New kind of AI audio chip transforms earbuds into always-on 'intelligent' devices that run without a smartphone. How does it work?

MAUI, Hawaii — Engineers have built a first-of-its-kind artificial intelligence (AI) audio chip for wearable devices that they say will let users engage with AI assistants without needing to maintain a smartphone connection. Devices with the new chip will also harvest audio ‪—‬ and even video ‪—‬ data from the world around you to better serve these virtual agents.

The new chip, called Snapdragon Sound Elite Gen 2, will pave the way for new features that are currently unavailable directly in portable devices such as headphones, smart glasses and speakers. Qualcomm representatives announced the new chip at the company's annual Snapdragon Summit, hosted here Sept. 21-24.

Unlike current earbuds, devices with the new chip will be able to host apps right on the memory of the devices themselves, without relying on a continuous smartphone connection, as well as sync with cloud-based services like ChatGPT when connected to Wi-Fi. In practice, the chip will enable users to make vocal queries and requests, with an AI model taking actions such as setting up entries in an online calendar or making online purchases. Unlike existing devices that can perform similar functions, this would be possible without a smartphone connection.

Beyond earbuds, company representatives want to integrate the chip into other "hearables," such as over-ear headphones, open-ear audio devices, audio glasses, camera buds (headphones that use tiny built-in cameras) and hearing devices, as well as "future personal AI wearables," like pendants or clips.

What features will the chip enable, and how does it work?

For users who wish to connect hearables to a smartphone or computer (to interact with a visual user interface, for example), the new chip uses a specialized component within the platform to establish connections over micropower Wi-Fi channels alongside Bluetooth. This technology harnesses architectural improvements at the chip level to consume much less power than standard Wi-Fi connections — but at the expense of higher latency and lower peak speeds. For audio devices, however, using Wi-Fi rather than Bluetooth generally improves playback quality, given that Bluetooth compresses data during transmission, Qualcomm representatives said.

Adaptive and selective active noise cancellation also means users can filter out audio on command. For example, it allows listeners to hear key sounds, such as emergency sirens, while walking through a city or highlight people's voices during a conversation, while blocking out everything else. This noise cancellation is achieved through standard machine learning algorithms, rather than transformer-based large language models that power AI systems like ChatGPT.

Devices could also allow lossless audio streaming — a high-quality audio standard that's usually available only if you subscribe to premium streaming services, like Spotify or Tidal — thanks to another built-in subsystem.

Qualcomm representatives also highlighted the chip's "always-on intelligence," in which an on-device eNPU AI accelerator component powers virtual assistants, transcription and translation, as well as the building of "contextual awareness." With contextual awareness, the system would constantly monitor the user's environment to harvest data to add to a personal profile, which representatives say helps it answer future queries.

Although the system is audio-centric, it's also built to interface with hardware that includes sensors and cameras — like earbuds with built-in lenses that passively capture footage of a wearer as they go about their daily lives. This forms part of the data harvesting to build contextual awareness for the agentic AI systems people can access. Qualcomm representatives attempted to assuage privacy concerns by saying camera lenses on future earbuds would be low resolution and wouldn't identify specific individuals due to an AI mask that automatically obfuscates them.

There's no information yet about the likely impact of these features on battery life compared with conventional non-AI devices. But Qualcomm representatives noted that device makers will no longer need to choose between audio quality, AI features and battery life. That said, Andrew Laister, staff product manager at Qualcomm, added in a media Q&A session that there's likely to be an impact on how a user experiences battery drain. That's because, unlike conventional earbuds that are used sporadically for calls and music playback, these new devices are designed to be used continuously.

How does Qualcomm's new AI chip compare with similar technologies?

AI-enabled headphones already exist in some capacity. For example, manufacturer Viaim launched its Rise and RecDot devices this year. These are designed to record, transcribe, translate and summarize conversations, although details on the chips powering them are not publicly available. Apple's AirPods, for example, let users tap into the Siri AI system, but they require a continuous iPhone connection to perform complex tasks.

Devising smart audio features and getting them to work in real devices have also been at the heart of several recent research projects. For example, in 2024, University of Washington scientists embedded a computing system into off-the-shelf earbuds to zero in on individuals speaking in noisy environments while blocking all background noise.

The previous year, the research team put a deep learning system into headphones so wearers could use voice commands to engage with a selective active noise cancellation system, choosing which sounds to hear and which ones to block out.

Other companies have explored building new kinds of digital audio platforms for headphones. Three years ago, xMEMS unveiled Cypress, an audio chip that generates ultrasonic sound using the "piezoelectric effect," in which a material moves when a current is applied to it. Although the chip entered "mass-production readiness" in September 2025, consumer devices fitted with the platform have yet to be announced.

Apple also may be working on a similar technology. This could manifest as AirPods with built-in cameras that will perform similar data harvesting as users go about their day-to-day lives, according to Bloomberg Managing Editor Mark Gurman.

Qualcomm's new chip is a spiritual successor to the 3-year-old Snapdragon S7 Gen 1 system, which featured in devices such as the Xiaomi Buds 5 Pro series. The previous chip also used AI for conventional active noise cancellation, audio customization and lossless audio streaming while connecting to devices via micropower Wi-Fi.

However, the new chip has twice the AI power, completing 128 billion operations per second, compared with the previous one's 64 billion operations per second. It also uses 40% less power and is 30% smaller.

A crucial aspect of the new system is its capacity to store apps on the device itself in the chip's onboard memory. Because the device will have its own IP address, it can communicate with servers using the https protocol, without needing to go through another phone or computer.

Laister told journalists in the Q&A session that the company is currently scoping out whether the device could run two apps in RAM (short-term memory) at once — an AI agent and an audio streaming platform, for example — while keeping the rest in flash memory (long-term storage). He added they had to overcome a communication hurdle with micropower Wi-Fi foron the launch of the previous chip (specifically, that its power consumption is on a par with Bluetooth's). Now, he said the communication hurdle is actually being able to run apps on the device.

"It's like the first smartphone moment with the Play Store, but in this sense, that app store for your earbuds is currently owned by the device maker," he added. "They will be the guys that will choose which apps they will pre-bundle, and then we'll go from there."

No details were available on when the system is likely to be found in devices, but representatives said Qualcomm is working with other companies, including HP and Bose, to explore headphones and speakers that feature the chipset.

Live Science was invited to attend Snapdragon Summit 2026 courtesy of Qualcomm, with the company covering travel and accommodation.

Help us improve Live Science Pro: We're always trying to make our content better. Leave us feedback about Pro here.