Multi-tenant, real-time voice agents that answer phone calls, understand intent, and execute business actions — without sending your data through a third-party telephony cloud. Sub-second response times. One operator, many bots. Bring your own AI providers.
Four loosely-coupled tiers connected by a real-time event stream. New tenants don't require redeploys — bot definitions land in the admin database, the platform picks them up and starts answering calls within seconds.
Behind the scenes, a phone call is two parallel streams talking to each other — signalling (who's calling whom, what codecs to use, when to hang up) and media (the actual audio packets). Here's the short version of what's in flight.
A caller dialing one of the bot's extensions, end to end.
A real call arrives from your SIP carrier or PSTN provider (or the built-in browser dialer for demos). The telephony gateway terminates signalling and bridges media.
The PBX core matches the dialed number to one of the registered bots — picked from the admin store.
A per-call AI pipeline is assembled from that bot's definition — voice, prompts, available tools.
Caller speech is transcribed live. The LLM responds, calls tools as needed, and the answer is spoken back — typically in ~1.3 seconds.
Every transcript line, detected intent, and lifecycle event is broadcast on the platform's event stream. Downstream consumers (CRM, analytics, custom orchestrator) react in real time.
One product configuration on top of the platform. An account manager configures a study; evaluators receive magic-link invitations; each is interviewed by an AI interviewer; the platform aggregates verbatim quotes into a leadership-ready brief. Two personas, one flow.
Brand, scenario, evaluator roster. Everything else follows from the study record.
Each participant gets a single-use token wrapped in a link the manager can copy or email. Delivery is provider-agnostic — Postmark, Resend, SES, or manual paste.
No account, no password. The token identifies them, the OTP proves they own the inbox. In the current POC the OTP is hardcoded to 111111 until an email provider is wired.
A warm streaming-TTS voice, tuned for calm editorial delivery. The interviewer asks one open-ended question at a time, follows the evaluator's energy, probes short answers gently.
The interviewer calls record_quote(quote_text, topic, sentiment) whenever the evaluator says something vivid or brand-specific. Multiple quotes per topic land as they surface — no post-hoc extraction.
Every call has a stereo recording, a full utterance transcript, and its quote stream on the Quote Board. Interviews and quotes deep-link to each other; a reference code on both dialer and admin makes support trivial.
An LLM aggregates every quote across the study into 3–5 themes with two-to-three hero quotes each — the "brand CEO reads three lines" deliverable. Verbatim only; the model doesn't paraphrase.
Production-grade voicebot capability without the third-party telephony bill or the data-exit problem.
Streaming STT, streaming TTS, smart turn-taking. Callers don't notice a robot on the line.
One deployment hosts unlimited bots — each with its own voice, prompts, scenario, and phone number.
Pluggable Speech-to-Text, LLM, and Text-to-Speech providers. Pin per bot, swap without redeploy.
Drop in a new business scenario — pizza ordering, hotel booking, support triage — as a small module. The platform exposes its tools to the LLM automatically.
Every transcript line, intent, and call event is broadcast in real time. Build dashboards, CRM hooks, or analytics on top.
Runs on any Linux box or VPS. Calls, transcripts, and customer data never leave your perimeter.
Real traffic flows in over standard SIP from your carrier or PSTN provider. A built-in WebRTC dialer ships alongside it for sales demos and internal QA — no client install needed.
Per-call logs, intent traces, and metrics. See what the AI heard, what it decided, and what it said — in real time.
Shipping in phases — each shippable on its own, none blocking the next.