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

# Introduction

> Build voice AI agents in Python. Zero Runtime runs the real-time voice pipeline so you never manage latency, turn-taking, or scale.

<Frame>
  <img src="https://mintcdn.com/zeroruntime/DxZ_iPFBcVnQWS8B/images/zrt-architecture.svg?fit=max&auto=format&n=DxZ_iPFBcVnQWS8B&q=85&s=67ba5113b8d185a1d16ffc30ad259554" alt="Zero Runtime architecture: users connect through integrations to the fully managed real-time voice pipeline (denoise, VAD, STT, turn detection, LLM/realtime model, TTS), driven by your agent code in the Python SDK." width="1400" height="620" data-path="images/zrt-architecture.svg" />
</Frame>

**Zero Runtime** lets you build real-time voice AI agents in Python.

You write the agent code; we run the entire voice infrastructure including speech-to-text, LLM processing, text-to-speech, turn detection, noise cancellation, scaling, and GPUs.

Your code runs in your process, while all real-time voice handling runs on ours.

> **Think serverless for voice AI: you build the agent, we run the runtime.**

## Build

<CardGroup cols={3}>
  <Card title="Python" icon="python" href="/sdks/python">
    Build voice agents with the Python SDK.
  </Card>

  <Card title="Node JS" icon="node-js" href="/sdks/nodejs">
    Build voice agents with the Node JS SDK.
  </Card>
</CardGroup>

***

## Integration

Connect your agents with communication channels and client applications.

#### Communication

<CardGroup cols={2}>
  <Card title="Telephony" icon="phone" href="/telephony/introduction">
    Handle inbound and outbound voice calls.
  </Card>

  <Card title="WhatsApp" icon="whatsapp" href="/telephony/whatsapp-voice-agent-quick-start">
    Engage users through WhatsApp messaging.
  </Card>
</CardGroup>

#### Client SDKs

<CardGroup cols={2}>
  <Card title="React" icon="react" href="/quickstarts/web-integration/react">
    Build voice-enabled React experiences.
  </Card>

  <Card title="React Native" icon="mobile-screen" href="/quickstarts/mobile/react-native">
    Integrate voice features into mobile apps.
  </Card>

  <Card title="iOS" icon="apple" href="/quickstarts/mobile/ios">
    Add voice experiences to iOS apps.
  </Card>
</CardGroup>

***

## Observe

Monitor, analyze, and troubleshoot agent interactions and performance.

<CardGroup cols={2}>
  <Card title="Tracing" icon="telescope" href="/build/observability-and-monitoring/analytics/traces">
    Track agent execution step by step.
  </Card>

  <Card title="Metrics" icon="cube" href="/build/observability-and-monitoring/analytics/session-analytics">
    Measure usage, performance, and outcomes.
  </Card>

  <Card title="Logs" icon="binoculars" href="/build/observability-and-monitoring/analytics/observability-options">
    Review detailed agent activity records.
  </Card>

  <Card title="Recording" icon="file-audio" href="/build/observability-and-monitoring/recording">
    Access and review conversation recordings.
  </Card>
</CardGroup>

## Deploy

Take your agent from local development to production on Zero Runtime.

<CardGroup cols={2}>
  <Card title="Overview" icon="rocket" href="/deployments/overview">
    Understand how Zero Runtime deploys and scales your agents.
  </Card>

  <Card title="Deploy an Agent" icon="cloud-arrow-up" href="/deployments/deploy-an-agent">
    Ship your agent to production step by step.
  </Card>
</CardGroup>

## Use Cases

Explore production-ready examples and reference implementations to accelerate development.

<CardGroup cols={2}>
  <Card title="Appointment Scheduling" icon="calendar" href="https://github.com/ZeroRuntimeAI/zeroruntime-python-examples/blob/main/tools/n8n_workflow/appointment_telephony.py">
    Phone-tuned booking agent whose tools are an n8n workflow reached over MCP.
  </Card>

  <Card title="Customer Support" icon="headphones" href="https://github.com/ZeroRuntimeAI/zeroruntime-python-examples/blob/main/tools/human_in_the_loop/customer_agent.py">
    Support agent that escalates to a human over MCP instead of guessing.
  </Card>

  <Card title="Live Translation" icon="language" href="https://github.com/ZeroRuntimeAI/zeroruntime-python-examples/blob/main/context/translator_agent.py">
    Detects the caller's language each turn and rebuilds the pipeline to answer in it.
  </Card>

  <Card title="Multilingual Support" icon="globe" href="https://github.com/ZeroRuntimeAI/zeroruntime-python-examples/blob/main/context/demo_multilang.py">
    Detects the user's language automatically and provides support in their preferred language.
  </Card>
</CardGroup>

## Need Help?

<CardGroup cols={3}>
  <Card title="Community" icon="discourse" href="https://community.zeroruntime.ai/">
    Join the community and connect with other developers.
  </Card>

  <Card title="Python examples" icon="github" href="https://github.com/ZeroRuntimeAI/zeroruntime-python-examples/tree/main">
    Runnable Python agents to read, copy, and adapt.
  </Card>

  <Card title="Node JS examples" icon="github" href="https://github.com/ZeroRuntimeAI/zeroruntime-js-examples/tree/main">
    The same agents in TypeScript, one file per idea.
  </Card>

  <Card title="Talk to an Expert" icon="headset" href="https://zeroruntime.ai/talk-to-expert">
    Book a demo, contact support, or speak with our sales team.
  </Card>
</CardGroup>