# gemini-tts-mcp [Health: Active]

**Category:** 🎧 Text-to-Speech  
**Repository:** https://github.com/runapi-ai/gemini-tts-mcp  
**GitHub Stars:** 0  
**npm Downloads (last month):** 458  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/gemini-tts-mcp

## Description
RunAPI MCP server for Gemini TTS: create tasks, poll status, check pricing.

## Tools
Capabilities this server exposes over MCP:

- **text_to_speech** — Create a Gemini TTS text to speech task and optionally wait for a terminal status. Returns the task id, status, and output URLs.
- **get_task** — Fetch the current status and latest payload for an existing task.
- **check_pricing** — Look up current pricing for a Gemini TTS model and endpoint.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "gemini-tts-mcp": {
    "command": "npx",
    "args": ["-y","@runapi.ai/gemini-tts-mcp"],
    "env": {
      "RUNAPI_API_KEY": ""
    }
  }
}
```

**Requires environment variables:** `RUNAPI_API_KEY` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What gemini-tts-mcp does

The gemini-tts-mcp MCP server gives an MCP-compatible host access to RunAPI’s Gemini TTS model line. It supports one RunAPI endpoint and two documented model variants: `gemini-2.5-pro-tts` and `gemini-3.1-flash-tts`.

The server is intended for agents that need to submit text-to-speech work, inspect asynchronous results, or review pricing before creating a task. It keeps the available model scope limited to Gemini TTS rather than exposing the full RunAPI catalog.

## How it works

The server runs over stdio and can be added to an MCP host with the `@runapi.ai/gemini-tts-mcp` npm package. An assistant can call `text_to_speech` to create a task. That call can either return after submission or wait for a terminal status, and its response includes the task ID, status, and output URLs when available.

For work submitted without waiting, `get_task` retrieves the current status and latest payload using the task ID. `check_pricing` looks up current pricing for a Gemini TTS model and endpoint and does not require authentication.

## Setup and configuration

The package can be launched with `npx` using this MCP configuration:

```json
{
  "mcpServers": {
    "gemini-tts": {
      "command": "npx",
      "args": ["-y", "@runapi.ai/gemini-tts-mcp"]
    }
  }
}
```

Claude Code can add the server at user or project scope with its `claude mcp add` command. The same stdio command is documented for Codex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts.

For authenticated operations, credentials are resolved from `RUNAPI_API_KEY` first, then from `~/.config/runapi/config.json`. The MCP `login` tool can open a browser sign-in and save credentials in that file. Headless environments can set `RUNAPI_API_KEY` before launching the host. A pre-provisioned configuration file may contain an `apiKey` field. Real keys should not be committed to source control.

## Tools and capabilities

- `text_to_speech`: Creates a Gemini TTS task and optionally waits for completion. Supported models are `gemini-2.5-pro-tts` and `gemini-3.1-flash-tts`.
- `get_task`: Reads the current state and latest response data for an existing task.
- `check_pricing`: Returns current pricing information for a Gemini TTS model and endpoint without requiring sign-in.

The gemini-tts-mcp MCP server is suitable for conversational workflows where an agent first checks price, submits audio generation, and then reports the task ID or output URLs.

## Limitations and notes

Task creation and status polling require RunAPI authentication; pricing lookup remains available without a key. Model availability can change between releases, so clients should use `check_pricing` or the RunAPI Gemini TTS model page for the current catalog. The package covers Gemini TTS rather than the complete RunAPI model collection.

_Full upstream README: https://allmcps.com/mcp/gemini-tts-mcp/readme_