Google ADK Speaker Agent with ElevenLabs

Name: Google ADK Speaker Agent with ElevenLabs
Author: reymerekar7

@reymerekar7

代码仓库

关于 Google ADK Speaker Agent with ElevenLabs

Quick example of building a speaker agent with Google ADK and ElevenLabs' MCP server

基本信息

分类

AI 与智能体

运行时

python

传输方式

stdio

发布者

reymerekar7

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "elevenlabs-mcp": {
      "command": "uvx",
      "args": [
        "elevenlabs-mcp"
      ],
      "env": {
        "ELEVENLABS_API_KEY": ""
      }
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Google ADK Speaker Agent with ElevenLabs?

Google ADK Speaker Agent with ElevenLabs is a Text-to-Speech (TTS) speaker agent built using Google’s Agent Development Kit (ADK) and the ElevenLabs MCP server. It connects to ElevenLabs via uvx to provide text-to-speech capabilities for developers building voice-enabled applications.

How to use Google ADK Speaker Agent with ElevenLabs?

Install dependencies (Python 3.11+), set your ElevenLabs and Google Gemini API keys in a .env file, activate a virtual environment, and navigate to the agents/ directory. Then run adk web to start the web client – the agent only supports async execution through this interface.

Key features of Google ADK Speaker Agent with ElevenLabs

Built with Google ADK and ElevenLabs MCP server
Connects via uvx for seamless TTS integration
Requires Python 3.11 or higher
Runs as an async agent through the web client
Simple project structure with minimal setup

Use cases of Google ADK Speaker Agent with ElevenLabs

Convert user text input into spoken audio using ElevenLabs voices
Integrate TTS capabilities into a Google ADK‑based agent workflow
Build voice‑enabled applications (e.g., interactive assistants, narrators)
Serve as a reference architecture for combining ADK with external MCP servers

FAQ from Google ADK Speaker Agent with ElevenLabs

What are the prerequisites for using this agent?

You need Python 3.11+, an ElevenLabs API key, a Google Gemini API key, and Google ADK installed.

How do I run the agent?

Activate your virtual environment, go to the agents/ directory, and run adk web. The agent is only executable as an async agent through the web client.

What environment variables are required?

A .env file in the root directory must contain ELEVENLABS_API_KEY and GOOGLE_API_KEY.

What should I do if I encounter issues?

Ensure your virtual environment is active, verify API keys are correctly set in .env, confirm all dependencies are installed, and check that you are running the command from the correct directory.

Where can I find additional documentation?

Refer to the Google ADK documentation, ElevenLabs documentation, and uvx documentation for further details.

AI 与智能体分类下的更多 MCP 服务器

欢迎来到智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

1MCP - One MCP Server for All

1mcp-app

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

468

Model Context Protocol Server for Home Assistant

tevonsb

A MCP server for Home Assistant

574

MCP Manager for Claude Desktop

zueai

simple web ui to manage mcp (model context protocol) servers in the claude app

290

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768