Decision Framework

Build or Buy? AI Receptionists in Canada After GPT-Live-1

OpenAI's GPT-Live-1 and Google's Gemini 3.8 Live shipped five days apart and cut real-time voice to cents a minute. For a Canadian clinic or small business, the model was never the expensive part — here's how to decide whether to build on the new APIs or buy a managed AI receptionist.

The short answer: the models got cheap this week, not the receptionist. On 10 September 2026 OpenAI shipped GPT-Live-1, a full-duplex voice layer at US$0.05 a minute; five days later Google answered with Gemini 3.8 Live. Voice is now close to a commodity input, but a working AI receptionist is still the backend model, the integrations, the call-flow design, the testing, and, for a Canadian clinic, the data-residency and PHIPA/PIPEDA work around it. Buying remains the sounder call for most Ontario clinics; building on the new APIs is now viable for a technical founder running a non-health business with low-stakes calls. This post is the framework for telling which one you are.

Key takeaways

  • OpenAI's GPT-Live-1 (10 September) and Google's Gemini 3.8 Live (15 September) both shipped new real-time voice models within five days of each other; OpenAI's is explicitly built for phone calls.
  • GPT-Live-1's US$0.05/minute, about CA$0.07, covers only the front-end voice layer — the backend model and tools are billed separately.
  • Google's published rate card lists Gemini Live audio at US$0.005/minute input and US$0.018/minute output.
  • OpenAI's data-controls docs list GPT-Live residency in the US and Europe only; its Canada region is storage-only and excludes GPT-Live and Realtime.
  • PIPEDA allows cross-border processing but keeps the organization accountable; PHIPA sets no "stay in Canada" rule but keeps the custodian responsible for safeguarding data.
  • Orchestration platforms such as Retell AI list US$0.07–$0.31/minute for the voice agent itself — a benchmark for what assembling the pieces costs.

What shipped this week

On 10 September 2026, OpenAI introduced GPT-Live-1 in its API: a voice model built for full-duplex conversation, meaning it can listen and speak at once instead of waiting for a caller to finish talking. OpenAI says the model handles interruptions naturally, delegates reasoning and tool calls to a backend model of your choosing, and is built for telephony: it "enables deployment of full-duplex voice agents for phone calls, from restaurant reservations to customer support." Twelve new voices shipped with it, and OpenAI reports a 30-percentage-point improvement over GPT-Realtime-2.1 on Full Duplex Bench. Yelp's CTO, Alex Levy, said GPT-Live-1 is delivering "meaningful improvements in call handling rates," and Speak reported cutting thinking-pause interruptions by almost 80% versus older turn-based systems. (OpenAI, 10 September 2026)

Five days later, Google answered with Gemini 3.8 Live and a companion Extended Thinking variant, reporting 82.6 on Artificial Analysis's Speech to Speech Quality Index and 68.6% on τ-Voice, a benchmark for agentic task completion in conversation. It detects and switches between 97 languages mid-conversation and runs tool calls in the background without interrupting speech; generated audio carries a SynthID watermark. It's rolling out in the Gemini API and AI Studio, with Gemini Enterprise in private preview. (Google, 15 September 2026)

What the per-minute price really covers

The headline number is US$0.05 per minute, and it's tempting to read that as the whole AI voice agent cost per minute. It isn't. OpenAI's own wording is specific: "GPT‑Live‑1 is available in the API today at $0.05 per minute for the front-end voice layer. Pair it with the backend model and agent harness that fit your product…" That price covers listening and speaking. The reasoning, and any tool calls such as checking a calendar, come from a separate backend model billed separately.

A worked example: at the Bank of Canada's 16 September 2026 rate of 1.3947, US$0.05 is roughly CA$0.07 a minute. A clinic doing 1,000 call-minutes a month would pay 1,000 × US$0.05 = US$50, about CA$70, for the voice layer alone, before backend-model token charges and telephony. Twilio's Canada voice pricing lists inbound local calls at $0.0085 a minute plus $1.15 a month for a local number. This is illustrative arithmetic, not a quote. (Bank of Canada, Twilio Canada voice pricing)

Orchestration platforms that bundle the voice layer, backend model and tooling price the assembled pipeline as one per-minute rate: Retell AI's public pricing lists pay-as-you-go voice agents at US$0.07–$0.31 a minute depending on the LLM and voice chosen, with telephony on top. (Retell AI pricing)

What the API doesn't give you: the receptionist around the model

A per-minute price for a voice model is not a receptionist. Between "the model can hold a phone conversation" and "the phone rings and gets handled correctly" sits a list of work that doesn't show up on OpenAI's or Google's pricing page:

None of this is exotic engineering, but it's real project time, whether you build on GPT-Live-1 or on Gemini 3.8 Live. See our guide to what a custom AI agent costs to build, or our Pilot-to-Production Deployment service for what the work looks like end to end.

