Gemini Tts Mcp

io.github.runapi-builderPublished by GitHub account runapi-builderv0.2.1Updated Oct 29, 2026

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

VerifiedSTDIODesktop onlyMedia & DesignAI & ML

Overview

AI-generated overview

RunAPI MCP server for Gemini TTS that lets an assistant create text-to-speech tasks, poll their status, and check pricing.

What you can do
  • Create Gemini TTS text-to-speech tasks and optionally wait for a terminal status, returning task id, status and output URLs
  • Fetch the current status and latest result payload of an existing task
  • Look up RunAPI pricing for the Gemini TTS model line before submitting
  • Authenticate RunAPI through a browser login flow that saves the API key to a shared config file
When to use it
Use it when an assistant should generate speech audio through RunAPI's Gemini TTS models and stay scoped to that one model line, including checking price before spending. For access to every RunAPI model line, a broader RunAPI server is intended instead.
Requirements
Runs locally over stdio via npx from the npm package, so Node.js is needed. Task creation and status polling require a RunAPI account: either the login tool (browser flow writing ~/.config/runapi/config.json) or the RUNAPI_API_KEY environment variable for headless hosts. Pricing lookup works without sign-in.
Before you install
Creating tasks spends money on the RunAPI account, so confirm cost before expensive or batch requests. The login tool writes an API key to a config file on disk; keep that file and any RUNAPI_API_KEY value out of version control. Task creation and polling send prompts and task data to RunAPI's service.

Installation

In SourceWeft

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

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

RunAPI Gemini TTS MCP Server

Gemini TTS API access for AI agents: run audio generation operations, poll asynchronous results, and check pricing through one focused MCP server.

Works with Claude Code, Codex, Cursor, Windsurf, VS Code, Roo Code, and any MCP-compatible host.

[npm version] [GitHub repository] [Apache-2.0 license] [MCP Server] [2 models]

Install | Tools | Models | Agent Prompts | Configuration | Links

Why This Package?

@runapi.ai/gemini-tts-mcp is a focused Model Context Protocol server for the Gemini TTS model line on RunAPI. It gives MCP-compatible assistants direct access to 1 endpoint and 2 model variants without loading the full RunAPI catalog.

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

Install

Add it to Claude Code:

bash
claude mcp add gemini-tts -s user -- npx -y @runapi.ai/gemini-tts-mcp

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

bash
claude mcp add gemini-tts -s project -- npx -y @runapi.ai/gemini-tts-mcp

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

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

ToolAuthPurpose
text_to_speechYesCreate a Gemini TTS text to speech task and optionally wait for a terminal status. Returns the task id, status, and output URLs.
get_taskYesFetch the current status and latest payload for an existing task.
check_pricingNoLook up current pricing for a Gemini TTS model and endpoint.

Models

Gemini TTS covers 2 model variants across 1 endpoint. Each tool accepts the models listed for it:

ToolModels
text_to_speechgemini-2.5-pro-tts, gemini-3.1-flash-tts

Model availability can change between releases. Use check_pricing or the Gemini TTS 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

text
Run a Gemini TTS text to speech task with RunAPI.

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

Submit without waiting

text
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

text
Check current Gemini TTS pricing, then create the task if it matches my request.

The assistant calls check_pricing and can link to the Gemini TTS 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:

json
{  "apiKey": "your_runapi_key"}

Do not commit real API keys.

Links

ResourceURL
Gemini TTS model pagehttps://runapi.ai/models/gemini-tts
npm package@runapi.ai/gemini-tts-mcp
GitHub repositoryrunapi-ai/gemini-tts-mcp
RunAPI MCP overviewrunapi.ai/mcp
RunAPI docsrunapi.ai/docs

License

Licensed under the Apache License, Version 2.0.

Source: README.md at commit 3500a69

Tools

4

login

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

Parametersforce

text_to_speech

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

Parameterswaitmodelscenespeakersrequiredtimeout_mstemperaturecallback_urldialogue_turnsrequiredsample_contextpoll_interval_ms

get_task

Fetch the current status and latest result payload for a gemini-tts task.

Parametersactiontask_idrequired

check_pricing

Look up RunAPI pricing for the gemini-tts model line.

Parametersmodelaction

Version history

3
  1. v0.2.1LatestOct 22, 2026
  2. v0.2.0Sep 30, 2026
  3. v0.1.1Sep 16, 2026

Score

90% 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 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts