Creating a transcript is incredibly easy using descript. If you’re importing a video file (like an MP4) or audio file ( like a WAV) into a project in descript, transcription starts processing automatically.
To make it more accurate, you can tell descript how many speakers to look for (how many different people’s voices are in the video.) But, if you’re not sure, that’s no problem because there’s an option for that too.
If there are multiple speakers in the recording, Descript will ask you who’s who after it finishes transcribing. Descript plays a short clip of each voice it found (one at a time) and you put it a name too it. Your transcription will now include speaker labels so you have the text of what was said AND who said what! Pretty cool, huh?
If you’re recording directly in Descript, whether it’s an audio recording or you’re recording a screen and audio, Descript will transcribe the spoken words as you go. When you’re finished recording and the transcription is complete (it’s usually a few seconds behind) you can identify the speakers just like we talked about above. And no worries if something is a little off – you can always change speaker labels anywhere in the script at any time.