The Canadian catch: where the audio is processed

Here's the catch for a business operating under Canadian data residency expectations. OpenAI's data-controls documentation is specific: "GPT-Live supports data residency in the United States and Europe. Delegated backend models and tools have their own data controls." OpenAI's Canada region is storage-only, with no in-region processing, and GPT-Live and Realtime endpoints aren't among the services listed for it. Sessions are eligible for zero data retention, and session storage is off by default (if you switch it on, a completed recording is kept for 30 days) — but that doesn't change where the audio is processed while the call happens. (OpenAI data controls documentation, checked 17 September 2026)

For Gemini 3.8 Live, we did not find official confirmation that Google can process the audio in a Canadian region. If that matters, and for a clinic it does, get it confirmed in writing from Google first.

The price tells you what the voice layer costs, not where your callers' voices are processed. For an Ontario clinic booking patients by phone, that's not a footnote — see our note on responsible AI in Canada for how we think about Canadian data residency at the architecture stage.

PHIPA and PIPEDA: what they actually require

Two Canadian privacy regimes touch this decision, and neither one gives a simple yes-or-no answer on where data has to live.

PIPEDA doesn't ban cross-border processing. The Office of the Privacy Commissioner of Canada's guidance is direct: "PIPEDA does not prohibit organizations in Canada from transferring personal information to an organization in another jurisdiction for processing." But accountability stays put: "The transferring organization is accountable for the information in the hands of the organization to which it has been transferred." Customers must be told their information may cross the border and could be accessed by that country's courts or authorities. (Office of the Privacy Commissioner of Canada)

Ontario's PHIPA adds a layer for health information custodians — a dental or physiotherapy clinic answering the phone about a patient's care. There's no blanket rule that health information must stay in Canada; PHIPA requires the custodian take reasonable steps to safeguard it (section 12) and remain responsible for vendors handling it on the custodian's behalf. A caller explaining why they need an appointment is disclosing health information the moment they say it. The Information and Privacy Commissioner of Ontario's guidance, "AI Scribes: Key Considerations for the Health Sector" (28 January 2026), is the closest regulator guidance to an AI system that records patient conversations, and is worth reading directly. (IPC of Ontario)

None of this is legal advice; talk to a privacy lawyer about your specific obligations. If federal AI legislation is relevant to your business, see our separate note on Bill C-36. Keeping processing and storage in Canada isn't the only lawful route, but it removes the cross-border questions entirely — one reason we built Maya that way.

A build-vs-buy comparison table

Laid out side by side, the three paths differ less in what's technically possible than in who owns the work of getting there.

FactorDIY on the raw APICustom build with a partnerManaged receptionist
Setup timeWeeks to months, depends on in-house timeTypically weeks, scoped up frontLive in days
Who owns integration & upkeepYouPartner builds it; you or the partner maintain itThe vendor
Data residencyWhatever the model vendor offers — confirm in writingChosen deliberately at the architecture stageSet by the vendor's existing architecture
PHIPA / PIPEDA paperworkYours to work outBuilt into the scoping phaseHandled by the vendor's existing setup
Ongoing engineeringRequired indefinitelyNeeded for changes, less for day-to-dayMinimal — the subscription covers upkeep
Cost shapeVariable, per-minute plus your timeFixed project fee, scoped up frontFixed monthly subscription
Best forTechnical founder, non-health business, low stakesRegulated or complex workflow, wants ownershipClinic or SMB that wants it live without building a team

When building makes sense

Building a custom AI voice agent on GPT-Live-1 or Gemini 3.8 Live is reasonable for a non-health business with an engineer to own the integration, and calls where a wrong answer costs little more than a redo — a quote line, an order-status line, an internal helpdesk.

What building doesn't remove is the list above: designing the call flow, connecting it to your booking system, testing it against real callers, watching it once live. If that's more time than you have, price out a scoped custom build first — see our AI agent cost guide for Canadian numbers.

