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.
In the Smallest AI Console, create an API key. You’ll paste it into the demo in the next step.
A production-grade Next.js app with multi-agent presets, local tool execution, and a live wire log.
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.
Auth, query params, idle timeout, close codes.
Voices, persona, mid-session updates, conversation items.
Input PCM16, output rate negotiation, browser AudioWorklet.
Server-side VAD events and how to flush scheduled audio on the client.
Declare tools, run them locally, narrate the result.
Capabilities, voices, performance, pricing.