Live Translation with OpenAI's Realtime API: how an AI phone agent actually works, and what it costs to run
Most businesses do not need a robot that can talk about anything. They need one that can handle the same twenty calls a day, perfectly, and know when to stop.
- 14:02Call from +61 4** *** 219 rings out. Everyone is on a roof.
- 14:02Number checked: mobile, not a known spam range.
- 14:02SMS out: “Sorry we missed you, it’s Dan at Coastline.”
- 14:03Reply: “hot water system leaking, can someone come today”
- 14:03Dan paged. Job drafted with the transcript attached.
- 14:04Booked. Nobody touched a phone.
What it actually does
A speech pipeline sits on the call: audio in, transcription, a language model deciding what to say, speech back out, all inside the latency budget a human conversation tolerates.
A programmable contact centre: agent tooling, authentication, canned responses, live translation and web chat. In practice, Live Translation with OpenAI's Realtime API is the version of that we deploy when a business needs the result rather than a project. The foundation is maintained by Twilio itself, which is the strongest signal a sample will still work next year. That matters more than it sounds: the failure modes have already been found by someone else, in public.
Why businesses ask for this
Once you pass a handful of people answering calls and messages, routing and visibility matter more than the phone system itself. A programmable contact centre is configured to your process instead of the other way around.
The people who get the most out of it: teams of five or more answering calls and messages all day.
- Calls and chats routed by skill, hours and priority
- Agents see the customer record on answer, not after
- Supervisors get real numbers on volume, wait and resolution
How we build it, step by step
The sequence below is the one we follow on every Conversational AI build. It is deliberately boring, because the interesting version is the one that breaks in month three.
- Define the narrow job the agent is allowed to do and what it must hand off
- Write the system prompt and the refusal cases before writing any code
- Instrument every turn so you can read back exactly what was said
- Set a hard escalation path to a human on confusion, silence or request
What we change before it goes live
A reference implementation is a starting line, not a product. Every one we deploy gets the same treatment:
- Your numbers, your sender identity and your wording, so nothing reads as generic
- Secrets moved out of the code and into managed configuration
- Retries, rate limits and idempotency, so a hiccup never sends twice
- Structured logging and alerting, so a failure is noticed by us and not by a customer
- Consent, opt-out and record-keeping built in rather than bolted on
- Source control, a staging environment and a rollback that takes a minute
Compliance and risk
Contact centre projects fail on change management, not technology. We roll out to one queue first, measure, then widen.
The technical foundation
Twilio Flex with custom plugins, single sign-on, and integrations into your CRM.
- javascript — Node.js, which is where most of this ecosystem lives and where we default unless you have a reason otherwise.
The open-source starting point sits here, and it stays public whether you work with us or not:
Upstream last updated 2026-06-18.
What it costs
Three ways to buy this, and the honest recommendation is usually the middle one:
- Starter build, from $2,500 — we build it, hand it over and warrant it for 30 days. Suits a business with someone technical in-house.
- Managed, from $390/mo — we build it and then own it: monitoring, changes, compliance upkeep and a monthly report. Suits everyone else.
- Platform, from $2,400/mo — when this is one of several systems and you want them designed as one layer instead of five.
Platform usage is billed at cost on top and itemised on the invoice. There is no margin on it and no minimum spend.
Common questions
How long does Live Translation with OpenAI's Realtime API take to build?
For a standard configuration, about a week from kick-off to a staging number you can test on, then a few days of live monitoring before we call it done. Anything involving a port of an existing phone number adds one to two weeks of carrier time that nobody controls.
What does it cost to run each month?
Two lines: our managed plan from from $390/mo, and platform usage billed at cost. Usage for this kind of system usually lands between $30 and $300 a month depending on volume. You see both itemised, and the platform account stays in your name.
Do we own it, or are we locked in?
You own it. The account, the numbers, the phone history and the source code are yours, and the foundation is open source. If you take it in-house, we hand over the repository and the runbook and that is the end of the conversation.
What if it breaks at 6pm on a Friday?
It is monitored. Failures raise an alert, the system degrades to something safe rather than silent, and hello@betr.agency is the inbox that answers. That is what the managed plan buys.
Can it work with the systems we already use?
Usually yes. Twilio Flex with custom plugins, single sign-on, and integrations into your CRM. Where a system has no API, we look at whether an export, a shared inbox or a scheduled sync gets you 90 percent of the value for 10 percent of the cost.
Where to next
The product page for this build lists the specification, the timeline and what is included: Live Translation with OpenAI's Realtime API. If you want to talk it through against your actual process, a scoping call is 30 minutes and costs nothing.