Skip to main content
Glama
Sign In
gemini-mcp-server

gemini-mcp-server

by mnthe
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

generate_speech

Convert text to speech using Gemini TTS models. Supports single or two-speaker synthesis with prebuilt voices.

Instructions

Generate speech audio using Gemini TTS models. Supports single-speaker and two-speaker TTS. Input is text-only; audio, image, and video reference files are not accepted. TTS has a 32k-token context limit and does not support streaming. Audio is saved to /root/Music/gemini-generated/speech and returned as MCP audio content.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "generate_speech"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoSpeech model (default: gemini-3.1-flash-tts-preview, valid on both backends). Vertex AI uses GA ids gemini-2.5-flash-tts/gemini-2.5-pro-tts; Google AI Studio uses gemini-2.5-flash-preview-tts/gemini-2.5-pro-preview-tts.
promptYesText or transcript to synthesize as speech. Gemini TTS is text-only input; audio/image/video reference files are not accepted.
speakersNoExactly two speaker voice configs for multi-speaker TTS
voiceNameNoPrebuilt voice name for single-speaker TTS (default: Kore)
languageCodeNoOptional BCP-47 language code for speech synthesis

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description bears full responsibility. It discloses key behaviors: text-only input, 32k-token limit, no streaming, output saved to a specific path and returned as MCP audio content.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences encapsulate all essential information without redundancy. The most critical purpose is front-loaded, making it easy for an agent to quickly grasp the tool's function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the 5 parameters and no output schema, the description covers input constraints, output location, and return type. It could mention output length or multi-speaker prompt formatting, but overall it's sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by explaining model defaults, backend-specific IDs, and the nature of the speakers array, exceeding baseline expectations.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it generates speech audio using Gemini TTS models, specifying support for single and two-speaker. It distinguishes from sibling tools like generate_music or generate_video by focusing on text-to-speech.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: input is text-only, no audio/image/video references, 32k-token limit, no streaming. While it doesn't explicitly contrast with alternatives, it clearly defines when this tool is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools