AI glossary · Voice
Voicebot
In one sentence
A voicebot is a program that holds spoken conversations: it listens to what a person says, works out what they want and answers out loud. It can run on a phone line, a website, an app or a smart speaker, and with generative AI it handles open conversation, not just menus.
Also known as: voice bot · voice assistant · voice agent · AI voice bot
What is a voicebot?
A voicebot is the spoken counterpart of a chatbot. For years these systems were rigid: they recognised a handful of keywords and followed a decision tree. Today’s language models change that: a voicebot understands everyday sentences, keeps track of the conversation and, if it’s connected to tools, gets things done. When it carries out whole tasks it’s usually called a voice agent, a type of AI agent.
Put it to work
A voice agent that picks up the phone
From €149/mo + VAT
It answers calls 24/7, books appointments and logs every call in the CRM.
See the voice agentWhen a voicebot works on a phone line, it’s also called a callbot.
Related to this term
UTIO Voice
- 500 minutes and a number included
- Natural conversation in 26 languages
- Introduces itself as a virtual assistant
- 14-day free trial, no card needed
From €149/mo + VAT
See the voice agentHow it works
The most common design chains three parts together:
- Ears: speech to text. The caller’s voice is turned into text as they speak.
- Brain: a language model. It interprets the text, decides on a reply and, if needed, checks the calendar or the CRM.
- Mouth: text to speech. The written reply becomes synthetic speech.
Some recent systems use models that go straight from speech to speech, with no text in between. Either way, the latency of the whole chain decides whether the exchange sounds natural or like an answering machine.
| Traditional IVR | AI voicebot | |
|---|---|---|
| How you talk to it | Keypad or single words | Everyday sentences |
| What it handles | Routes you to a department | Answers, books, takes details |
| If the caller goes off script | Repeats the menu | Rephrases or hands over to a person |
Example
A language school in Edinburgh is swamped with calls every September, nearly all asking the same things: timetables, levels and fees. A voicebot takes the calls, explains which groups have places, takes the name and number of anyone who wants a placement test and books it in the calendar. Trickier calls, such as a complaint, are transferred to the office with a summary.
Voicebots at UTIO
UTIO’s voice agent is a voicebot that works on your phone line: it answers 24/7, introduces itself as a virtual assistant and converses in 26 languages. It books into real free slots in your Google Calendar, qualifies callers, takes messages and transfers the call by time of day, by topic or when the caller asks.
Numbers and minutes are included in the monthly fee, together with the CRM where every call is logged. Recordings and transcripts are stored in Spain.
Frequently asked questions
What is the difference between a voicebot and an IVR?
A traditional IVR offers a fixed menu: “press 1 for sales”. A voicebot understands free speech, such as “I need to move my Tuesday appointment”, and responds accordingly. Many voicebots replace the IVR or sit in front of it.
Are voicebots and callbots the same thing?
Almost. A callbot is a voicebot working inside a phone call, inbound or outbound. Voicebot is the umbrella term: it also covers voice assistants on websites, in apps or on smart speakers.
Can a voicebot cope with accents and background noise?
Modern speech recognition copes well with accents and moderate noise. It struggles most with unusual names, numbers read out quickly and very noisy places. Good design has the bot read those details back to confirm them.
Related terms
- Callbot
A callbot is a voicebot that works inside phone calls: it answers inbound calls or places outbound ones, talks with the person by voice and handles tasks such as bookings, reminders or lead qualification, connected to your phone system and your tools.
- Speech to text
Speech to text (STT) is the technology that turns spoken audio into written text. It's the software component, usually a model reached through an API, that does the listening in a voicebot, a dictation tool or a transcription service, either live or on recordings.
- Text to speech
Text to speech (TTS) is the technology that turns written text into spoken audio. It's the component, usually a model reached through an API, that gives a voice to a phone agent, a screen reader or any audio generated from text.
- Latency
Latency is the time between making a request and starting to receive the response. In a voice agent, it's the silence from the moment the caller stops talking to the moment they hear the agent's first word, and it decides whether the call sounds natural.
- Chatbot
A chatbot is a program that holds text conversations with people, on a website or on WhatsApp, to answer questions or guide them through a task. It either follows fixed rules or uses a language model to understand what people write.
Updated on