Audio Time Range

The Audio Time Range feature allows users to select a specific part of the audio for processing. It works across all technologies that involve audio input. Users can define the start and end times of the segment they want to analyze. The start/end time can be omitted, in which case it is automatically set to the start/end of the recording.

For instance, let's say we have a recording where the first 10 seconds of audio consists of a question asked in synthesized speech and the next 20 seconds are reserved for an answer. Since we only want to process the answer, the rest of the recording is insignificant. By specifying the start time to 10 and end time to 30, we can omit the synthesized speech and only process the answer window.

Start/end times reaching beyond the duration of the audio will be automatically adjusted. For instance, if we set a range from 5 to 15 seconds on a 10-second recording, it'll be corrected to a range from 5 to 10 seconds. And if we set a range from 15 to 30 seconds, which exceeds the recording's duration, it will simply result in an empty range.