OnePlus is reportedly working on an artificial intelligence (AI) feature that will allow users to create text summaries from voice recordings. The feature was spotted in the latest version of Oxygen OS, the company’s custom skin for Android. It is said to support multiple audio formats. This feature is currently hidden and those who participated in the beta testing program will not be able to test it. Interestingly, India was mentioned among the countries where this feature could be launched first in one of the lines of code.
OnePlus is reportedly getting an AI Voice Summary feature
Android Authority spotted an underdeveloped feature in Oxygen OS 14.1. This feature is currently not enabled, and the publication discovered it during the dismantling of the company’s software. The smartphone maker is said to be working on an audio recorder that uses the AI Summariser feature that was introduced by the company earlier this year and spotted on the OnePlus 12 and OnePlus Open.
Lines of code also provide some clues about the intended function. For example, the AI Voice Recording Summary feature will support multiple audio file formats, including MP3, AMR, AWB, AAC, and WAV, according to the “convert_error_format” line.
The recording file size must be less than 500MB and the duration of the recording must be less than five hours for the feature to work, according to the lines revealed by the post. Also, it seems that voice recordings that are too short will not be used to generate a summary.
Additionally, the lines of code emphasize that there will be a limit to the number of summary generation tasks that the user can initiate at any one time. There is also a daily limit, the details of which are currently unknown. These criteria may mean that there is a server-level limitation for these features. They may also be offered with a paid subscription tier.
The publication also uncovered lines of code describing the feature in Android 15 Developer Preview 2. These lines don’t reveal more details about the feature, but rather the places where it might launch in the first place. Three languages are reportedly mentioned — Chinese, Hindi, and English — suggesting that the AI Voice Recording Summary feature may first appear in China, India, and the US, according to the report.
