Byblos User Manual
Version 0.1.0
Getting Started
First Launch
When you first open Byblos, an onboarding wizard guides you through:
- Microphone permission — Byblos needs mic access to hear you.
- Download a model — Pick a speech model and optionally an AI model.
- Ready — Byblos appears as a waveform icon in your menu bar.
Permissions
- Microphone (required) — for voice recording.
- Accessibility (recommended) — for typing text into other apps and the hold-to-record hotkey. Grant in System Settings → Privacy & Security → Accessibility.
Without Accessibility permission, Byblos copies transcriptions to your clipboard instead of typing directly.
Recording & Transcription
Starting a Recording
Three ways to record:
- Left-click the menu bar icon — click once to start, click again to stop.
- Hold-to-record hotkey — hold Option (configurable), speak, release.
- Transcript workspace button — click the red record button at the bottom.
While Recording
- The menu bar icon turns red.
- A floating overlay at the bottom of the screen shows a preview of the transcription, word count, and elapsed time.
- For a full view, open the Transcript workspace.
Stopping
- Left-click the menu bar icon again.
- Release the hotkey.
- Click the overlay.
- Auto-stop — detects when you stop speaking (~3 seconds of silence).
Where Does the Text Go?
- Your active app — text is pasted into whatever app you were using.
- Transcript history — every transcription is saved automatically.
Tip: If text isn't appearing, check Accessibility permission. Without it, text is copied to your clipboard — press ⌘V to paste.
Undo
Say "scratch that" or "delete that" to undo the last transcription.
Dictation Modes
Right-click the menu bar icon → Mode to switch.
Clean (default)
Removes filler words (um, uh, like, you know), fixes punctuation and capitalization.
Professional tone with paragraph breaks. Great for Mail, Gmail, Outlook.
Notes
Converts speech into bullet points. Pairs well with Notes.app, Obsidian, Notion.
Translate
Speak in any language, get English text. 99+ languages supported via Whisper.
Raw
Exact transcription with no processing.
Code Comment
Concise output prefixed with //. For developers dictating comments.
Agent EXPERIMENTAL
AI assistant mode. See Agent Mode.
Automatic Mode Switching
When enabled, Byblos picks the right mode based on which app you're using: Mail → Email, VS Code → Code, Notes → Notes, etc.
Transcript Workspace
Right-click → Show Transcripts.
- Sidebar — all transcriptions grouped by date.
- Detail panel — full text, metadata, editable.
- Record button — record directly into the workspace.
- Search & filter — by content or mode.
- Export — Markdown, plain text, or JSON.
File Transcription
Drag audio/video files onto the Transcript workspace, or click Import Audio.
Supported: WAV, MP3, M4A, FLAC, OGG, MP4, MOV, MKV.
Managing Models
Settings → Models.
Speech Models (Whisper)
| Model | Size | Best For |
|---|---|---|
| Tiny | 74 MB | Quick notes, low memory |
| Base | 141 MB | General use |
| Small | 465 MB | Better accuracy |
| Large v3 Turbo | 1.5 GB | Fast + excellent quality |
| Distil-Large v3 | 1.4 GB | Near-best quality, great speed |
| Medium | 1.5 GB | High accuracy |
| Large v3 | 2.9 GB | Maximum accuracy |
CoreML encoders are downloaded automatically for 3x faster transcription on Apple Silicon.
Recommendation: Start with Distil-Large v3 — near-best quality at good speed.
Custom Vocabulary
Settings → Vocabulary. Add replacements for names and jargon that Whisper misspells.
Examples: "byblos" → "Byblos", "kubernetes" → "Kubernetes", "react" → "React"
Settings Reference
General
- Hold key to record (Option, Control, Fn)
- Output mode (type into app / clipboard)
- Voice commands, auto-capitalize
- Auto-stop on silence + delay
- Auto-select mode based on app
- Launch at login
- Language (18 supported)
Models
Download, activate, and remove speech and AI models.
Audio
Input device, noise suppression, VAD.
Agent Mode EXPERIMENTAL
Requires a local LLM.
- "What's on my screen?" — reads current window
- "Find files called readme" — searches via Spotlight
- "Open Safari" — launches apps
- "What's on my clipboard?" — reads clipboard
Local LLM Setup (Optional)
Download an AI model in Settings → Models. Recommended: Qwen 3 8B (4.7 GB, needs 16GB+ RAM) or Qwen 3.5 4B (2.7 GB, 8GB+).
The LLM runs in a separate helper process alongside Whisper, both using Metal GPU.
License & Support
Free for personal use. No limits, no nag screens, all features available.
Commercial use (work, business, revenue) requires a license: $49/user/year. Honor system — we trust you.
To activate a commercial license: Settings → About → paste key → Activate.
support@byblos.im · GitHub Issues
Troubleshooting
No transcription
- Speak closer to the mic
- Check input device in Settings → Audio
- Check a model is downloaded in Settings → Models
Text not appearing in app
- Grant Accessibility: System Settings → Privacy & Security → Accessibility
- Or use clipboard mode: Settings → General → Output mode → Clipboard
Hotkey not working
- Requires Accessibility permission
- After updates, may need to re-grant
Logs
~/Library/Logs/Byblos.log
Quick Reference
| Action | How |
|---|---|
| Start/stop recording | Left-click menu bar icon |
| Hold-to-record | Hold Option |
| Open menu | Right-click menu bar icon |
| Stop from overlay | Click the overlay |
| Undo last | Say "scratch that" |
| Auto-stop | Pause ~3 seconds |
| Show Transcripts | Right-click → Show Transcripts |