Updated on February 1, 2023

Editing Transcripts

Even though UserBit uses industry leading AI models for the transcription module, the accuracy is still dependent on the media quality and voice similarities. We give you a host of editing features to help manually correct your transcripts in such cases.

Inline editing

You can edit any part of the transcript. Click on it once to activate edit mode, which will allow you to change any word or text. Keep in mind though that once a transcript is changed, it might not be in perfect sync with the video.

Editing transcript
Editing transcript

Splitting speaker text

If you find that the transcript has merged text from two speakers into one, you can split them manually by inserting a new transcription section after or before the relevant one.

Inserting transcript section
Inserting transcript section

⚠️ The text in the new section should be copied from another transcription section to carry the video timing data with it. If you just type the text in, the video sync will not work.

Adding/Switching speakers

You can also easily switch or add speakers for a transcrpition section by clicking on the associated speaker name. This will result in the following modal:

Add or switch speaker for transcription section
Add or switch speaker for transcription section

Here you can:

  • Assign a different speaker to the transcription section
  • Add a new speaker for your transcription

Together, these editing capabilities allow you to edit any part of your transcription.