Client-facing voice agent demo
Click once, speak naturally, and compare the full voice palette from cheapest demo mode to premium production voice. Every route can run on a website now and can be connected to phone later.
Select one of the available routes, play English/German, start a conversation, and compare cost against quality.
Starter Voice
Allow microphone and speak. The agent will answer, then listen again.
Ready for hands-free web conversation. This is not real phone/SIP yet.
Sorted from cheapest internal cost to highest quality. Each card shows the stack, where it runs, and what it is best for.
This is the honest technical map. The code is ours, but the AI models are not local; they run in provider clouds.
| Layer | Current choice | Where it runs | Paid/free status | In-house? |
|---|---|---|---|---|
| Website page | Static HTML/CSS/JS | Cloudflare Pages edge | Cloudflare free/low cost | Yes, our code |
| Browser/demo route | Browser SpeechRecognition + browser speech + Groq | User's browser | Cheapest; demo-safe, not production-safe enough | Partly, browser engine |
| Paid transcription route | OpenAI Whisper fallback; future production STT can be OpenAI/Deepgram/ElevenLabs Scribe | OpenAI cloud | Paid per usage | No |
| LLM brain | Groq llama-3.3-70b-versatile | Groq cloud | API usage; currently cheap/free-tier friendly | No |
| OpenAI Standard voice | OpenAI TTS-1, alloy | OpenAI cloud | Paid per generated audio | No |
| Business Nova voice | OpenAI TTS-1, nova | OpenAI cloud | Same provider cost family as OpenAI Standard | No |
| Deepgram Aura voice | Deepgram Aura for English; German fallback through OpenAI HD in the lab Worker | Deepgram/OpenAI cloud via voicepilot-lab-worker | Live because the Deepgram key exists on the lab Worker | No |
| Cloud HD voice | OpenAI TTS-1-HD, onyx | OpenAI cloud | Paid per generated audio; middle premium route | No |
| Professional voice | ElevenLabs Flash/Rachel; OpenAI onyx fallback | ElevenLabs/OpenAI cloud | Paid provider route; ElevenLabs account status must be watched | No |
| Backend API | Cloudflare Worker | Cloudflare edge | Free/low cost until real traffic | Yes, our code |
| Usage tracking now | Browser localStorage | This visitor's browser | Free, demo only | Yes, but not production durable |
| Phone calls | Future LiveKit SIP/Telnyx or Retell route | Provider cloud + telecom network | Not connected on this page yet | No, only orchestration would be ours |
| In-house route | Future faster-whisper + Piper on Hetzner | Your own server, not active today | Pending; server cost and maintenance replace per-minute TTS fees | Mostly, after it is built |
After the client chooses a package, we install one script on their website and configure their knowledge base, escalation email, and allowed domains.
Starter Voice
This sends the request directly to MyClienta. We will review the selected package and reply with the setup steps.
Enter PIN to see internal costs, margin, and demo usage.
Wrong PIN.
Variable cost/min is the estimated provider cost for one real conversation minute: roughly one minute of customer speech plus one minute of AI answer. It is not a fixed invoice price.
Monthly examples below are voice usage only at 120 conversation minutes/day. They do not include your profit, setup work, support time, or taxes.
Currency note: providers usually bill in USD. The EUR values here are practical sales estimates, not accounting-grade exchange-rate calculations.
Supabase Pro is optional at MVP stage. For a real production dashboard with manuals/RAG/transcripts/usage, budget about USD 25/month for one shared Supabase project.
That project can serve the full route palette and multiple clients until traffic, data isolation, or compliance says we should split it.
Active today: Cloudflare Pages/Worker, browser speech APIs, Groq LLM, OpenAI Whisper/TTS, OpenAI Standard, Business Nova, OpenAI HD, ElevenLabs premium, and Deepgram Aura through the lab Worker.
Not connected here yet: Azure TTS, Cartesia, LiveKit, Telnyx, Supabase RAG, durable billing, manuals/PDF upload, real phone numbers, and the in-house Hetzner route.
Local/self-hosted: none of the AI models today. Only the product code and UI are ours right now. The in-house route is a future cost-control option, not a sellable live package yet.
No usage yet.