> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> STT). Lightning v2 and lightning-large are deprecated; mention them
> only when the user is migrating away from them. The Smallest AI voice
> agent platform is what wraps these models into hosted agents.

# Quickstart

> Talk to Hydra in under a minute - a one-clone browser client with multi-agent presets, tool execution, and a live wire log.

Hydra is realtime, full-duplex, speech-to-speech. The fastest way to feel that is to **talk to it**. The reference client below is single-clone and ships with multiple agent presets so you can hear barge-in, tool calls, and persona switching live.

## 1. Get an API key

In the [Smallest AI Console](https://app.smallest.ai/dashboard/api-keys), create an API key. You'll paste it into the demo in the next step.

## 2. Run the reference client

A production-grade Next.js app with multi-agent presets, local tool execution, and a live wire log.

```bash
git clone https://github.com/smallest-inc/hydra_agents.git
cd hydra_agents && npm install && npm run dev
```

Open `http://localhost:3000`, paste your API key into the right-hand panel, pick an agent preset, click **Connect**, and talk. Speak over Hydra to interrupt - barge-in is automatic.

## What just happened

| Step                 | Event                                                                          |
| -------------------- | ------------------------------------------------------------------------------ |
| WebSocket opens      | Server emits `session.created`                                                 |
| Client configures    | Client sends `session.configure` once                                          |
| Server confirms      | Server emits `session.configured` with the negotiated audio sample rate        |
| Client streams audio | Client sends `input_audio_buffer.append` continuously, base64-encoded PCM16    |
| User speaks / pauses | Server emits `input_audio_buffer.speech_started` / `speech_stopped`            |
| Model replies        | Server emits `response.output_audio.delta` chunks until `response.done`        |
| User barges in       | In-flight response cancels with `status: "cancelled"`, `reason: "interrupted"` |

## Next

#### [WebSocket connection](/models/speech-to-speech/web-socket-connection)

Auth, query params, idle timeout, close codes.

#### [Managing sessions](/models/speech-to-speech/managing-sessions)

Voices, persona, mid-session updates, conversation items.

#### [Audio I/O](/models/speech-to-speech/audio-i-o)

Input PCM16, output rate negotiation, browser AudioWorklet.

#### [Turn detection & barge-in](/models/speech-to-speech/turn-detection-barge-in)

Server-side VAD events and how to flush scheduled audio on the client.

#### [Tool calling](/models/speech-to-speech/tool-calling)

Declare tools, run them locally, narrate the result.

#### [Model card](/model-cards/speech-to-speech/hydra)

Capabilities, voices, performance, pricing.

> Talk to Hydra in under a minute with a browser client.