Customer Experience
Voice Support Agent
Speak to it and it speaks back — a phone-style agent, right in your browser.
Production proof: Voice is the breakout 2026 category: AI calls cost ~$0.40 vs $7–12 for a human. This runs the whole speech loop on your device. Read the case study →
⚡ Run it live with your own API key no key set
Your key is held in memory for this session (kept for this tab only if you tick the box) and sent only to the provider you choose, directly from your browser. This site has no backend server — you can confirm it in your browser's Network tab: requests go only to the provider, never to this site. Live runs use small, fast models with hard token caps; a typical run costs well under $0.01, billed to your own account.
Honest limits: no website can protect a key from a compromised browser or malicious extension. Use a key with a spending cap, and revoke it after playing if you like.
How it’s engineered
- The full loop runs in your browser: the Web Speech API transcribes your voice, the reply is generated, and speech synthesis reads it back. No telephony vendor, no per-minute fee for the demo.
- Speech input is progressive enhancement: where the browser supports it you can talk; everywhere else you type or tap a sample, and the reply still plays aloud.
- Recognized speech is fuzzy, so replies are matched by intent, not exact words, the same intent-routing approach behind my 22-intent production router.
- In production this connects to a telephony provider (Twilio/LiveKit) with barge-in and sub-300ms turn-taking; the demo shows the conversational core that makes it feel human.