The voice assistant that greets guests in their own language, checks availability and passes special requests to your team
For front office and reservations teams: availability, check-in and facility questions go to the assistant; rates and bookings are confirmed by current system conditions and the guest's approval.
Common problems on the phone line
Calls in many languages
Calls from international guests wait until a colleague who speaks the language is free.
Phone and guests at the front desk
At busy check-in times, the ringing phone either goes unanswered or keeps the next guest waiting.
Special requests are not written down
Requests such as transfers or early check-in are discussed on the phone but do not always reach the right team.
How it works in this sector
Every call follows the same four steps; the assistant acts only with defined permissions.
- 01 / 04
Greets
Greets the guest and listens to the dates and number of guests.
- 02 / 04
Understands and verifies
Clarifies the dates and number of guests by reading them back.
- 03 / 04
Takes action
Checks availability in the connected booking system.
- 04 / 04
Confirms or hands off
Leaves the booking to the guest's confirmation; passes transfers and special requests to the team.
What the assistant takes on
Handles booking enquiries and forwards special requests to the relevant team.
- Availability and booking requests
- Check-in, check-out and facilities
- Transfers and special requests
- Dates and number of guests read back for confirmation
- Voice replies in the guest's language
Example call
A fictional scenario: what the caller says, what the assistant understands and how it replies.
- Caller
- “I need a room for two people for two nights this weekend.”
- Detected request
- Stay request · 2 people · 2 nights · Weekend
- Assistant response
- I can clarify the dates and check availability. Rates and bookings depend on current system conditions and your confirmation.
Availability and rates come from the connected booking system; this example is not a quote.
Illustrative example · Not live system data
Related integrations
The assistant connects to your systems only with defined permissions; your PBX setup is reviewed during discovery.
Netgsm 0850 / SIP Trunk
Carrier line (SIP Trunk)
Booking system · CRM
API access only with defined permissions
Operator handoff
Calls that need a person, plus fallback routing
Call summary to the CRM
The call summary is written to the relevant record
Runs on your own server
- Your data stays in-house.
- A single GPU server is enough.
- Several calls at the same time, on the same system.
The architecture supports your compliance processes with restricted API access, configurable retention and operator fallback. Compliance depends on the deployment configuration, data processing practices and your organizational procedures.
The path of a call
- 01Phone lineNetgsm 0850 · SIP Trunk
- 02PBXAsterisk
- 03Your serverSTT → LLM → TTS
- 04Your systemsBooking system · CRM
Frequently asked questions
- Does it quote rates?
- Availability and rates come from the connected booking system. The rate and the booking are confirmed by current system conditions and the guest's approval.
- Which languages does it support?
- It speaks and replies by voice in 30 languages, and understands and transcribes more than 99. Live validation was done in Turkish; in other languages, voice and recognition quality may vary by language.
- Does voice data leave the organization?
- No. Speech-to-text, response generation and speech synthesis run on your own server; your data stays in-house. Calls arrive through your telephone carrier and PBX.
- What if the agent can't resolve a request?
- Calls that need a person are transferred to an operator, with fallback routing in place.
Request a demo
Your sector is preselected in the form. Briefly describe your call scenario, and we will schedule an online meeting at a time that suits you.
Let's plan your phone line together
In a discovery call we go through your call flows and the systems to connect.
* Footnote: Latency values were measured on real call recordings (from the moment the caller stops speaking until the first sound arrives, server side). Internet latency adds 0.05–0.3 s. Word error rate was measured on the public FLEURS-tr dataset (200 sentences, 8 kHz telephone audio). Language support is at model level. Live validation was done in Turkish; in other languages, voice and recognition quality may vary by language.
