End-to-end open-source voice agents platform: Quickly build LLM based voice driven conversational applications

Bolna is the end--to-end open source production ready framework for quickly building LLM based voice driven conversational applications.

Bolna helps you create AI Voice Agents which can be instructed to do tasks beginning with:

1. Initiating a phone call using telephony providers like Twilio, etc.
2. Transcribing the conversations using Deepgram, etc.
3. Using LLMs like OpenAI, etc to handle conversations
4. Synthesizing LLM responses back to telephony using AWS Polly, XTTS, etc.
5. Instructing the Agent to perform tasks like sending emails, text messages, booking calendar after the conversation has ended

Refer to the docs for a deepdive into all supported providers.

This repo contains the following types of agents in the agents/agent_types directory which can be used to create conversational applications:

1. contextual_conversational_agent: LLM-based free flow agent
2. graph_based_conversational_agent: LLM-based agent with classification
3. extraction_agent: Currently WIP. Feel free to contribute and open a PR

A basic local setup uses Twilio for telephony. We have dockerized the setup in local_setup/. One will need to populate an environment .env file from .env.sample.

The setup consists of four containers:

1. Twilio web server: for initiating the calls one will need to set up a Twilio account
2. Bolna server: for creating and handling agents
3. ngrok: for tunneling. One will need to add the authtoken to ngrok-config.yml
4. redis: for persisting agents & users contextual data

Running docker-compose up --build will use the .env as the environment file and the agent_data to start all containers.

Once the docker containers are up, you can now start to create your agents and instruct them to initiate calls.

The repo contains examples as a reference for creating for application agents in the agent_data directory:

1. airbnb_job: A streaming conversation agent where the agent screens potential candidates for a job at AirBnB
2. sorting_hat: A preprocessed conversation agent which acts as a Sorting Hat for Hogwarts
3. yc_screening: A streaming conversation agent which acts as a Y Combinator partner asking questions around the idea/startup
4. indian_elections_vernacular: A streaming conversation agent which asks people for their outlook towards Indian elections in Hindi language
5. sample_agent: A boilerplate sample agent to start building your own agent!

All agents are read from the agent_data directory. We have provided some samples for getting started. There's a dashboard coming up [still in WIP] which will easily facilitate towards creating agents.

General structure of the agents:

your-awesome-agent-name
├── conversation_details.json         # Compiled prompt
└── users.json                        # List of users that the call would be made to

1. Create a directory under agent_data directory with the name for your agent
2. Create your prompt and save in a file called conversation_details.json using the example provided
3. Optional: In case if you are creating a preprocessed agent, generate the audio data used by using the script scripts/preprocess.py

1. At this point, the docker containers should be up and running
2. Your agent prompt should be defined in the agent_data/ directory with conversation_details.json with the user list in users.json
3. Create your agent using the Bolna Create Agent API. An agent will get created with an agent_id
4. Instruct the agent to initiate call to users via scripts/initiate_agent_call.py <agent_name> <agent_id>

Though the repository is completely open source, you can connect with us if interested in managed offerings or more customized solutions.

We love all types of contributions: whether big or small helping in improving this community resource.

1. There are a number of open issues present which can be good ones to start with
2. If you have suggestions for enhancements, wish to contribute a simple fix such as correcting a typo, or want to address an apparent bug, please feel free to initiate a new issue or submit a pull request
3. If you're contemplating a larger change or addition to this repository, be it in terms of its structure or the features, kindly begin by creating a new issue open a new issue and outline your proposed changes. This will allow us to engage in a discussion before you dedicate a significant amount of time or effort. Your cooperation and understanding are appreciated