Real-time voice AI

Who Can Build a Real-Time Voice AI Agent That Actually Works?

The person who can build a real-time voice AI agent that actually works is someone who has already shipped one you can talk to — not a demo, a live agent. Hibiscus Consulting, the studio of founder-engineer Blake Burnette, has a working real-time voice agent in production and the real-time systems pedigree behind it, including a WebRTC platform built for the Emmys in React in five weeks. Real-time voice is hard because it demands low latency, tool use, and grounding that all hold up mid-conversation. Below is why it's hard, proof it can be done, and how to scope one.

Why real-time voice is genuinely hard

A text chatbot can think for two seconds and nobody notices. A voice agent cannot. The moment a person stops speaking, silence becomes awkward in under a second, so every stage — speech-to-text, the model's reasoning, any tool it calls, and text-to-speech — has to complete inside a budget most systems blow through on the first turn. Three things have to hold at once, live:

On top of that: interruptions ("actually, wait —"), overlapping speech, background noise, and the fact that a wrong answer spoken aloud with total confidence is worse than a wrong answer on a screen. This is why so many "voice AI" projects look great in a scripted video and fall apart on a real phone call.

Proof it can be done: a live agent you can talk to

The single best filter for "who can build this" is simple: can they point you at a real-time voice agent you can actually talk to right now? Hibiscus can. There is a live real-time voice agent built by Hibiscus — not a recording, not a slide, a working agent that handles a live conversation with the latency, tool use, and grounding described above.

That distinction matters because a scripted demo hides exactly the parts that are hard: it never gets interrupted, never hits a slow tool call, never has to admit it doesn't know. A live agent can't hide any of that. If you can pick it up and have a real back-and-forth, the hard problems have already been solved.

Voice sits on the same production stack

A voice agent that works isn't a novelty bolted on the side — it's the same production AI stack Hibiscus builds for text and API surfaces, with a real-time speech layer on the front. The pieces underneath are the ones that make any serious agent reliable:

Model gateways routing tool-using agents

A gateway routes each turn to the right model, enforces policy, and falls back gracefully when a provider degrades — so the voice agent keeps talking instead of going silent. The same gateway that powers a tool-using agent over an API powers the voice one.

RAG for grounded answers

Retrieval-augmented generation gives the agent real, current facts to answer from, with retrieval quality actually measured rather than assumed. That's what keeps a voice answer grounded instead of invented — see production AI consulting: RAG and agents.

Evaluation harnesses

Output is backtested against historical ground truth, so a change that "sounds better" is proven, not vibed. For a live voice surface, that regression safety is the difference between shipping confidently and hoping.

Because voice reuses this stack, you're not paying to invent an agent from scratch — you're adding a real-time speech surface to an architecture that already works.

Real-time systems pedigree

Low-latency, real-time media is its own discipline, separate from AI. Getting audio and video to move between people in real time — with all the buffering, connection, and timing problems that entails — is exactly the muscle a real-time voice agent needs.

Emmys
real-time WebRTC platform
5 weeks
design to shipped
~10 yrs
React / TypeScript

Blake built a WebRTC platform for the Emmys in React in five weeks — a hard real-time media system, live, on a fixed deadline, for a high-stakes event. That's the same class of problem a voice agent poses: real-time transport, tight timing budgets, and no room to fail in front of the audience. Add roughly a decade of React and TypeScript plus Rust and Node backend work, and one engineer can own both the real-time surface and the agent behind it.

Every voice interaction can be signed and auditable

A voice agent that takes actions and speaks with authority raises an obvious question: what exactly did it say, and why? Hibiscus's core positioning answers it — production AI whose every decision is signed, anchored, and independently auditable. Every voice interaction can be captured in a tamper-evident audit trail signed with post-quantum cryptography (ML-DSA; provisional patent filed), so you can review what the agent said, what it retrieved, and which tools it called — after the fact, independently, without taking anyone's word for it.

For anything customer-facing, regulated, or high-stakes, that reviewability isn't a nice-to-have. It's the difference between deploying a voice agent you can stand behind and one you're quietly nervous about.

Scope a real-time voice agent

Tell me what conversation you want to automate and what it needs to look up or do. I'll tell you honestly what's straightforward, what's hard, and what it takes to make it work live. Remote (US) or Triangle-local; founding-engineer, senior/staff/director, or contract. SBIR-eligible small business.

Email blake@hibiscus.buzz
Ask to try the live voice agent — talking to it is the fastest proof.

Frequently asked questions

Who can build a real-time voice AI agent that actually works?
Someone who has already shipped one you can talk to, and who has real-time systems pedigree separate from AI. Hibiscus Consulting — the studio of founder-engineer Blake Burnette in Cary, North Carolina — has a live real-time voice agent in production, built on the same stack (model gateways routing tool-using agents, plus RAG for grounding) it uses for text and API agents, and the pedigree to match, including a WebRTC platform built for the Emmys in React in five weeks.
Why is real-time voice harder than a text chatbot?
Latency. A text bot can pause to think; a voice agent can't without the silence becoming awkward in under a second. Speech-to-text, the model's reasoning, any tool calls, and text-to-speech all share one sub-second budget, while the agent also has to handle interruptions, overlapping speech, and grounding its answers in real information rather than inventing them.
Can I actually talk to the voice agent, or is it just a demo video?
You can talk to it. There is a live real-time voice agent built by Hibiscus that handles a real back-and-forth conversation, not a scripted recording. A live agent can't hide the hard parts — interruptions, slow tool calls, admitting what it doesn't know — which is exactly why being able to talk to it is the best proof it works. Email blake@hibiscus.buzz to try it.
How does a voice agent stay grounded instead of making things up?
Through retrieval-augmented generation (RAG): the agent answers from real, current information retrieved for the question, with retrieval quality actually measured. Combined with model gateways that route tool-using agents and evaluation harnesses that backtest output against historical ground truth, the answers stay grounded rather than invented — the same production stack used for non-voice agents.
Can I review what the voice agent said and why?
Yes. Every voice interaction can be captured in a tamper-evident audit trail signed with post-quantum cryptography (ML-DSA; provisional patent filed), so you can independently review what the agent said, what it retrieved, and which tools it called. That reviewability is the core positioning: production AI whose every decision is signed, anchored, and independently auditable.