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

# Voice

> Real-time voice sessions, TTS voices, and STT/TTS model discovery.

The Voice API provides everything you need to build voice-powered agents:

* **List voices** — browse TTS voices across all configured providers
* **List models** — discover TTS, STT, and STS models
* **Create voice session** — establish a real-time voice session over LiveKit WebRTC
* **List providers** — see which voice providers are enabled for your organization

<CardGroup cols={2}>
  <Card title="List voices" icon="waveform" href="/api-reference/voice/voices">
    Browse all TTS voices available across providers.
  </Card>

  <Card title="Create voice session" icon="phone" href="/api-reference/voice/sessions-create">
    Start a real-time voice call powered by LiveKit.
  </Card>

  <Card title="List voice models" icon="microchip" href="/api-reference/voice/models">
    Discover TTS, STT, and STS models for agent configuration.
  </Card>

  <Card title="List providers" icon="plug" href="/api-reference/voice/providers">
    View enabled voice providers for your organization.
  </Card>
</CardGroup>

## Key concepts

* **TTS (Text-to-Speech)** — converts the agent's text reply into audio streamed to the caller.
* **STT (Speech-to-Text)** — converts caller speech into text that the LLM processes.
* **STS (Speech-to-Speech)** — end-to-end speech model that bypasses the text layer entirely (lower latency, less control).
* **Voice pipeline** — the combination of STT → LLM → TTS that processes a voice turn.
* **`voicePipelineMode`** on agents:
  * `pipeline` — classic STT + LLM + TTS
  * `sts` — direct speech-to-speech
  * `hybrid` — adaptive mode that switches based on conditions

## Connecting to a voice session

After calling `POST /v1/voice/sessions`, you receive a `token` and `serverUrl` for [LiveKit](https://livekit.io). Use the LiveKit SDK to connect:

```javascript Node.js theme={null}
import { Room, RoomEvent } from 'livekit-client';

const { token, serverUrl } = await fetch('https://api.agntix.ai/v1/voice/sessions', {
  method: 'POST',
  headers: { 'x-api-key': 'pk_live_••••', 'Content-Type': 'application/json' },
  body: JSON.stringify({ agentId: 'a1b2c3d4-...' }),
}).then(r => r.json());

const room = new Room();
await room.connect(serverUrl, token);
room.on(RoomEvent.TrackSubscribed, (track) => {
  // play agent audio
});
```

## Inbound calls

Assign a phone number to an agent in the dashboard or via `PATCH /v1/chat/phone-numbers/{id}`. Inbound calls to that number automatically start a voice session with the assigned agent.