Restaurant phone greetings and voice phrases
A restaurant phone needs a welcome, a menu of options and a handful of lines for the busy moments: you are on the waitlist, your table is ready, we will hold your table for ten minutes. These are those lines, spoken in natural voices and checked before they were added. Allergy lines never promise a dish is allergen-free.
Looking for the receptionist, not the voice lines? The AI side of this trade, with bookings, reminders and texts, is on ai answering service for restaurants. This page is for the voice phrases and phone greetings themselves.
Lines for restaurants
A few of the situations the restaurants pack has lines for. Each one is written for this situation, spoken in a natural synthetic voice and checked before it was added.
- Thank you for calling, are you booking a table or ordering?
- You are on the waitlist, we will text you.
- Your table is ready.
- We will hold your table for ten minutes.
- We have noted your allergy and the kitchen is aware.
- How was your visit with us?
Related trades
ai phone assistant for food trucks and bars · ai phone agent for farm stands and markets · ai receptionist for hotels
What an AI receptionist costs · Pay-once alternatives · Every agent feature · AI front desk by industry · All industries
Example lines
- “Thanks for calling, how can I help you today?”
- “Hi there, what can I do for you?”
- “You've reached us, what can I help you with?”
Packs and prices
| Voice | Phrases | Size | Price (once): audio only / with the agent | |
|---|---|---|---|---|
| ph_delia | 3,839 | 127.0 MB | $49 / $249 | Free sample · Buy |
| ph_alfie | 3,839 | 121.3 MB | $49 / $249 | Free sample · Buy |
| ph_easton | 3,839 | 118.7 MB | $49 / $249 | Free sample · Buy |
| ph_everly | 3,839 | 127.8 MB | $49 / $249 | Free sample · Buy |
| ph_juniper | 3,839 | 126.3 MB | $49 / $249 | Free sample · Buy |
| ph_pippa | 3,839 | 127.1 MB | $49 / $249 | Free sample · Buy |
| pk_jasper | 3,839 | 114.3 MB | $49 / $249 | Free sample · Buy |
Also in other languages
Native-speaker review pending.
| Language | Voice | Phrases | Price (once): audio only / with the agent | |
|---|---|---|---|---|
| ar | chatterbox-ar | 500 | $24 / $224 | Free sample · Buy |
| de | chatterbox-de | 384 | $14 / $214 | Free sample · Buy |
| Spanish | ef_dora | 837 | $24 / $224 | Free sample · Buy |
| Spanish | em_alex | 500 | $14 / $214 | Free sample · Buy |
| French | ff_siwis | 646 | $14 / $214 | Free sample · Buy |
| Hindi | hm_omega | 654 | $24 / $224 | Free sample · Buy |
| Hindi | hf_alpha | 646 | $24 / $224 | Free sample · Buy |
| Italian | if_sara | 500 | $14 / $214 | Free sample · Buy |
| Italian | im_nicola | 500 | $14 / $214 | Free sample · Buy |
| Japanese | jf_alpha | 836 | $24 / $224 | Free sample · Buy |
| Japanese | jm_kumo | 835 | $24 / $224 | Free sample · Buy |
| Portuguese | pf_dora | 764 | $24 / $224 | Free sample · Buy |
| Portuguese | pm_alex | 500 | $14 / $214 | Free sample · Buy |
| ru | chatterbox-ru | 500 | $24 / $224 | Free sample · Buy |
| Mandarin Chinese | zf_001 | 554 | $14 / $214 | Free sample · Buy |
| Mandarin Chinese | zm_009 | 500 | $14 / $214 | Free sample · Buy |
When a line is not in your pack
A pack covers the common restaurants and food lines, but a customer will sooner or later need one it does not have. With your API key the new line is voiced on demand:
- It arrives fast. In our November 21, 2026 test, an English catalog voice reached the first audible sound in 44 ms with a Phonon voice, from a client in AWS us-east-1 (our own measurement, using the Coval test method).
