📖 Documentation

Everything you need to know about Tells me More

Getting Started

Tells me More is a powerful AI-powered audio transcription app that runs completely offline on your Mac. It uses OpenAI's Whisper model for speech recognition and Llama 3.2 for intelligent text correction and summarization.

💡 Note: This guide is for macOS. Windows and Linux versions are coming soon.

System Requirements

For Apple Silicon Macs (M1/M2/M3/M4):

  • macOS 12 (Monterey) or later
  • 8GB RAM minimum (16GB recommended for large files)
  • 2.5GB free disk space

For Intel Macs:

  • macOS 11 (Big Sur) or later
  • Intel Core i5 or better
  • 16GB RAM recommended
  • 2.5GB free disk space

Installation

Step 1: Download

  1. Go to tellsmemore.com
  2. Click the "Download for Apple Silicon" button (or "Intel Mac" if applicable)
  3. Save the .dmg file to your Downloads folder

Step 2: Install

  1. Double-click the downloaded .dmg file
  2. Drag "Tells me More" to your Applications folder
  3. Eject the DMG by right-clicking and selecting "Eject"

Step 3: First Launch

  1. Open Finder → Applications
  2. Find "Tells me More"
  3. Right-click → Open (first time only, due to Gatekeeper)
  4. Click "Open" in the security dialog
⚠️ First Time Setup: On first launch, the app will download AI models (~2.5GB). This may take 5-10 minutes depending on your internet speed. After this, everything runs offline.

Your First Transcription

Quick Start Guide

  1. Launch Tells me More
  2. Click "Select Audio File" or drag & drop an audio/video file
  3. Choose an audio profile (Podcast recommended for most uses)
  4. Click "Start Transcription"
  5. Wait for the process to complete (progress bar shows status)
  6. Review your transcription in the "Original" and "AI Enhanced" tabs
  7. Click "Export" to save in your preferred format
💚 Pro Tip: For best results, use high-quality audio with minimal background noise. See our guide on improving accuracy.

Key Features

AI Enhanced Transcription

The AI Enhanced feature is always enabled and runs automatically after transcription. It uses Llama 3.2 1B to:

  • Fix grammar and spelling errors
  • Add proper punctuation
  • Correct capitalization
  • Remove filler words (um, uh, like)
  • Improve overall readability

Automatic Summary

After transcription, the AI generates a concise summary (150-300 words) highlighting:

  • Main topics discussed
  • Key points and takeaways
  • Important details

Multi-Language Support

Supports 99+ languages including:

  • English, Spanish, French, German, Italian
  • Chinese (Mandarin, Cantonese), Japanese, Korean
  • Arabic, Portuguese, Russian, Hindi
  • And many more!

The AI automatically detects the language from your audio.

Audio Profiles

Choose the right profile for your content:

🎙️ Podcast

Best for: Podcasts, interviews, conversations

  • Optimized for voice with minimal processing
  • Recommended for most users

💼 Meeting

Best for: Business meetings, conference calls

  • Enhanced for multiple speakers
  • Handles overlapping speech better

🎵 Music/Background

Best for: Audio with background music or noise

  • Aggressive noise reduction
  • Use when there's background music

📖 Lecture

Best for: Educational content, presentations

  • Optimized for clear, single-speaker audio
  • Good for technical vocabulary

Export Options

Export your transcriptions in multiple formats:

Plain Text (.txt)

Simple, unformatted text - compatible with any text editor

Markdown (.md)

Formatted text with headers and structure - perfect for note-taking apps

HTML (.html)

Web-ready document with styling - great for websites or email

PDF (.pdf)

Professional document format - ideal for sharing and printing

Word Document (.docx)

Microsoft Word format - perfect for further editing and collaboration

Tips & Best Practices

For Better Accuracy

  • Use high-quality audio (16-bit, 44.1kHz or higher)
  • Record in a quiet environment
  • Speak clearly and at a moderate pace
  • Use an external microphone if possible
  • Convert video files first if extracting audio

For Faster Processing

  • Close other heavy applications
  • Use the "Podcast" profile for fastest results
  • Ensure your Mac is plugged in (better performance)
  • Split very long files (2+ hours) into smaller chunks

Privacy Best Practices

  • All processing is offline - your data never leaves your Mac
  • Perfect for confidential meetings, medical records, legal audio
  • No account or internet connection required after setup
  • Transcriptions are saved only where you choose

Troubleshooting

App Won't Open

Solution:

  1. Right-click the app → Open (don't double-click)
  2. If that fails, go to System Settings → Privacy & Security
  3. Click "Open Anyway" next to the blocked app message

Models Not Downloading

Solution:

  1. Check your internet connection
  2. Ensure you have 2.5GB+ free disk space
  3. Try restarting the app
  4. Check if your firewall is blocking the download

Transcription is Inaccurate

Solution:

  1. Check audio quality - is there background noise?
  2. Try a different audio profile
  3. Ensure speakers are speaking clearly
  4. Check if the correct language is detected
  5. See our accuracy guide

App is Slow/Crashing

Solution:

  1. Close other applications to free up RAM
  2. Restart your Mac
  3. Check available disk space (need 2.5GB+)
  4. Update to the latest macOS version
  5. Reinstall the app

Export Fails

Solution:

  1. Check write permissions for the selected folder
  2. Try exporting to a different location (Desktop/Documents)
  3. Ensure you have disk space for the export
  4. Try a different export format
Still Need Help? Fill out our survey with your question or check our FAQ for more solutions.

Additional Resources