second-statesecond-stateOfficialยท1 Agent Skills Included

echokit_server

Run a voice AI server connecting speech, LLM, and TTS services

Runs a real-time voice AI server that connects speech recognition, language models, and text-to-speech into one pipeline. Generates ready-to-use config.toml files through an interactive setup covering platforms, API keys, and MCP servers. Removes manual TOML editing and guesswork when deploying EchoKit voice devices locally or in the cloud.
npx skills add second-state/echokit_server --all -g -y

All Skills in This Repository (1)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install EchoKit Server?โ–ผ

Run `npx skills add second-state/echokit_server --all -g -y` in your terminal to install all tools in this suite globally.

What does EchoKit Server do?โ–ผ

It connects your EchoKit voice device to AI services, running a full ASR to LLM to TTS pipeline for real-time spoken conversations.

Which AI models work with EchoKit?โ–ผ

Any OpenAI-compatible API works for speech recognition, language models, and text-to-speech, including Gemini, Groq, ElevenLabs, and local open-source servers.

How do I generate an EchoKit config file?โ–ผ

Just ask your AI agent to generate an EchoKit config, and the skill walks you through choosing platforms, entering API keys, and launching the server.

Can I use EchoKit without coding experience?โ–ผ

Yes. The config generator skill asks plain-English questions and produces a working server configuration automatically.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’