Minimum Volume Threshold (RMS): is a field that sets the Root Mean Square (RMS) level, a statistical measure of the magnitude of a varying quantity. It is configured to a value of 100 by defauit, which serves as the minimum volume level required for the audio input to be processed by the system. This setting is used to prevent Voxta from processing audio that lacks sufficient volume, thereby avoiding the transcription of silent or noise-only audio into text.
Backtracking: This is a toggle option, when enabled, the software keeps an additional buffer of audio data. This feature is particularly useful for detecting sounds that may not produce a strong audio signal, such as silent letters (like ‘M’), ensuring that these sounds are not missed in the speech-to-text process.
Optional Label: This is a text field where you can enter a label for the configuration. This could be used to distinguish between multiple configurations.
