> ## Documentation Index
> Fetch the complete documentation index at: https://www.bolna.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Voice agents

> Learn how to build, deploy, and monitor Bolna Voice AI agents that hold natural phone and web conversations in 40+ languages.

A Bolna voice agent listens to a caller, decides what to say, and answers in a natural voice — on inbound calls, outbound calls, batch campaigns, or in the browser. Every agent follows the same lifecycle: **build** it, **deploy** it to a phone number or app, then **monitor** what happens on each call. When it works in testing, **go live** with the launch checklist.

<CardGroup cols={2}>
  <Card title="Build" icon="sliders" href="/docs/agent-setup/overview">
    Set the prompt, LLM, voice, languages, tools and knowledge base in Agent Studio, or design a multi-step flow with graph agents.
  </Card>

  <Card title="Deploy" icon="phone-arrow-up-right" href="/docs/agents/deploy">
    Buy or connect phone numbers, place outbound, batch and workflow calls, receive inbound calls, or bring your own SIP trunk.
  </Card>

  <Card title="Monitor" icon="chart-line" href="/docs/agents/monitor">
    Review call history, receive webhooks, pull executions over the API, and extract structured data from every call.
  </Card>

  <Card title="Go live" icon="rocket" href="/docs/production/readiness-checklist">
    Test before calling real customers, control cost per call, handle failures at scale, and troubleshoot common problems.
  </Card>
</CardGroup>

## Featured

<CardGroup cols={2}>
  <Card title="Graph agents" icon="diagram-nested" href="/docs/graph-agent/introduction">
    Part of **Build**. Design a multi-step conversation as typed nodes and routing rules instead of one long prompt.
  </Card>

  <Card title="Workflows (beta)" icon="diagram-project" href="/docs/workflows/introduction">
    Part of **Deploy**. Chain calls, WhatsApp messages, conditions and retries into one sequence per contact, and run it over contact lists as campaigns.
  </Card>
</CardGroup>

Not sure which one you need? See [graph agents vs workflows](/docs/graph-agent/graph-agents-vs-workflows).

## Build your first agent

<CardGroup cols={2}>
  <Card title="Quickstart" icon="wand-magic-sparkles" href="/docs/agent-setup/studio">
    Describe your use case and get a call-ready agent from Agent Studio in 5 to 8 minutes.
  </Card>

  <Card title="API quickstart" icon="code" href="/docs/quickstarts/api">
    Place an outbound call and fetch the result over the API.
  </Card>

  <Card title="Inbound quickstart" icon="phone-arrow-down-left" href="/docs/quickstarts/inbound">
    Link a phone number to an agent and answer incoming calls.
  </Card>

  <Card title="Browse templates" icon="grid-2" href="/docs/agent-templates">
    Start from a ready-made agent for support, sales, reminders, bookings and more.
  </Card>
</CardGroup>

## Platform capabilities

### Build

| Capability | What it does |
| - | - |
| [Prompting](/docs/prompting/introduction) | Write the agent's instructions and personalize them per call with [dynamic variables](/docs/prompting/using-context) |
| [LLM](/docs/agent-setup/llm-tab) | Pick the model that reasons for your agent, or [bring your own](/docs/custom) |
| [Voices](/docs/agent-setup/audio-tab) | Choose the voice for each language, or [clone](/docs/clone-voices) and [import](/docs/import-voices) your own |
| [Languages & transcription](/docs/customizations/multilingual-languages-support) | Switch languages mid-call, write [prompts in other languages](/docs/writing-prompts-in-non-english-languages), and improve recognition with [keywords](/docs/customizations/asr-keywords-and-context) |
| [Engine](/docs/agent-setup/engine-tab) | Tune response latency and how the agent handles interruptions |
| [Knowledge base](/docs/knowledge-base) | Ground answers in your PDFs and URLs |
| [Tools](/docs/tool-calling/introduction) | Transfer calls, book calendar slots, and call your own APIs mid-conversation |
| [Graph agents](/docs/graph-agent/introduction) | Design multi-step conversations with typed nodes and routing |
| [Templates](/docs/agent-templates) | Start from a ready-made agent for your industry |

### Deploy

| Capability | What it does |
| - | - |
| [Phone numbers](/docs/buying-phone-numbers) | Buy numbers from Bolna, including [140 & 160-series numbers](/docs/obtaining-regulated-phone-numbers) in India |
| [Outbound calls](/docs/outbound/making-calls) | Call one person, or thousands with [batch calls](/docs/outbound/batch-calling), [auto-retry](/docs/outbound/auto-retry) and [calling guardrails](/docs/outbound/calling-guardrails) |
| [Workflows](/docs/workflows/introduction) (beta) | Chain calls, conditions, retries and WhatsApp messages into one sequence per contact, run them as [campaigns](/docs/workflows/campaigns), and get a [webhook](/docs/workflows/execution-webhook) when each finishes |
| [Inbound calls](/docs/inbound/receiving-calls) | Answer calls, [identify callers](/docs/customizations/identify-incoming-callers) and route them through an [IVR](/docs/inbound/ivr) |
| [Telephony](/docs/supported-telephony-providers) | Connect Twilio, Plivo, Exotel or Vobiz, or [bring your own SIP trunk](/docs/sip-trunking/introduction) |
| [Web calls](/docs/developer-resources/sdks/web-call) | Talk to your agent from the browser with the Web Call SDK |

### Monitor

| Capability | What it does |
| - | - |
| [Call history](/docs/agent-setup/call-history) | Listen to recordings and read transcripts, costs and latency for every call |
| [Call analytics](/docs/agent-setup/call-analytics) | See how many calls complete and become conversations, and the best time to call |
| [Latency](/docs/concepts/latency) | Understand and [measure](/docs/concepts/call-latencies) where response time goes |
| [Webhooks](/docs/post-call/polling-call-status-webhooks) | Receive call updates on your server as they happen |
| [Extractions](/docs/prompting/using-extractions) | Pull structured data such as outcomes, dates and intents out of each conversation |
| [Call statuses](/docs/post-call/list-phone-call-status) | Understand every state a call moves through and why it ended |

### Go live

| Capability | What it does |
| - | - |
| [Launch checklist](/docs/production/readiness-checklist) | Verify telephony, compliance, quality, observability, concurrency and cost before real calls |
| [Test before calling customers](/docs/production/test-before-calling-customers) | Check your agent end to end before it reaches real people |
| [Control cost per call](/docs/production/control-cost-per-call) | Reduce spend without hurting quality |
| [Failures & retries at scale](/docs/production/failures-and-retries-at-scale) | Classify failures, set retry policy and monitor large campaigns |
| [Troubleshooting](/docs/troubleshooting/calls-fail-or-drop-early) | Fix dropped calls, audio problems, interruptions, failed transfers and missing webhooks |

## How a call works

A standard agent chains three services: a **transcriber** turns the caller's audio into text, an **LLM** decides what to say, and a **synthesizer** turns the reply back into audio. A [speech-to-speech](/docs/speech-to-speech) agent replaces all three with a single realtime model. See [how a call flows through Bolna](/docs/concepts/call-flow) for the full lifecycle, from dialing to the finished execution record.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.