i
News
News · 2026-11-21

How Google Duplex learned to call businesses for you through Gemini

Dataist Dataist

Google has launched Duplex in the Tasks section of the Gemini app. The system can now call businesses on users’ behalf—for example, to check whether a service is available or arrange a time. Introduced in 2018 for conversations with local businesses, the technology has evolved from narrow models built for individual tasks into a unified system based on Gemini. It is designed to account for conversational context, plan actions and respond with little delay.

Cover: How Google Duplex learned to call businesses for you through Gemini

From narrow tasks to calls in Gemini

Duplex was built for phone conversations where the other person might change their mind, go off script or use intonation to signal when it is their turn to speak. The system needs to understand speech, track context and respond quickly so it does not interrupt or leave long pauses.

Over time, Duplex became shared conversational infrastructure across Google products. During the COVID-19 pandemic, the system automatically checked business information to update opening hours and service details. According to Google, by 2023 information from Duplex calls had appeared more than a trillion times in Search and Maps.

Since 2019, Google has also released Call Assist features across five generations of Pixel phones. Duplex models support Call Screen, which filters unknown numbers, and Hold for Me, which waits on hold and lets the user join the conversation when an employee answers.

In 2025 and 2026, foundation models enabled Google to expand automated calls in Google Search and Ask Maps. The system uses them to check prices, product availability and service availability—from pet grooming to car repairs.

Source: research.google

Three generations of Duplex

The system’s architecture changed as models developed: from specialized neural network pipelines to a unified system based on Gemini.

1. Models for individual tasks

Work on Duplex began before modern language models and transformers emerged. To make conversations predictable, the system was limited to specific tasks, with dedicated recurrent neural networks trained on anonymized phone calls to handle them.

The models had no prior knowledge of the world, so they were trained separately for each type of request. Booking a table required one scenario; checking holiday opening hours required another. Each task needed its own data and logic.

2. Generative models and hybrid systems

When foundation models became available, Duplex began using them in live calls. In 2022, the system used LaMDA. Pretraining helped models understand speech and reason in everyday situations, as well as respond to unexpected remarks and digressions without losing context—for example, a conversation about booking a table.

Early generative models were less predictable and sometimes slower than today’s models. Google therefore combined them with rule-based conversation-state tracking and strict constraints. The generative component handled flexible wording, while the other components helped keep the conversation on track.

3. Gemini and tasks without fixed categories

As foundation models developed, Google moved away from predefined service categories. A task can now be described in plain text, and the system determines how to carry it out. This lets it handle new kinds of requests and services without building a separate dialogue model for each case.

For example, a user can ask for a table by the window or extra room for a stroller. The system also brings together understanding of different data types, planning and dialogue generation, all based on Gemini. That helps it account for several conditions at once—for example, scheduling car maintenance around calendar commitments—and revise its plan if the receptionist suggests another time.

What makes phone conversations difficult

Even advanced models trained on ordinary internet data do not solve every challenge of a live phone conversation. Google identifies two distinct requirements:

Understand intent and context. The internet does not contain all the information about how calls with busy business employees unfold. Nearly a decade of work on targeted calls has helped Duplex account for conversational norms before dialing. For example, the system can use call history to account for a particular business not accepting large groups on weekends. During a call, the models need to choose an appropriate question, recognize a polite indirect refusal and keep the conversation brief.
Respond in under a second in noisy environments. Phone lines compress audio, and the background may include a noisy kitchen, coffee machine, street or other people. The system processes speech as a low-latency stream. Specialized acoustic and conversational timing models help it account for noise and pauses, and end its turn at the right moment.

Rules for both sides of the call

Duplex needs to work for both the user and the business being called. Google describes four principles behind the system:

Disclose automation upfront. Every call begins with an explanation that an automated Google system is calling.
Let businesses opt out. Businesses can turn off automated calls in their Google Business Profile settings or ask during a call not to be contacted again.
Require no setup. The system calls the number the business already uses: there is no need to install software, maintain a booking system or train employees. Whoever answers can speak as they would with an ordinary customer, even at peak times.
Reuse information. Information gathered on one call helps answer later questions and saves businesses from repeat calls to confirm the same details. Google Maps can display information Duplex has collected about happy-hour specials, patio seating, whether pets are allowed, parking and weekly quizzes.

Calls and other Gemini tasks

Google connects the launch of Duplex in Tasks to requests that still require talking to a person: everyday errands, nearby services and urgent tasks. Voice interaction is intended to complement digital ways of getting things done—for example, online interfaces for apps and booking forms that a business may not have.

Google also says Gemini Tasks uses new Gemini 4 models, including Gemini 4 Hydrogen and Gemini 4 Neon. According to the company, the system can support more complex workflows: analyzing utility bills, making payments securely through the Agent Payments Protocol, and coordinating with users over email and Rich Communication Services (RCS).

Google thanked the Duplex team and project contributors for a decade of work. For the shift to Gemini-based calls and the launch of Duplex in Tasks, the company specifically recognized Yoav Tzur, Sasha Goldstein, Rafael Goldfarb, Liran Peretz, Ritika Pathak, Sen Lee, Ran Manor and Dekel Auster, as well as other team members.

Dataist's take: Duplex integration brings phone calls into a set of tasks Gemini can handle for users, but the system still needs to account for speech timing, noise and the rules of dealing with businesses. Google also gives businesses the option to decline automated calls.

Daily AI news

Every day we pick what actually matters in AI and explain it plainly — no hype, no filler. Subscribe if you want to follow where the industry is going.

Only what matters — every day

Follow on X