<aside> 💪

Discover our two Whisperit modes: Smart transcription and standard

</aside>

Whisperit offers two distinct modes for turning your dictation into text :

• Smart Transcription
• Standard

While both modes aim to convert your speech into text, they differ in how they operate and when to use them. This article explains the differences and how each one can enhance your dictation experience.

1. Smart Transcription : AI that understands and contextualizes your dictation

The Smart transcription mode is more advanced. Instead of simply transcribing your speech word for word, the AI understands the context and adapts the transcription based on your intent and meaning.

This mode is ideal when you want the AI to interpret and organize your input to create a structured document.

Example use case

Let’s say you want to create a structured legal report. With Smart transcription, you can dictate not only content, but also instructions to guide the AI in structuring the document. For example:

• “Review these legal clauses”
• “Write a paragraph explaining the legal context of this clause"

In this case, Smart Transcription won’t just transcribe what you say, it will organize the content, add sections, and follow your instructions to produce a well-structured document.

dictation-smart-transcription.mov

Benefits of Smart Transcription

• Context awareness : The AI adjusts transcription based on the context of your words.
• Automatic structure : Organizes text based on your instructions (titles, sections, etc.)