Community Help

In automatic mode, VoxRelay analyzes confident speech and rechecks the spoken language every 30 seconds. English is transcribed directly. Supported non-English speech is translated into English and prefixed with a label such as [Translated from Spanish 96%].

To avoid rapid switching during short clips or uncertain audio, a new language must be detected confidently more than once before the remembered language changes. Silence, music, overlapping speakers, and very short samples can delay a language update.