Transcriptions

As part of postprocessing, Sapling offers the ability to process speech transcriptions.

Speech-to-text (STT), also known as automatic speech recognition (ASR) or speech transcription, has become highly accurate and a convenient way to convert the spoken word to written notes. It can be used in hands-free settings or as a faster alternative to typing.

However, transcription systems often introduce artifacts and other undesirable outputs in the resulting transcription. A few examples:

• Disfluencies such as uhh or umm.
• Dictation commands such as new line, quote, period, or next paragraph.
• Blocks of text without structured formatting.

For these and other transcription issues, Sapling offers postprocessing configurations that can greatly reduce the amount of manual editing required. Contact us to learn more.