Bolna Docs

API Reference

Try Bolna on the Playground

List agents

Prompts to be provided to the agent. It can have multiple tasks of the form `task_<task_id>`

An array of tasks that the agent can perform

Description of all the tools you'd like to add to the agent. It needs to be a JSON string as this will be passed to LLM.

Parameters for each tool, where keys must match the `name` field in the `tools` array.

Bodhi

Toggle to add ambient noise to the call to add more naturalism

Ambient noise

Track for ambient noise can be coffee-shop, call-center, office-ambience

Track for ambient noise

This will enable agent to acknowledge when user is speaking long sentences

Backchanneling

Gap between every successive acknowledgement. We will also add a random jitter to this value to make it more random

Backchanneling Message Gap

Basic delay after which we should start with backchanneling

Backchanneling Start Delay

Call Cancellation Prompt

The call automatically disconnects reaching this limit

Terminate a call after specified number of seconds

Weather to use LLM prompt to hang up or not. Pretty soon this will be replaced by predefined function

Hangup After Llmcall

Time to wait in seconds before hanging up in case user doesn't speak a thing

Hangup After Silence

Since we work with interim results, this will dictate the linear delay to add before speaking everytime we get a partial transcript from ASR

Incremental Delay

To avoid accidental interruption, how many words should we wait for before interrupting

Number Of Words For Interruption

ConversationConfig

Deepgram

ElevenLabs

Polly

It can be a stand alone string or array of responses. If it's an array the length should be same as number of utterances and a particular index will be matched before returning

Response

Route Name

Score Threshold

This is an array of utterances which when spoken you want to send a static response

Utterances

Route

Since we use fastembed all models supported by fastembed are supported by us

Embedding Model

These are predefined routes that can be used to answer FAQs, or set basic guardrails, or do a static function call.

route

Routes

Style TTS

Should be used onkly in conversation task for now and it consists of all the required configuration for conversational nuances

Agent will execute these tools in the specified order

Configuration of multiple tools that form a task

Api tools you'd like the agents to have access to

Configuration of LLM model for the agent task

Configuration of Synthesizer model for the agent task

Configuration of Transcriber model for the agent task

API Token in case the URL needs authentication

Link of the URL to control the transferring of call

transfer_call

bearerAuth

Items

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

Introduction

Platform Concepts

Pricing

Leverage and scale Bolna Voice AI for your applications

Enterprise

Some pointers to get you started on your journey to creating and deploying Bolna agents

Tips & Tricks for Agent Creation

You can use these agents as templates for your use-cases

Agent templates

You can use your own providers for agents and lower your costs

Connect your Providers

Learn how to inject variables and other useful context in conversations

Adding dynamic context

Injecting dynamic variables and user context

Learn how to use functions with Bolna and connect large language models to external tools

Function calling

Learn how to ingest your PDFs and use them in Agent context

Using your knowledgebases

Learn how to use guardrails preventing harmful, inappropriate, or unintended outputs

Guardrails

Get real-time updates for call data using webhooks

Poll call data using webhooks

Use Bolna Voice AI with your own custom LLM

Using your own custom LLM

Use Bolna to initiate calls to & from phone numbers

Supported Telephony providers

Use Twilio with Bolna for initiating calls

Using Twilio

Use Twilio telephony to make outbound call to your customers & users

Using Twilio for outbound calling

Make Bolna agents answer your inbound calls using Twilio

Using Twilio for inbound calls

Use your own Twilio account to make outbound & inbound calls through Bolna

Connect your Twilio account

Use Plivo with Bolna for initiating calls

Using Plivo

Use Plivo telephony to make outbound call to your customers & users

Using Plivo for outbound calling

Make Bolna agents answer your inbound calls using Plivo

Using Plivo for inbound calls

Use your own Plivo account to make outbound & inbound calls through Bolna

Connect your Plivo account

Scheduling batches for your agent to call using APIs

Batch Calling

Create and deploy your Voice AI agents using playground

This is your home page! Create, modify or test your agents

Agent Setup

Your home page! Create, modify or test your agents

Agents Tab

Transcriber Tab

LLM Tab

Voice Tab

Call Tab

Functions Tab

Add follow up tasks for summary, extraction, etc

Tasks Tab

Agent executions

Bolna API Documentation

Use Agent APIs to create autonomous Bolna Voice agents

Overview

Agent APIs overview

Create agent

Get agent

Update agent

Use call APIs to invoke calls from your Agents

Calling APIs overview

Initiate Call

Use Executions APIs to get all your agent call & conversations history

Executions APIs overview

Get execution

List agent executions

Inbound agent APIs overview

Set inbound agent

Create and schedule multiple calls together

Batch APIs overview

Create batch

Schedule batch

Stop batch

Get batch

List batch executions

List all batches

Delete a batch

Knowledgebases

Create Knowledgebase

Get knowledgebase

List all knowledgebases

Delete knowledgebase

Providers APIs overview

Add a new provider

List providers

Remove a provider

Enterprise-only account APIs for accessing voices

API Documentation

Current APIs

Legacy APIs

List agents

Authorizations

Response