Deploy conversational voice agents with Bolna
Build and run voice-first conversational agents by configuring telephony, ASR, LLM, and TTS providers behind a deployable orchestration service.
Prerequisites
Docker Compose, Redis, a telephony provider such as Twilio or Plivo, ASR/LLM/TTS provider credentials, optional ngrok for local telephony testing
Installation
Use the upstream install or setup path that matches your environment:
- docker compose build
- docker compose up -d
- docker compose up -d bolna-app twilio-app
- docker compose up -d bolna-app plivo-app
Requirements and caveats from upstream:
- This script will check for Docker dependencies, build all services with BuildKit enabled, and start them in detached mode.
- Make sure you have Docker with Docker Compose V2 installed
- Once the docker containers are up, you can now start to create your agents and instruct them to initiate calls.
Basic usage or getting-started notes:
A basic local setup includes usage of Twilio or Plivo for telephony. We have dockerized the setup in local_setup...
Choosing Twilio: for initiating the calls one will need to set up a Twilio account
The easiest way to get started is to use the provided script:
Extracted from upstream docs: https://raw.githubusercontent.com/bolna-ai/bolna/HEAD/README.md