When buying makes sense

Buying a managed receptionist is the sounder default for a Canadian clinic. Health information comes up on many calls, which puts you inside PHIPA's custodian duties from the first ring. A vendor that has already made the data-residency and compliance decisions removes that research project from your to-do list.

It's also right for any small business without engineering time for ongoing upkeep. Mihron AI's Maya is an AI phone answering service for exactly that: an AI voice receptionist for dental clinics and other Ontario SMBs, bilingual in English and French (see our note on bilingual AI receptionists), purpose-built for dental clinics including Canadian Dental Care Plan questions, hosted in a Canadian Supabase region with row-level security per clinic. Plans start at CA$299 a month. Our buyer's checklist covers what to ask before you sign any managed receptionist.

What we would do with these models at Mihron

To be direct: Maya does not run on GPT-Live-1 or Gemini 3.8 Live. Its stack today is Retell AI for orchestration, Anthropic's Claude API for reasoning, Deepgram Nova-3 for speech-to-text and Cartesia Sonic for text-to-speech, over Twilio and Vonage telephony, with data in a Canadian Supabase region.

We're not ignoring what shipped this week. Before routing any call through a new voice model, we'd benchmark it against our current stack using test scripts and consented call recordings. We wouldn't route an Ontario clinic's calls through an endpoint that can't process audio in Canada, or under terms a health custodian can't accept — which rules out GPT-Live-1 for us in that use case today, whatever the voice quality. If either vendor extends Canadian processing, that changes the calculus. This is the first question our AI Readiness Sprint (CA$5,000–9,500) answers, feeding into a fixed-fee, scoped-up-front AI Agent & Workflow Build.

Next steps

If you're deciding between building and buying, start with the honest question: what happens on your calls, who owns the integration a year from now, and where does the audio need to live. A scoped AI Readiness Sprint answers that with your own numbers. If a managed receptionist fits better, hear Maya on our live demo or call 437-367-8009. For build vs buy at enterprise scale, see our related post on build vs buy for enterprise GenAI, and for the guardrails question next door, see AI agent guardrails.

People Also Ask

Build vs Buy AI Receptionist FAQ

Should a Canadian clinic build its own AI receptionist with GPT-Live-1 or Gemini Live?
For most Ontario healthcare clinics, no. GPT-Live-1 and Gemini Live are voice layers, not receptionists: you still pair a backend model, build the booking integration, design the call flow, test it against real callers, and decide where the audio is processed. A clinic handling health information needs that settled before a call goes live. A non-health business with a technical founder and low-stakes calls can reasonably prototype on the raw API; a clinic booking patients is a different risk category.
What does GPT-Live-1's $0.05-per-minute price actually cover?
OpenAI's own announcement is specific that the $0.05 US per minute covers only the front-end voice layer, the part that listens and speaks. You still pair it with a separate backend model and agent harness for the reasoning and tool calls, billed separately by usage. On top of that sits telephony and the integration work that turns a voice layer into something that can actually answer your phone.
Is it legal to process a Canadian patient's voice data in the United States?
PIPEDA does not prohibit sending personal information to another jurisdiction for processing, but the Canadian organization stays accountable for it and must tell customers their information may cross the border and could be accessed by that country's courts or authorities. Ontario's PHIPA has no blanket rule requiring health information to stay in Canada, but the custodian remains responsible for taking reasonable steps to safeguard it and for any vendor handling it. This is general information, not legal advice.
Can Gemini Live or GPT-Live-1 be processed in a Canadian data centre?
OpenAI's data controls documentation lists GPT-Live data residency in the United States and Europe only; its Canada region is storage-only and does not list GPT-Live or Realtime among the services covered. We did not find official confirmation that Google can process Gemini Live audio in a Canadian region. Confirm this in writing with the vendor rather than assuming either way.
When does it make sense to buy a managed AI receptionist instead of building one?
Buying makes more sense when calls involve health or sensitive information, when there is no in-house team to own integrations and upkeep, or when the business wants data-residency and compliance decisions already made. Building makes more sense when a technical founder wants full control, the business is not handling regulated data, and engineering time is available to maintain the system. Many Canadian clinics start with a scoped readiness sprint to make that call with real numbers.

Not Sure Whether to Build or Buy?

Hear Maya answer a call, or book a scoped readiness sprint before you write a line of integration code.