Skip to main content
practical, build-it-from-scratch guides. each one is a complete walkthrough you can follow start to finish, in plain language, with every command and file you need.

​
build a voice agent

a voice agent listens to a person, thinks, and talks back, all in real time. the loop is always the same four steps: 
🎙️ you speak  →  STT (speech to text)  →  LLM (the brain)  →  rumik TTS (text to speech)  →  🔊 it speaks
rumik is the last step: it turns the agent’s reply into natural hinglish speech. these guides wire up the whole loop around it. pick your framework:

with pipecat

build a voice agent using pipecat, an open-source framework for real-time voice.

with livekit

build a voice agent using livekit agents, with rooms and telephony built in.

​
which framework?

both give you a production-ready real-time agent. the difference is what they ship around the voice loop:
pipecatlivekit
best fora lightweight, code-first pipeline you fully controlrooms, web/mobile SDKs, and phone calls out of the box
transportbrings its ownlivekit’s WebRTC rooms
rumik pluginpipecat-rumiklivekit-plugins-rumik-ai
new to both? start with pipecat, it’s the shortest path to hearing your agent talk.
these guides assume you can run python and use a terminal. you do not need prior experience with voice agents.