Transcriptor is an audio transcription application designed using State of the Art Deep Learning Models. It was written to translate English audio to English text, but can be expanded to translate any modern language. The benefit of this approach is that this can process any audio passed to it, even if we have not seen a word before, the model will attempt to transcribe it as close as possible to the actual word.


Drag a .WAV file into the window to parse it or click on the microphone below to start recording. To stop the recording and transcribe, click on the microphone again.

or click on this text to select a WAV file to process!