- You pay once for it. $3 per million characters, about $0.0002 for a 60-character line, paid when the line is voiced.
- It joins your library. The local agent (version 0.40 or later) saves the audio on your computer and maps it to a slot, so the next time it plays from disk, instantly, with no internet and no charge, and the same words are not voiced or charged twice. Saved lines keep playing if you later stop using the key; speaking new lines needs a working key.
- Your own AI can write it. If you connect an AI of your own, it can write the reply, and Speakvora voices it as soon as the text exists (how fast the words appear depends on that AI). Lines that hold a name, a number or a link are spoken but are not added to the library automatically, so customer details stay out of it.
The voices are AI-generated. Details and method: text to speech latency · grow your voice library.
What is in this agent
- Library: approved, pre-recorded restaurants and food lines, one payment per voice and location, no per-play fee, the first 12 months of support and upgrades included with the industry agent (afterwards everything you downloaded keeps working for ever; support and upgrades after that are an optional support plan at $99 a year per location), and you can request lines that are missing.
- Agent: open-source, runs on your own machine with ready-made workflows for this industry. You configure it to handle the routine questions and events you choose, from your recordings: no per-turn or per-minute charge from us.
- Offline: the recordings play with no connection; texts, calls and posts queue when the internet drops and go out in order when it returns. Anything that may or may not have arrived is held for your review, not sent again by itself.
- API: the same voices through the speak API for any new sentence ($3 per million characters, $3 for your own voice).
More sample lines
These come from the free 25-sentence sample of the Restaurants and food pack, so you can judge the writing before you buy. Each line was written for this situation and checked before it was added.
Restaurants food
- A full refund is absolutely the right solution here.
- A new order is being prepared for you now.
- Absolutely, high chairs are part of our standard seating options.
- Accessible parking spaces are located near the side entrance.
- Adjustments can be made to suit your taste.
- Alert: ground beef delivery from this morning has been flagged for recall.
Coffee shop bakery
- A restroom is available in the back of the shop for customers.
- Absolutely, whole unsliced cakes are available for order.
Grocery supermarket
- A staff member should be able to assist you by opening the door manually from inside.
- A supervisor is heading to the front end to help manage the checkout lines now.
- A supervisor will follow up with you shortly regarding this incident.
- Accessible parking availability is currently good.
- Accessible parking requires a valid permit or license plate.
- Accessible parking spots are clearly marked with signage.
- Accessible spaces include van-accessible spots with extra room.
- Accessible spots are located in the front section.
Drive through fast food
- Absolutely no problem, we're on it.
- Absolutely we can do that, extra toppings are available on any burger.
- Absolutely, go right ahead and add whatever extra toppings you're in the mood for.
- Absolutely, just pull around to the pickup window and we'll have it ready.
- Absolutely, we can load that burger up with whatever extra toppings you'd like.
- Absolutely, we'd be happy to add extra sauce on the side for you.
- Absolutely, we'd be happy to make that right for you today.
- Absolutely, we'll pack additional napkins along with your order.
- Advance reservations aren't supported through this ordering channel right now.
What the included agent does for restaurants and food
Every pack includes the open-source pack agent. It runs on your own server, uses your own phone, Slack, Teams, calendar and email accounts, and only says the approved sentences. For this industry it ships with 93 ready-made workflows: 42 written for it and 51 that react to events in your app, for example:
- Passes allergy questions to a person: when a customer texts, then a reservation, a reply, a staff alert.
- Confirms a new order: when your app sends an event, then an order status, a text.
- Says an order is being made: when your app sends an event, then an order status, a text.
- Thanks customers after they collect: when your app sends an event, then an order status, a text.
- Tells customers their delivery is on its way: when your app sends an event, then an order status, a text.
- Confirms a delivery: when your app sends an event, then an order status, a text.
- Confirms a cancelled order: when your app sends an event, then an order status, a text.
