The phone rings while everyone is busy.
In a clinic, salon or trade business the people who could answer the phone are with a customer. Calls go to voicemail, and many callers try the next business instead of leaving a message.
The job is narrow and repetitive: most calls are someone wanting to book, move or cancel a time, or to check one. A receptionist that handles those reliably, and passes everything else to a person, gives staff their hands back without risking a wrong booking.
Today
- Calls during appointments go unanswered.
- Staff return calls between customers, often hours later.
- After-hours callers get voicemail.
With the receptionist
- Every call is answered at once, day or night.
- Bookings with a clear day and time are read back and written to the diary.
- Everything else becomes a short message for the team.
The build
A complete voice loop that runs on an ordinary computer: no GPU and no paid speech service.
Each call passes through five parts: speech-to-text, a reader that decides what the caller wants, a reader for spoken days and times ("the twenty first at seven", "tomorrow ten am"), a clinic diary, and a spoken reply. The agent never books on a guess: it reads every booking back and asks the caller to confirm.
Recorded calls through the full loop
Recordings from the SLURP test set, through the phone-line filter. Speech-to-text output is shown as produced, with unreadable characters removed. SLURP's requests were spoken to a home assistant, so some are reminders rather than appointments; the agent treats any "set" request as a booking.
How it works
The call, step by step
What it runs on
What it means for the front desk
Out of 598 test calls, this is what the agent’s first reply did.
Per 100 calls, about 35 need no staff time, 31 are rightly passed on as messages, and 31 are passed on although the agent could have handled them.
At 3 minutes of staff time per handled call, that is about 1.8 hours saved per 100 calls.
The cost of being careful is the 31% of calls passed on that the agent could have handled. Lowering the confidence bar would hand more calls to the agent but let more go the wrong way.
Behind the line
Method, results and failure cases.
Data and test design
- Speech: SLURP, a public set of people speaking requests to a voice assistant, recorded on a headset and from across the room. The study uses the headset recordings, which sound closest to a phone held to the ear, and passed every clip through a telephone-line filter (8 kHz, 300–3,400 Hz).
- Requests: SLURP's calendar requests ("set", "query", "remove") became book, check and cancel; a random selection of its other requests ("play some jazz", "make me a coffee") stand in for calls that aren't bookings.
- Split: the request reader learned only from SLURP's training text. The test recordings were split by sentence into a tuning half (553 recordings, used once to choose the confidence bar) and a reporting half (598 recordings of 362 sentences). No sentence is in both.
- Intervals: 95% bootstrap intervals, resampling sentences so that repeat recordings of one sentence move together.
Speech-to-text costs the most: request type drops from 91% on the human transcript to 78% on what it heard; the day reader drops from 100% to 84%.
On the tuning half, 0.85 was the lowest bar keeping wrong turns at or under 5%. On the reporting half it gave 7.0%: the target was not held.
All outcomes
| First reply | Agent | Keyword rules | Agent on the human transcript |
|---|---|---|---|
| booking, every detail right | 46 | 31 | 79 |
| booking, asks for the missing detail | 8 | 3 | 0 |
| booking, no detail given | 71 | 52 | 104 |
| check or cancel, right flow | 86 | 99 | 176 |
| passed to staff, correctly | 185 | 140 | 183 |
| passed to staff, could have been handled | 186 | 201 | 28 |
| booking, a detail misheard | 0 | 1 | 0 |
| wrong flow | 16 | 71 | 28 |
Reporting half: 598 recordings. "Could have been handled": the caller wanted to book, check or cancel, but the agent wasn’t confident enough.
Speed on an ordinary computer
Speech-to-text took a median 0.51 s for a median 2.8 s request (90th percentile 0.63 s), about 0.22 s per second of speech. Understanding and the diary take a few milliseconds, and the spoken reply 0.38–0.69 s on the four calls above, so the caller hears an answer roughly a second after they stop talking.
Findings
The problem in real terms
A physiotherapy, dental or allied-health clinic with two to six practitioners and one person on the front desk. That person is also checking patients in, taking payments and answering Medicare and health-fund questions, so the phone rings out in the busiest hours and goes to voicemail after 5 pm. Call audits in Australian multi-site clinics put unanswered calls at around one in ten, and practices that add an automated line report a large share of calls handled without the desk, most of them bookings.
- Team
- One receptionist, sometimes shared across two sites
- Systems
- Cliniko, Halaxy, Nookal or Timely diary; a VoIP line from Telstra, Aussie Broadband or Twilio
- Calls
- Mostly book, move, cancel or check a time; a minority are clinical or billing questions for a person
- Constraints
- Privacy Act and the APPs for health information; call-recording consent; no clinical advice
Baselines
| Where calls went wrong | Calls |
|---|---|
| Misheard the request type | 34 |
| Request type missed on the human transcript too | 26 |
| Day misheard | 12 |
| Time misheard | 8 |
Assumptions
- Three minutes of staff time per handled call.
- Headset recordings through a telephone filter stand in for mobile calls; far-field recordings were much worse (word error 67% against 35%).
- SLURP calendar requests stand in for appointment calls.
What a clinic would do next
- Week 1: connect the diary read-only and route after-hours calls to the receptionist, with staff call-back on every message.
- Weeks 2 to 4: record consenting calls, re-measure word error and wrong turns on the clinic’s own callers.
- Weeks 5 to 8: allow bookings with read-back; keep cancellations and anything clinical with staff.
- Then: review missed-call rate, after-hours bookings and wrong bookings monthly.
Limits, and what comes next
- SLURP was recorded for home assistants, not clinics. The accents, phrasing and background noise of real callers will differ, so a pilot should re-measure on the business's own calls (with consent).
- The phone connection itself is not part of this study: the agent ran on recorded calls. A live line needs a SIP or telephony provider and call recording consent.
- A larger speech model (small.en or a hosted one) should cut misheard words, at several times the computing time. I have not measured it here.
- The agent only books, checks and cancels. It takes no payments and gives no advice; a live version should also send urgent callers straight to a person.
Run it yourself
# code MIT; SLURP audio and text CC BY 4.0 git clone https://github.com/manazafzal/case-studies && cd case-studies/ai-receptionist/code python -m venv .venv && . .venv/bin/activate && pip install -r requirements.txt python asr.py test base.en 800 asr_test_base.parquet # about 25 minutes on three CPU cores python agent.py receptionist.json && python media.py
Run 18 Nov 2026, 23:42 AEDT (Melbourne time) · seed 20261118
Sources
- Bastianelli, E., Vanzo, A., Swietojanski, P. & Rieser, V. (2020). SLURP: a spoken language understanding resource package. EMNLP. Data CC BY 4.0, via huggingface.co/datasets/marcel-gohsen/slurp.
- Radford, A. et al. (2023). Robust speech recognition via large-scale weak supervision (Whisper). ICML. Run with faster-whisper (SYSTRAN).
- Piper text-to-speech (Rhasspy / Open Home Foundation), en_GB alba medium voice.