@everyone

🗣️🎙️ New Alpha Lab Article — Audio-Powered Event Annotations

Eye tracking often focuses on where participants look — but there's a lot to learn from what they hear too.

We've put together a simple way to automatically mark key events in your recordings based on audio captured by Neon eye tracking glasses.

In this Alpha Lab article, we walk through how you can combine OpenAI Whisper with Pupil Cloud to:

• Detect spoken keywords
• Automatically generate events in Neon recordings
• Automate annotations without the hassle of manual tagging

Perfect for experiments involving instructions, conversations, or verbal tasks — no more scrubbing through videos to tag events by hand. Let audio do the heavy lifting!

Check it out here: https://docs.pupil-labs.com/alpha-lab/audio-event-annotations/

@everyone Big updates for Neon Companion App. Lots of new data streams available on device and for real-time streaming + new Companion Device on the horizon. Head over to the Playstore and update to the latest version.

New data streams in recording data and real-time data streams

• Fixations
• Eyelid angles and eyelid aperture
• Blinks
• Worn state detection
• An additional IMU raw output recorded file (the current protobuf output is still available, but to be deprecated) *Note: If all data streams are enabled, the computations may slow down the real-time gaze rate on older Companion Devices. Please make sure to toggle off streams you don't need in settings.

For those using the real-time API, Neon Recording library, or Neon Player: You will need to update these to interact with the new data streams.

UX changes

• Audio recording is now on by default
• Workspace anonymization state display - so you can confirm when you are in a workspace with anonymization features enabled
• Settings option to skip recording save/discard dialog (skip as default)

Misc changes

• Dtype self-documenting recording format
• A number of stability fixes
• Watchdog can be silenced from UI
• USB watchdog sends events over the status on real-time api endpoint

New Companion Device Last but not least, we are gearing up to support Samsung S25 as a new Companion Device. The S25 is capable of running all data streams at full 200 Hz! Stay tuned.

@everyone We are excited to announce two big new features for Pupil Cloud (plus a few other smaller features 😉 ). Check out the video for an overview and head over to Pupil Cloud to try them out.

Manual Correction for Enrichments We added a way to augment and correct the results from our automated gaze mappers. You can now correct for missed classifications, occlusions and anything else that needs a human in the loop. It can also be used to add a validation step to each automated enrichment.

Scanpath Visualization This is a new visualization that renders fixation and saccade patterns on reference images. You can make visualizations for one or more recordings, and adjust the visual properties of the scanpath(s) to suit your requirements.

Full release notes here

@everyone Greetings Yokohama 🇯🇵 We are here for ACM CHI Conference this year. Stop by booth 301 and say hi & get a hands-on with Neon.