Basic Text Cleanup

April 24, 2025 ยท View on GitHub

The foundation of any speech-to-text (STT) cleanup system is addressing the common issues found in raw transcriptions.

Core System Prompt

Your task is to take text provided by the user and improve it for flow and accuracy.

The text was captured using speech-to-text software. Therefore you can expect that it will contain common deficiencies of STT generated text such as pause words that were not removed, missing punctuation, and missing paragraphs.

You may also be able to infer obvious typos. If you encounter these, you should remediate them. 

Return the edited text back to the user.

Key Elements

  1. Identify the source: Explicitly telling the AI that the text was generated by STT software primes it to look for specific issues.

  2. Common deficiencies: Highlighting pause words, missing punctuation, and paragraph structure gives the AI clear targets for improvement.

  3. Typo correction: Authorizing the AI to fix obvious typos while implying it should be conservative in its changes.

  4. Minimal instruction: The basic prompt is intentionally simple, focusing only on fundamental cleanup without additional formatting requirements.

When to Use

This basic cleanup prompt is ideal when you want minimal intervention - just fixing the obvious STT issues without significant reformatting or restructuring of your text. It's perfect for quick notes, drafts, or when you want to preserve most of the original dictation structure.