What's the difference between the text made from individual files I upload and Riverside's built-in Transcription tool?

After you record in the Riverside Studio, Riverside automatically creates a transcription and you can use the text to help you edit, generate Magic Clips, add captions, and more.

These transcript texts identify each person who speaks. For example:

copied-transcript-text-with-timestamps.png

But if you upload a media file to the standalone transcription tool , you can only download the text file or a captions file. The text is not divided by each speaker. For example:

standalone-transcription-tool-example.png

Learn more

Did this answer your question?