Yes, it can! When Dragon transcribes an audio file that is pre-recorded, it’s called back-end speech recognition.

However, there are a few things to bear in mind when using this method of transcription. Allow us to explain…

Accuracy may be affected

Dragon is designed for one user per license. Therefore, if you are inputting audio files of different voices or of multiple people speaking, the accuracy will be affected.

It’s for this reason that we don’t recommend using Dragon to transcribe multi-speaker audio.

You will need to format

Due to putting a file through Dragon’s speech engine after it was recorded, it’s likely that the person speaking won’t be using dictation etiquette i.e. voice commands and punctuation.

This means that someone will need to go through the transcription to create paragraphs, add punctuation and ensure the text is displayed correctly.

You will need a specific workflow

Back-end speech recognition is only available with the Dragon Professional 16 (DP16) version.

Unlike when using Dragon in real-time (requiring only a computer and a headset), back-end is a little different.

For Dragon to transcribe audio files, you will need some kind of omni-directional microphone such as a voice recorder or voice tracer like this 👇🏻

This will be how you capture the audio file.

You’ll then be able to connect the recorder to your computer and input the file into Dragon’s engine.

Want to give it a try? You can try Dragon Professional 16 free for 7-days with us.

Did you enjoy our ‘Can Dragon transcribe audio files?’ blog? Check our more of our support blogs here.