Dicta-Notes

Getting Started with Dicta-Notes

Find detailed guides and answers to common questions about using Dicta-Notes for AI-powered meeting transcription, speaker identification, and document analysis.

Universal Transcription Platform

Record in your browser, see live words on screen, then process a saved session with Google Gemini 3.7 Flash.

🚀 What Dicta-Notes Does

Dicta-Notes is an advanced universal transcription platform that works natively in any language. It uses three powerful AI engines working together to give you the best transcription experience!

🟢 Browser Speech

Live captions in Chrome or Edge while you record

🟣 Google Gemini 3.7 Flash

Powerful AI transcription engine

🔵 Google Translate

Translation into any language

📱 What You Need

  • A computer, tablet, or phone with a microphone
  • Chrome or Edge for live captions while recording
  • Firefox or Safari can still record; live captions may be missing
  • Optional: the Windows desktop app (records, but skips live captions)
  • No extra software required for the browser app

🚀 Step 1: Access the Platform

  1. Open your web browser
  2. Go to: dicta-notes.com
  3. Sign in, or create an account (no administrator required)
  4. Open More → Record Meeting (that is the Transcribe page)

🎯 Step 2: Start Recording

On Record Meeting, pick an audio source and a Speech recognition language, then click Start Dual Recording. Two layers run together:

🟢 Browser Speech (live on-screen words)

What it does: Shows live captions as you speak

  • Live captions in Chrome or Edge — pick the language before you start
  • Client-side Web Speech API (not Gemini)
  • Display only — helps you see the meeting is being captured
  • The Windows desktop app skips this layer (no speech backend)

Note: This is for UX only — not the final transcript

🟠 Audio capture (saved when you stop)

What it does: Records the actual audio for later AI transcription

  • Choose Microphone or System Audio (keep Include my voice on for meetings)
  • Use Pause / Resume for breaks, then Stop when finished
  • Stop uploads the audio and creates a session automatically
  • Audio is also backed up locally every 30 seconds in case a save is interrupted

Setup: Runs automatically in the background once recording starts

🟣 Google Gemini 3.7 Flash (AI transcription)

What it does: Creates the professional transcript after you save

  • On-demand transcription with long-form speaker diarization
  • After save, Gemini auto-detects the spoken language per segment, including code-switching
  • Process saved audio whenever you are ready — Gemini does not run while you record

Use: Open the session, then click Click here to transcribe this Audio

🔵 Translation (any language)

What it does: Translates finished transcripts between languages

  • On the session Transcript tab after Gemini finishes
  • Any language supported
  • Does not translate live while you are recording

Note: Only needed if converting between languages — Gemini transcribes natively

📝 Step 3: Start Your Meeting

  1. Optionally fill in a meeting title and add participant names (click a name badge when that person speaks)
  2. Choose Microphone or System Audio
  3. Set Speech recognition language for live captions (Chrome/Edge)
  4. Click Start Dual Recording and grant microphone (and, for System Audio, screen/tab) permissions
  5. Begin your meeting and speak normally
  6. If live words appear, that is browser speech feedback, not the final transcript
  7. Speaker names and diarized sections are produced later, when you transcribe the saved session

🌍 Step 4: Language Support

Native Language Transcription

After you save, Google Gemini 3.7 Flash transcribes in any language and auto-detects the spoken language per segment — including mid-conversation code-switching. You do not pick a language for that step.

Live captions vs translation

Live captions follow the speech-language picker (Chrome/Edge). Translation of the finished transcript is a separate step on the Transcript tab — it is not live during recording. Yoruba and Hausa have no Chrome live-caption tag, so those captions may fall back to English while Gemini still transcribes the saved audio.

Example: Spanish meeting → Gemini transcribes in Spanish after save → optionally translate to English on the Transcript tab

✅ Step 5: Stop, Transcribe, and Share

  1. When your meeting ends, click Stop — the recording is saved automatically
  2. Open Sessions, then View Details on that meeting
  3. Click Click here to transcribe this Audio to run Google Gemini 3.7 Flash
  4. Rename speakers on the Edit Speakers tab if needed
  5. Export as PDF, Word, Text, Markdown, or CSV, or use Analyze transcript for a summary (also saved under Document analysis)

🔗 Enterprise Features Available

  • Organisation Workspaces - Personal, Union Local, or Corporate accounts
  • On-Demand Transcription - Process recordings when ready
  • Advanced Security - Firebase enterprise auth
  • PWA Installation - Works like native app
  • Document Analysis - Upload PDF/Word/TXT or scan pages with your camera
  • Speaker Management - long-form speaker diarization
  • Audio Playback - Waveform visualization
  • Cross-Platform - Desktop, mobile, tablet

💡 Pro Tips for Best Results

  • Speak clearly - Normal pace, clear pronunciation
  • Minimize overlapping - Let speakers finish before others start
  • Good audio setup - Close to microphone, quiet environment
  • Test first - Try a quick test recording before important meetings
  • Save recordings - Process with Google Gemini 3.7 Flash when ready
  • Use System Audio for screen-shared presentations
  • Use Microphone for in-person meetings
  • Install PWA for better performance

📱 Mobile Recording Tips

On phones and tablets, the operating system pauses audio capture when you switch to another app. For an uninterrupted recording, keep Dicta-Notes open and in the foreground for the full duration of your meeting.

✅ Best practice on mobile

  • Dedicate your phone to the recording — don't use it for anything else during the meeting
  • Disable screen auto-lock or keep the screen on
  • Turn on Do Not Disturb to avoid notification interruptions
  • Install the app from Safari (iPhone) or Chrome (Android) for the best experience

💻 On desktop you can multitask freely

  • Switch tabs, look things up, or write notes — recording continues uninterrupted
  • Chrome, Edge, and Firefox all keep the recording running in the background
  • Use a laptop or desktop for meetings where you'll need your device for other tasks

Note: If you do switch apps on Android, the app will show you exactly how long it was in the background so you know what may have been missed.

⚠️ Troubleshooting

Browser Speech (UX) Issues:

  • Use Chrome or Edge for live captions; check microphone permissions
  • Refresh the page if words stop appearing
  • On the Windows desktop app, missing live captions is expected — recording still works
  • Remember: this is visual feedback; your audio is still being recorded

Recording Issues:

  • Check microphone/system audio permissions
  • Ensure stable internet connection for saving
  • Verify sufficient storage space in your account

Transcription Processing Issues:

  • Wait for Google Gemini 3.7 Flash processing to complete
  • Check session detail page for progress
  • Large audio files may take a few minutes to process

❔ Remember

This is a professional enterprise platform! Three powerful AI engines work together: Browser Speech for instant UX feedback, Google Gemini 3.7 Flash for professional transcription, and Google Translate for international collaboration.

Universal language support: Google Gemini 3.7 Flash transcribes natively in any language - you only need Google Translate if you want to convert transcripts between different languages for team collaboration.

Need help? Use the floating support chat in the bottom-right corner, or ask your team administrator for guidance on using the recording and transcription features.