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

# Voice Calls

> Outbound and inbound phone calls

Voice is the original and most-used channel. A call moves through four hops:

```
Caller ──▶ Telephony Provider ──▶ Transcriber ──▶ LLM ──▶ Synthesizer ──▶ Caller
              (Plivo/Twilio)       (Deepgram)    (GPT-4)   (ElevenLabs)
```

1. **Inbound audio** streams from the telephony provider over WebSocket.
2. The **transcriber** converts audio to text in near real time.
3. The **LLM** receives the transcript plus conversation history and generates
   a response, optionally calling tools.
4. The **synthesizer** converts the response to audio, streamed back to the
   caller.

## Making an outbound call

Place an outbound call to a contact from the dashboard or trigger one as part
of a campaign.

## Receiving inbound calls

Point your telephony number at Agentic OS — see
[Receive Incoming Calls](/docs/guides/inbound/receive-incoming-calls).

## Latency

Each hop above adds latency. Typical end-to-end latency on a well-tuned agent
is 600–900ms. To reduce it:

* Use a streaming-capable LLM configuration
* Choose a low-latency transcriber model
* Tune the synthesizer's buffering to start playback early
* Keep response length short for faster generation