Echokit

v1.0.0Communicationstable

Open Source Voice Agent Platform

agentic-aiaiasresp32llm
Share:
566
Stars
0
Downloads
0
Weekly
0/5

What is Echokit?

Echokit is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to open source voice agent platform

Open Source Voice Agent Platform

This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Open Source Voice Agent Platform

Use Cases

Voice agent platform for AI
TTS and ASR capabilities
Real-time voice interaction
second-state

Maintainer

LicenseGPL-3.0
Languagerust
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx echokit

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Echokit

EchoKit is an open-source voice agent platform that pipelines automatic speech recognition (ASR), large language model inference, and text-to-speech (TTS) into a cohesive real-time voice assistant, with native support for ESP32 embedded hardware and MCP server tool integrations. Built in Rust for performance, it supports OpenAI-compatible ASR and TTS endpoints, ElevenLabs streaming voices, Google Gemini Live, and any OpenAI-spec chat completion backend. Developers use it to build custom smart speakers, voice-controlled AI assistants, and embedded conversational agents that can call external tools via MCP.

Prerequisites

  • Rust stable toolchain (install via rustup.rs)
  • OpenAI API key or a compatible ASR/TTS/LLM endpoint
  • config.toml configured with your service endpoints and API keys
  • ESP32 device (optional — works without hardware for web-based voice testing)
  • An MCP client if integrating with Claude Desktop via the MCP protocol
1

Clone the EchoKit repository

Fetch the source code from GitHub.

git clone https://github.com/second-state/echokit_server
cd echokit_server
2

Build in release mode

Compile the Rust binary. Use the ARM64 flag if you are targeting Apple Silicon or ARM servers.

cargo build --release
# ARM64:
# RUSTFLAGS="-C target-feature=+fp16" cargo build --release
3

Edit config.toml with your API credentials

Configure the ASR, TTS, and LLM sections with your chosen service endpoints and API keys. All three sections are required for a working voice pipeline.

addr = "0.0.0.0:8080"
hello_wav = "hello.wav"

[asr]
platform = "openai"
url = "https://api.openai.com/v1/audio/transcriptions"
api_key = "sk-your-openai-key"
model = "gpt-4o-mini-transcribe"
lang = "en"

[tts]
platform = "openai"
url = "https://api.openai.com/v1/audio/speech"
model = "gpt-4o-mini-tts"
api_key = "sk-your-openai-key"
voice = "ash"

[llm]
platform = "openai_chat"
url = "https://api.openai.com/v1/chat/completions"
api_key = "sk-your-openai-key"
model = "gpt-4o-mini"
history = 5
4

Start the server

Launch echokit_server with debug logging. It binds to port 8080 and begins accepting voice connections.

export RUST_LOG=debug
nohup target/release/echokit_server &
5

Test with the web client

Navigate to https://echokit.dev/chat/ and enter your server's URL. Use an ESP32 device's K0 button or a browser microphone to start a voice session.

6

Add MCP server integrations (optional)

To give EchoKit tool-calling capabilities, add MCP server configurations to config.toml. The server will forward tool requests to connected MCP servers and return results to the LLM.

Echokit Examples

Client configuration

Claude Desktop configuration block if using EchoKit as an MCP-connected voice interface.

{
  "mcpServers": {
    "echokit": {
      "command": "npx",
      "args": ["echokit"]
    }
  }
}

Prompts to try

Sample voice inputs to exercise the EchoKit voice pipeline and MCP tool capabilities.

- "What time is it right now?" (spoken via microphone)
- "Read me the latest news headlines"
- "Convert 100 dollars to euros"
- "Set a reminder in 10 minutes to check the build status"
- "Describe what you see" (if vision MCP tools are configured)

Troubleshooting Echokit

Cargo build fails with compiler errors about missing features

Run 'rustup update stable' to get the latest stable Rust toolchain. If you see fp16-related errors on ARM64, add the RUSTFLAGS env var: RUSTFLAGS="-C target-feature=+fp16" cargo build --release.

Voice sessions start but the LLM responses are not synthesized to audio

Check the [tts] section in config.toml — the api_key, model, and url must all be correct. Test the TTS endpoint independently with a curl request to ensure it returns audio. Check RUST_LOG=debug output for TTS pipeline errors.

ESP32 device cannot reach the server

The server must be reachable from the device's network. Ensure 'addr' in config.toml is '0.0.0.0:8080' (not localhost), that your firewall allows port 8080, and that the ESP32 firmware is configured with the correct server IP address.

Frequently Asked Questions about Echokit

What is Echokit?

Echokit is a Model Context Protocol (MCP) server that open source voice agent platform It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Echokit?

Follow the installation instructions on the Echokit GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Echokit?

Echokit works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Echokit free to use?

Yes, Echokit is open source and available under the GPL-3.0 license. You can use it freely in both personal and commercial projects.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "echokit": { "command": "npx", "args": ["-y", "echokit"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Echokit?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides