OnePlus is working on an artificial intelligence (AI) feature that will allow users to generate 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. The feature is currently not visible and those who participated in the beta program will not be able to try it. Interestingly, India was mentioned among the countries where the feature could be rolled out first in one of the code strings.
It looks like OnePlus will get an AI voice recording summary feature
Android Authority spotted the underdevelopment feature in Oxygen OS 14.1. The feature is not currently enabled and was discovered by the publication during a teardown of the company's software. The smartphone maker is said to be working on a sound recorder that uses the AI Summariser feature that the company introduced earlier this year and was found on the OnePlus 12 and OnePlus Open.
The code strings also provide some clues about the supposed feature. For example, the AI Voice Recording Summary feature will support multiple audio file formats, including MP3, AMR, AWB, AAC, and WAV, based on the “convert_error_format” string.
The file size of the recording should be less than 500MB and the duration of the recording should be less than five hours for the feature to work, according to the strings discovered by the publication. Also, it seems that voice recordings that are too short will not be used to generate a summary.
Also, the code strings highlight that there will be a limit to the number of summary generation tasks that a user can start simultaneously. There is also a daily limit, details of which are currently unknown. These criteria could mean that there is a server-level limit for these features. They can also be offered with a paid subscription level.
The publication also discovered code strings describing the feature in Android 15 Developer Preview 2. These strings didn't reveal more details about the feature but where it might launch first. According to the report, three languages are mentioned: Chinese, Hindi, and English, suggesting that the AI voice recording summary feature could arrive in China, India, and the US first.