- Tells customers their order is ready: when your app sends an event, then an order status, a text, a phone call, a Slack message.
- Says sorry when an order is late: when your app sends an event, then an order status, a text, a Slack message.
- Tells guests their table is ready: when your app sends an event, then a text, a Slack message.
- Confirms a table booking: when your app sends an event, then a text, a calendar entry, a Slack message.
- Follows up on a missed reservation: when your app sends an event, then a reservation, a text.
- Asks for a review after a visit: when your app sends an event, then a reservation, a text.
- Passes questions that need a person to your team: when a customer texts, then a reply, a staff alert.
It starts in practice mode, so nothing goes out until you switch it on, it always honours STOP replies, and the texts and calls need your own providers and an internet connection (when it drops, they wait in a queue and go out in order when it returns; anything it cannot confirm arrived is held for your review, not sent again by itself). How the agent works.
How people use a pack like this
- Phone menus and voicemail greetings. Load the files into the phone system you already have.
- Kiosks and devices. Ship the audio with the device so it speaks with no network call and no per-play fee.
- App notifications. Play the right file when an event happens, such as an order or appointment update.
- Anything not in the pack. Use the Speakvora API for new sentences and
POST /v1/prepareto get your own lines ready ahead of time.
Before you buy
- Format: M4A (AAC) audio, one file per line, with a manifest.json that maps each sentence to its file and a CSV.
- Licence: commercial use in your own systems and your company group's systems; no resale or redistribution of the audio files. Read the licence first.
- Voices: synthetic voices, not real people. Tell listeners where the law or good practice requires it.
- Free sample and updates: every voice has a free 25-sentence sample, and updates and support are included for 12 months per business location (afterwards everything you downloaded keeps working for ever; the support plan is optional and never automatic).
- Price: one time per voice, with no subscription and no meter.
Questions
What should a restaurant's phone greeting say?
Who you are, your hours, a way to book, and a line for takeaway. The pack has them, in several tones.
Is there a line for allergies?
There is a line that says an allergy was noted, and the rules block any promise that food is allergen-free or safe for an allergy.
Is this the AI answering service for restaurants, or only the voice lines?
Only the voice lines. Table bookings, hours and menu answers, and the waitlist texts, belong to the restaurant answering service page linked above.
What do I get?
A zip with one audio file per line, a manifest.json that maps each sentence to its file, a CSV and a licence. The largest restaurants and food pack has 3,839 recorded lines; smaller packs have fewer, as the table shows. Every pack also has a free 25-phrase sample.
Can I use the audio offline and commercially?
Yes. You may ship the audio inside your own apps, kiosks, phone systems and devices. You may not resell or redistribute the files themselves.
How is it priced?
Paid once per business location. Audio only is from $49; with the local agent, dashboard and workflows it is from $249, with the first 12 months of support and upgrades included and an optional $99 a year after that. Compare human voice-over at about $80 per 100 words. What you download keeps working for ever.
Are the voices real people?
No. They are synthetic voices. Disclose that to listeners where the law or good practice requires it.
Can I get lines that are not in the pack?
Yes. With your API key a new line is voiced on demand: in our November 21, 2026 test the first audio reached the listener in about 44 ms for an English Phonon voice, and the local agent can save the line on your computer so it plays instantly and free from then on.
What does a new line cost, and do I pay again for it?
$3 per million characters, about $0.0002 for a 60-character line, paid once when the line is voiced. The agent keeps the audio on your computer, and the same words are not voiced or charged twice.
Do saved lines still play if I stop using my API key?
Yes. Saved lines are files on your computer. They play with no internet and no further charge, and nothing shuts them off remotely. Speaking new lines needs a working key.
How fast is a new line, really?
Our own measurement, not a third-party benchmark: 44 ms to the first audible sound for a Phonon voice, measured from one client in AWS us-east-1, one request at a time, with the voices streamed from our Mac mini over the public internet, November 21, 2026 (add your network time). The speed depends on your connection.