Skip to main content

How do I best use speech-to-text?

To achieve the best results and a seamless experience with Tandem’s speech-to-text function, follow these guidelines:
​
​1. Speak Naturally
Tandem is designed to understand regular, fluent speech. This means you can talk at a natural pace using your normal voice. Don’t overthink each word—let the conversation flow.
​
​2. Initial Transcription Appears in Light Gray Text
As you dictate, your speech will appear on the screen in light gray text. This is a preliminary transcription and might include minor errors or duplicates, but there’s no need to worry.
​
​3. Automatic Proofreading and Adjustments
When you pause during your dictation, Tandem’s automatic proofreading feature kicks in:

  • Any duplicates are removed.

  • Grammar and punctuation are added automatically where relevant.

  • The text is refined to better match what you actually said.
    ​

4. Verbalize Formatting and Punctuation as Needed
If you want to control specific formatting or add punctuation while dictating, you can say:

  • “New paragraph” → Adds a new paragraph (\n\n).

  • “New line” → Creates a new line (\n).

  • “Period” → Inserts a period (.).

  • “Comma” → Inserts a comma (,).

  • “Left parenthesis” → Adds “(”.

  • “Right parenthesis” or “End parenthesis” → Adds “)”.

  • “Question mark” → Inserts a question mark (?).

  • “Exclamation mark” → Inserts an exclamation mark (!).

  • “Hashtag” → Inserts a hashtag (#).
    ​

By following these tips, you can ensure a smooth and accurate experience with Tandem’s speech-to-text feature. If you have any questions or need additional support, don’t hesitate to reach out to our team!

Did this answer your question?