and output URLs.

Submit without waiting

Create the task but don't wait for it to finish.

The assistant calls the create tool with wait: false and returns the task id. Check on it later with get_task.

Check pricing before creating

Check current ElevenLabs pricing, then create the task if it matches my request.

The assistant calls check_pricing and can link to the ElevenLabs model page for the canonical catalog entry.


Configuration

The server resolves auth in this order:

  1. RUNAPI_API_KEY environment variable, useful for headless and CI hosts

  2. ~/.config/runapi/config.json, created by the MCP login tool or runapi login

  3. No key, which still allows check_pricing

The config file is normally managed by login. A pre-provisioned headless config can use:

{
  "apiKey": "your_runapi_key"
}

Do not commit real API keys.


Resource

URL

ElevenLabs model page

https://runapi.ai/models/elevenlabs

npm package

@runapi.ai/elevenlabs-mcp

GitHub repository

runapi-ai/elevenlabs-mcp

RunAPI MCP overview

runapi.ai/mcp

RunAPI docs

runapi.ai/docs


License

Licensed under the Apache License, Version 2.0.

Available Tools

5 tools
check_pricingC

Look up RunAPI pricing for the elevenlabs model line.

Inputs: model, action.

get_taskB

Fetch the current status and latest result payload for a elevenlabs task.

Inputs: action (required), task_id (required).

loginA

Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.

Inputs: force.

text_to_dialogueB

Create a ElevenLabs task on RunAPI (text to dialogue). Returns a task id, status, and output URLs.

Inputs: dialogue (required), wait, model, stability, +4 more.

text_to_speechB

Create a ElevenLabs task on RunAPI (text to speech). Returns a task id, status, and output URLs.

Inputs: text (required), wait, model, speed, +11 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 5 tools

    Disambiguation4/5

    Each tool has a largely distinct purpose: login and check_pricing are unrelated to generation, get_task polls results, and the two creation tools differ by single- vs multi-speaker output. The main risk is text_to_speech vs text_to_dialogue, since both 'create a task' and an agent could pick the wrong one, but the descriptions make the distinction clear enough.

    Naming Consistency4/5

    All names use snake_case, and most follow a verb_noun pattern (check_pricing, get_task). The exceptions are the bare verb 'login' and the noun-phrase style text_to_speech/text_to_dialogue, which read more like resource names than actions, but the set is still predictable and readable.

    Tool Count4/5

    Five tools is a tight, focused surface for an ElevenLabs wrapper (auth, pricing, generation x2, task lookup). It is on the thin side but each tool clearly earns its place; no bloat.

    Completeness3/5

    Core generation, auth, and result polling are covered, but there is no list_tasks or cancel/delete operation, so once a task id is lost the agent has no way to recover or enumerate work. Voice/model listing and any voice-selection capability are also absent, which are natural parts of a text-to-speech domain.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers