BisonNotes AI

Complete User Guide — iPhone, iPad, Apple Watch, and Mac

v1.11

Contents

Getting Started
- Your First Recording
- First Transcript & Summary
Recording Features
AI Engine Configuration
Transcription Configuration
Working with Summaries
Audio Playback
Setup & Configuration
Privacy & Security
Troubleshooting
Advanced Features
Best Practices
External Resources

What’s new in v1.11:

Now on Mac. BisonNotes AI runs on macOS via Mac Catalyst — record, transcribe, and summarize on your Mac with the same data as iPhone and iPad.
Pause & Resume recording. Step away from a meeting without losing your spot.
Major security hardening. API keys, AWS credentials, and tokens live in the iOS Keychain. Recordings, transcripts, notes, and attachments get explicit file protection, and user-configured AI endpoints are validated to block insecure cleartext destinations.
Cleaner workflow. “Generate Transcript” lives on the recording, “Generate Summary” lives on the transcript — the right action shows up in the right place.
Refreshed local AI engine. Updated llama.cpp build with a dedicated Mac Catalyst slice; experimental MLX Swift summarization engine for Apple Silicon.

Getting Started

First Launch Setup

Install the App — Download BisonNotes AI from the App Store.
Simple Settings Welcome Screen — You’ll see a streamlined setup with three options:
Initial Setup Options
- Mistral AI (Free): Free cloud AI — no credit card required. A guided wizard walks you through creating a free Mistral account and API key in about 2 minutes. Includes transcription (Voxtral Mini with speaker diarization) and AI summaries (Mistral Medium). Paid tiers available for higher rate limits.
- On-Device AI: Private, on-device processing. No data leaves your device. Requires download of AI models (2-3GB each) and Parakeet transcription model. Best for recordings under 60 minutes.
- Advanced & Other Options: Configure providers manually. Includes OpenAI, Google AI Studio, AWS Bedrock, Mistral AI, OpenAI Compatible, Ollama. If you already have an AI provider configured, your existing settings are preserved.
Tip: The simple settings page automatically detects your current configuration. If you’ve configured something in advanced settings that doesn’t match the simple options, it will automatically show “Advanced & Other Options”.
Location Permission — The app will ask for location access if enabled:
- “Allow While Using App”: Recommended — captures location during recording
- “Don’t Allow”: You can still add locations manually later
Automatic Migration — On first launch, the app scans for existing audio files and migrates them into the database.

Your First Recording

Start Recording — Tap the large microphone button on the main screen.
Microphone Permission — On your first recording, the system will ask for microphone access. Tap “OK”. If denied, re-enable in Settings → Privacy & Security → Microphone (or System Settings → Privacy & Security → Microphone on Mac).
Recording Status — You’ll see a red recording indicator, live timer, and location indicator (if enabled).
Pause & Resume (v1.11) — Tap the Pause button to pause without ending the file; tap Resume to continue. Works on iPhone, iPad, and Mac.
Stop Recording — Tap the stop button to end.
Background Recording — The app continues recording when minimized or the phone is locked. On Mac, the app keeps recording when in the background or behind other windows.

First Transcript & Summary

v1.11 workflow: The “Generate Transcript” action lives on the recording; the “Generate Summary” action lives on the transcript. Each button only appears where it makes sense and disappears once the artifact exists — if you want to redo something, open the existing transcript or summary and regenerate from there.

Generate Your First Transcript

Access Recording — After stopping, you’ll see it in the Recordings list.
Start Transcription — Tap “Generate Transcript” on the recording row, or open the audio player and tap it there. The app processes your audio using your selected transcription engine.
Progress — You’ll see processing status and an estimate. You can continue using the app while it processes.
View Results — Open the Transcripts tab to read the full transcript with editable text and confidence indicators.

Generate Your First Summary

Prerequisites — You need a transcript first.
Start Summary — Open the transcript (Transcripts tab) and tap “Generate Summary”. A second “Generate Summary” button is also available directly on the transcript row.
AI Processing — The app analyzes your transcript and creates:
- Enhanced Summary: Main content overview
- Action Items: Tasks with priority levels
- Reminders: Time-sensitive items with urgency indicators
- Alternative Titles: AI-generated recording names
Review Results — Expandable sections, priority indicators, interactive maps, attachments, and integration options (Apple Reminders, Apple Calendar, Google Calendar).

iCloud Sync Setup

When does this appear? After generating your first successful summary.

“Enable iCloud Sync” — Summaries sync across all your devices. Uses your iCloud storage quota.
“Keep Local Only” — Summaries stay on this device only. Better for privacy-sensitive content. Can be changed later.

Managing & Deleting Recordings

Long press on any recording, or tap and use the “…” menu. Storage options:

Archive to iCloud Drive — Copies audio to iCloud Drive, keeps transcript/summary and a saved restore location, and can optionally remove only the local audio file.
Audio File Only — Keeps transcript/summary, removes audio. Good for saving storage.
Everything — Removes audio, transcript, and summary. Cannot be undone.
Summary Only — Keeps audio and transcript. Useful for regenerating with a different engine.

Archive note: Audio archive targets are currently limited to iCloud Drive. Other Files providers such as Dropbox, Google Drive, and Proton Drive are not used for new archives until restore and cleanup behavior is reliable.

Important: Deletion is permanent. Make sure you have backups if needed.

Recording Features

Mac Catalyst (v1.11)

BisonNotes AI runs natively on macOS as a Mac Catalyst app. The Mac build uses an AVAudioEngine-based recording pipeline that is tuned for desktop audio sessions:

Same Core Data store — Recordings, transcripts, and summaries sync with iPhone/iPad through iCloud (if enabled).
Pause & Resume — Full pause/resume support, the same as on iOS.
Microphone selection — Choose your built-in mic, USB interface, or Bluetooth device from Transcription Settings.
Local AI — The on-device llama.cpp engine ships with a dedicated Mac Catalyst slice; experimental MLX Swift summarization is available on Apple Silicon Macs.
Settings sheets — Settings forms use a Mac-friendly layout for reliable scrolling and button hit targets.

Pause & Resume Recording (v1.11)

Pause and resume the current recording without stopping the file:

Tap the Pause button while recording. The timer freezes; audio capture stops; the file stays open.
Tap Resume to keep adding to the same audio file from where you left off.
Works on iPhone, iPad, and Mac. On Mac the underlying pipeline uses AVAudioEngine for a clean pause boundary.

iPhone Action Button Integration

Available on: iPhone 15 Pro, iPhone 15 Pro Max, iPhone 16 Pro, iPhone 16 Pro Max, and future iPhone Pro models with Action Button.

Start recording instantly without opening the app first — perfect for capturing thoughts, meetings, or voice notes.

How to Configure the Action Button

Open the Settings app on your iPhone.
Navigate to Action Button.
Select Shortcut as the Action Button function.
Tap “Choose a Shortcut” → Search for “Start Recording” or “BisonNotes AI” → Select it.
Press the Action Button to test!

What happens: The app launches, switches to the Recordings tab, and starts recording immediately. Recording continues even if you switch apps or lock your phone.

Pro Tip: The Action Button works even when your phone is locked!

Location Tracking

Automatic — GPS location captured with each recording
Manual — Add or edit location later in the summary view
Privacy — Location tracking can be disabled in settings

Import Existing Audio

Tap “Import Audio Files” on the main screen.
Select audio files from your device.
Files are automatically added to your recordings library.

Archive Audio to iCloud Drive

Select one or more recordings, or choose the archive option for recordings older than a selected age.
Choose an iCloud Drive location when the document picker opens.
Optionally remove the local audio after export. Transcripts, summaries, tasks, reminders, and metadata remain in BisonNotes.
Use the download button on an archived recording to restore the audio. After restore, BisonNotes removes the archived iCloud Drive copy.

Current scope: New audio archives are iCloud Drive only. Other Files providers may appear in iOS, but BisonNotes leaves local audio untouched if the selected archive destination is not iCloud Drive.

Share from other apps: Import audio files directly from Voice Memos, Files, and other apps using the iOS share sheet.

Open the source app — Voice Memos, Files, or any app with the audio file.
Tap Share — Select “BisonNotes AI” from the share sheet.
Automatic Import — The file is saved and BisonNotes AI opens to import it.
Background Import — If BisonNotes AI is already running, it detects the new file immediately.

Supported file types:

Audio: M4A, MP3, WAV, CAF, AIFF, AIF
Documents: TXT, MD, PDF, DOC, DOCX

Combining Recordings

When to use: Merge two separate recordings into one continuous file — useful if your recording was interrupted.

How to Combine Recordings

Select recordings — Go to Recordings tab → tap “Select” → check two recordings.
Tap “Combine” — A “Combine” button appears when two are selected.
Choose order — The app recommends chronological order. Tap the “First” card to swap if needed.
Review & confirm — Check combined duration preview, tap “Combine Recordings”.
After combining — The new recording appears in your list. Original recordings remain unchanged. Generate new transcripts and summaries for the combined file.

Important: Recordings with existing transcripts or summaries cannot be combined. Delete any existing transcripts/summaries from both recordings first. Why? Transcripts and summaries are tied to specific audio files.

Tips:

Make sure recordings are in the correct chronological order
Combined file size = sum of both originals
You’ll need to generate new transcripts/summaries afterward

AI Engine Configuration

Overview: BisonNotes AI supports multiple AI engines for transcription and summarization. Each has different capabilities, requirements, and pricing.

1. On-Device AI — Free & Private

Free On-Device

Type: Local processing • Cost: Free • Privacy: 100% local • Internet: Only for initial model download

Requirements

Transcription: iOS 17.0+, 4GB+ RAM. Uses Parakeet (default) for on-device transcription.
AI Summary (llama.cpp models): iPhone 15 Pro, iPhone 16+, iOS 18.1+
Storage: 2-3GB per AI model, plus transcription model download

Recommended Models (by RAM)

8GB+: Gemma 3n E4B (4.5 GB) — Best overall quality
6GB+: Gemma 3n E2B (3.0 GB) — Good quality, smaller size
6GB+: Granite Micro (2.1 GB) — Very fast processing

Experimental Models (enable in settings)

8GB+: Granite (4.3 GB) — Reliable and accurate
6GB+: Ministral (2.1 GB) — Best for tasks/reminders
4GB+: LFM 2.5 Thinking (731 MB) — Fast, minimal summaries
6GB+: Qwen3.5 2B (1.3 GB) — Thinking mode, summary only
8GB+: Qwen3.5 4B (2.7 GB) — Thinking mode, excellent detail

Best for: Privacy-conscious users, offline use, recordings under 60 minutes

2. OpenAI — Cloud AI

Cloud Pay-per-use

Type: Cloud • Cost: Pay-per-use • Privacy: Data sent to OpenAI • Internet: Required

Setup

Get API key at platform.openai.com
Go to Setup → AI Settings → OpenAI
Enter your API key, select model, test connection.

Summarization Models

Model	Best For	Tier
GPT-4.1 Mini	Balanced performance (Default)	Standard
GPT-5 Mini	Next-gen reasoning	Premium
GPT-5.4 Mini	Latest GPT-5 Mini — improved reasoning	Premium

Transcription Models

Model	Notes
GPT-4o Transcribe	Most robust. Supports streaming.
GPT-4o Mini Transcribe	Cheapest/fastest. Streaming. Recommended.
Whisper-1	Legacy Whisper V2. No streaming.

Best for: High-quality results, advanced features

3. Google AI Studio — Gemini Models

Cloud Free tier

Type: Cloud • Cost: Free tier, then pay-per-use • Privacy: Data sent to Google • Internet: Required

Setup

Get API key at aistudio.google.com
Go to Setup → AI Settings → Google AI Studio
Enter API key, select model, test connection.

Available Models

Gemini 3 Flash Preview (Default) — Fast and efficient
Gemini 3.1 Flash Lite Preview — Lightweight variant for quick processing

Best for: Balanced performance and cost, with free tier for getting started

4. OpenAI API Compatible — LiteLLM, llama.cpp, Groq, etc.

Cloud/Local Flexible

Type: OpenAI-compatible endpoint • Cost: Varies • Privacy: Depends on provider • Internet: Required unless local

Note: This is a single engine option that works with multiple providers. You don’t select them as separate engines — just change the base URL and API key.

Supported Providers

LiteLLM — Base URL: your server (e.g., http://localhost:4000/v1)
llama.cpp — Base URL: http://localhost:8080. API key: “no-key” or empty.
Groq — Base URL: https://api.groq.com/v1. API key from console.groq.com
Nebius — Your Nebius endpoint URL
Custom — Any OpenAI-compatible endpoint

Setup

Go to Setup → AI Settings → OpenAI API Compatible
Enter API key and base URL for your provider.
Select model (use your provider’s exact model name, e.g., llama-3.1-70b-versatile for Groq).
Test the connection.

llama.cpp setup: Clone from github.com/ggerganov/llama.cpp, build, run ./server --model <model.gguf>. Or use Python: pip install 'llama-cpp-python[server]'

Best for: Using LiteLLM, llama.cpp, Nebius, Groq, or other compatible services

5. Mistral AI — Summarization & Transcription Free Tier

Cloud Free Tier Available Paid Tiers Available

Type: Cloud • Cost: Free tier available (no credit card); paid tiers for higher rate limits • Internet: Required

Free Tier: Mistral AI offers a free Experiment plan with access to all models. No credit card required — just a verified phone number. Includes ~2 requests/second, 500K tokens/min, and 1B tokens/month. More than enough for personal use. You can upgrade to paid Build or Scale tiers anytime at console.mistral.ai for higher rate limits and production use.

Guided In-App Setup (Recommended)

BisonNotes AI includes a step-by-step onboarding wizard that walks you through the entire process in about 2 minutes:

Launch the wizard from any of these places:
- First-time setup: Select “Mistral AI (Free)” and tap “Save & Configure”
- AI Settings: Tap Mistral AI (look for the orange “Free” badge), then “Configure” → “Set Up Free Account”
Create account — The wizard opens console.mistral.ai in an in-app browser. Sign up with email and verify your phone number.
Generate API key — The wizard opens the API keys page. Create a key named “BisonNotes” and copy it.
Paste & validate — Paste your key (or use the clipboard button), then test the connection.
Done! — The wizard auto-configures Mistral Medium for summaries, Voxtral Mini for transcription, and enables speaker diarization.

Summarization Models

Mistral Large (25.12) — Most capable, 128K context (Premium)
Mistral Medium (25.08) — Balanced, 128K context (Standard) — default after guided setup
Magistral Medium (25.09) — Economy, 40K context

Transcription

Voxtral Mini Transcribe — $0.003/min with optional speaker diarization
Supports MP3, MP4, M4A, WAV, FLAC, OGG, WebM
Automatic language detection or explicit language code
Files over 24MB automatically chunked

Manual Setup (Alternative)

Get API key at console.mistral.ai
Go to Setup → AI Settings → Mistral AI → Configure
Enter API key, select model, test connection.
For transcription: Setup → Transcription Settings → select “Mistral AI”.

Best for: Free cloud AI with fast summaries and affordable transcription with speaker diarization

6. AWS Bedrock — Enterprise Claude AI

Cloud Pay-per-use

Type: Cloud • Cost: Pay-per-use • Internet: Required

Available Models

Claude 4.5 Haiku (Default) — Fast, efficient (Standard tier)
Claude Sonnet 4.5 — Advanced reasoning and analysis (Premium tier)
Llama 4 Maverick 17B — Meta’s latest, enhanced reasoning (Economy tier)

Setup

Create an AWS account and enable Bedrock service.
Create IAM user with Bedrock permissions and generate access keys.
Go to Setup → AI Settings → AWS Bedrock.
Enter AWS credentials, select region and model, test connection.

Best for: Enterprise features and compliance

7. Apple Native — Apple Intelligence

Free On-Device

Type: On-device • Cost: Free • Privacy: 100% local • Internet: Not required

New in v1.8: Apple Native uses Apple’s Foundation Models framework to run AI summarization entirely on-device with no internet connection and no data leaving your device.

Requirements

iOS 26.0 or later
iPhone 15 Pro or newer (Apple Intelligence–capable device)
Apple Intelligence enabled in Settings → Apple Intelligence & Siri

Setup

Go to Setup → AI Settings.
Select Apple Native from the engine library.
No API key or model download required — uses the built-in Foundation Model.

Limitations

Context window is 4,096 tokens. Long transcripts are automatically chunked and summarized in segments.
Only available on devices that support Apple Intelligence.

Best for: Maximum privacy, no setup, and users with Apple Intelligence–capable devices on iOS 26+

8. Ollama — Local LLM Server

Local Free

Type: Local server • Cost: Free • Privacy: 100% local • Internet: Not required

Setup

Install Ollama on your machine.

Download models:

ollama pull qwen3:30b
ollama pull gpt-oss:20b
ollama pull mistral-small3.2

Go to Setup → AI Settings → Ollama.
Set server URL and port (default: http://localhost:11434).
Tap refresh to scan for models, select one, test connection.

Tips: Use your server’s IP for network access (e.g., http://192.168.1.100:11434). Larger models = better results but more RAM.

Best for: Privacy, customizable models, offline use

9. MLX Swift — Experimental On-Device Summarization

On-Device Free

Type: On-device, Apple Silicon • Cost: Free • Privacy: 100% local • Internet: Only for initial model download

Experimental: The MLX Swift engine is gated behind the experimental toggle in Settings. It runs on Apple’s MLX framework and is best treated as a preview while we tune memory pressure on lower-RAM devices.

Setup

Go to Setup → Additional Settings.
Turn on “Experimental summary models & MLX AI engine”.
Return to AI Settings and pick MLX Swift from the engine library.
Download an MLX model from the MLX Swift settings screen.

Best for: Apple Silicon devices (especially Mac and iPad with M-series chips) where you want fully local summarization with a different model lineup than llama.cpp.

Transcription Configuration

Privacy first: For complete privacy, use On Device transcription. Your audio is processed entirely on your device and never leaves your iPhone or iPad.

Engine Selection

Go to Setup → Transcription Settings.
Select your preferred transcription engine.
Configure and test the connection.

Available Engines

On Device (Parakeet) — Default. Free, private, works offline. Requires model download.
OpenAI — GPT-4o Transcribe, GPT-4o Mini Transcribe, or Whisper-1.
Mistral AI — Voxtral Mini with optional speaker diarization. Free tier available; $0.003/min on paid tiers.
Whisper (Local Server) — Your own Whisper server (REST API or Wyoming protocol).
AWS Transcribe — Cloud service for long audio files.
OpenAI API Compatible — Any compatible transcription endpoint.

Transcription Engine Comparison

Engine	Type	Speakers	Cost
On-Device (Parakeet)	Local	No	Free (Default)
OpenAI GPT-4o	Cloud	No	Per token
OpenAI Whisper	Cloud	No	Per minute
Mistral AI Free Tier	Cloud	Yes	Free tier included; paid tiers for higher limits (~$0.003/min transcription)
AWS Transcribe	Cloud	Yes	Per minute
Whisper (local)	Local	No	Free

On Device Transcription (Parakeet) — Default

v1.8: Parakeet is now the sole on-device transcription engine. WhisperKit has been removed. Users who had WhisperKit selected are automatically migrated to Parakeet on first launch.

Initial Setup

Enable: Setup → Transcription Settings → select “On Device” → Parakeet is selected by default.
Download the model: Tap “Download” to get the Parakeet model.
Requirements: iOS 17.0+, model download required.

Benefits: Complete privacy, works offline, no API costs.

Whisper (Local Server) Setup

Install Whisper Server:

# Using Docker (recommended)
docker run -d -p 9000:9000 \
  -e ASR_MODEL=base \
  -e ASR_ENGINE=openai_whisper \
  onerahmet/openai-whisper-asr-webservice:latest

Configure: Setup → Transcription Settings → Whisper (Local Server). Set server URL and port (default: 9000). Choose protocol (REST API or Wyoming) and model size.

Protocols: REST API = traditional HTTP file uploads. Wyoming = modern WebSocket streaming.

AWS Transcribe Setup

Create an AWS account and enable Transcribe service.
Create IAM user with transcribe:StartTranscriptionJob and transcribe:GetTranscriptionJob permissions.
Setup → Transcription Settings → AWS Transcribe.
Enter access key, secret key, region, language. Test connection.

Tip: Choose a region close to you for better performance.

Large File Processing

Automatic Chunking — Files over 5 minutes are automatically split
Progress Tracking — Real-time updates
Background Processing — Continues when app is minimized
Configurable Timeouts — Adjustable processing time limits

Working with Summaries

Viewing Summaries

Tap the “Summaries” tab.
Browse recordings with AI-generated summaries.
Tap any summary to view details.

Summary Features

Expandable Sections — Tap to expand/collapse
Task Extraction — AI-identified actionable items
Reminder Detection — Time-sensitive reminders
Priority Indicators — Color-coded priorities
Location Maps — Interactive maps showing recording location
Attachments — Attach text, PDF, or other documents to a summary. Inline previews are available for text and PDF; other formats open with Quick Look. Note exports save your notes for sharing.
Send to Reminders / Calendar — Push extracted tasks and reminders into Apple Reminders, Apple Calendar, or Google Calendar (uses the Google Calendar app if installed, falls back to the web).

Search & Filtering

Search is available in three views:

Summaries View — Search content, tasks, reminders, titles
Transcripts View — Search transcript text
Recordings View — Search by recording name

Tap the search bar, type your terms — results filter in real-time (case-insensitive, partial match).

Date Filters

Tap the filter icon → select start/end dates → tap “Apply”. Clear with the X on the filter banner. Filters combine with search and persist until cleared.

Editing Metadata

Change Title, Date, or Location

Recording Title

You can rename a recording from three places:

The audio player view (tap the title to edit)
The transcript editor (tap the title at the top)
The summary view — “Titles” section → “Edit” → enter a new title or pick one of the AI-generated alternatives → “Use This Title”.

Custom Date & Time

Open summary → “Recording Date & Time” → “Set Custom Date & Time” → use pickers → “Save”. BisonNotes AI also persists the explicit recording start timestamp so date sorting matches when the audio was captured, not when it was imported.

Location

Open summary → location section → “Add Location” or “Edit Location”. Choose: Current Location (GPS), Map Selection, or Manual Entry → “Save”.

Audio Playback

Basic Playback

Go to the “Recordings” tab.
Tap any recording to play.
Controls: Play/Pause (center), Skip 15s (sides), Scrub (drag progress bar).

Advanced Playback

Seek Control — Drag scrubber for precise positioning
Background Playback — Audio continues when app is minimized
Audio Session Management — Handles interruptions gracefully

Setup & Configuration

Simple Setup vs Additional Settings

Simple Setup

Appears on first launch. Quick setup for common configurations.

Auto-detects your current config
Three quick options: OpenAI, On-Device AI, or Advanced
Preserves settings when switching

Additional Settings

Full control over all options.

All 8 AI engines plus the experimental MLX Swift engine
All transcription engines
Microphone selection
Preferences, iCloud, background processing, experimental toggles

Switching: Simple → Additional Settings: tap “Additional Settings” button. Additional Settings → Simple: the simple page auto-detects your config when you return.

Audio Settings

Quality: Whisper Optimized (22 kHz, 64 kbps AAC) — optimized for voice
Microphone Selection: Choose from available mics (built-in, Bluetooth, USB, audio interface). Saved across recordings. Auto-fallback if unavailable. Available on iPhone, iPad, and Mac.
Mixed Audio: Record without interrupting system audio (iOS / iPadOS)
Background Recording: Continue when the app is minimized (iOS / iPadOS) or behind other windows (Mac)
Pause & Resume (v1.11): Pause without ending the file; resume to keep adding to the same recording

AI Settings

Engine Selection — Choose from all 8 AI engines (plus MLX Swift if experimental engines are enabled)
Model Configuration — Temperature, max tokens, comedy mode tone, etc.
Connection Testing — Verify API connectivity
Batch Regeneration — Update all summaries with new engine

Comedy Mode

Comedy Mode adds an optional tone to AI-generated summaries. Turn it on in Settings, pick a style (e.g. snarky), and supported engines will rewrite summaries in that voice. Disable it to return to the standard, neutral summary style.

Privacy & Security

v1.11 security hardening: BisonNotes AI now stores all sensitive credentials in the iOS Keychain, applies file protection to recordings and notes, and validates user-configurable AI endpoints to block insecure cleartext destinations.

How credentials are stored

Keychain-backed storage — OpenAI keys, Mistral keys, Google AI keys, AWS access keys/secret keys/session tokens, OpenAI-Compatible keys, and Whisper auth tokens all live in the iOS Keychain.
Automatic migration — Existing values stored in legacy locations are migrated into the Keychain on first launch of v1.11 and then removed from their old locations.
Process environment is cleared — Any inherited AWS_* environment variables are scrubbed at launch so AWS SDKs only use the credentials you configured in-app.
iCloud settings backup — Sensitive settings (API keys, AWS credentials) are excluded from iCloud settings backups by default. If a previous backup contained sensitive values, they are restored into the Keychain rather than re-saved to settings storage.

File protection

BisonNotes AI applies explicit iOS file protection to:

Audio recordings, imported audio, restored archives, and watch backups
Live transcription placeholder audio
Summary attachments and their metadata
Persistent error logs
The Core Data SQLite store and related files

Endpoint safety

User-configurable AI services (OpenAI, OpenAI-Compatible, Ollama, Whisper) are checked against an endpoint policy:

Local/private endpoints (loopback, link-local, RFC1918 networks) are allowed by default.
Public cleartext endpoints (plain HTTP or WS pointing at the open internet) are blocked unless you explicitly enable Development Mode for that service.
HTTPS / WSS public endpoints (Groq, Nebius, OpenAI, etc.) work as expected.

Development Mode: Enable it only on networks you control. It exists so you can connect to a self-hosted server on a public address while you set it up — it does not weaken transport security for any other engine.

Share Extension hardening

Imports from the Share Extension are now authorized with one-time tokens before the main app scans the shared container, and the imported files themselves are file-protected. Full file paths are no longer written to logs.

Troubleshooting

Recording Problems

No Audio: Check microphone permissions in Settings → Privacy
Poor Quality: Adjust audio quality settings, ensure proper mic distance
Background Recording: Enable in app settings

AI Engine Issues

Connection Failed: Check internet and API keys
Timeout Errors: Increase timeout settings
Authentication Errors: Verify API credentials

Transcription Problems

No Transcription: Check engine configuration
Poor Quality: Try a different engine or model
Large File Issues: Enable chunking for files over 5 minutes

Data Issues

Missing Recordings: Use Data Migration tools
Corrupted Data: Clear and re-import data
Sync Problems: Check iCloud settings

Performance Tips

Battery: Use local engines when battery is low
Memory: Close other apps during large file processing
Storage: Regularly clean up old recordings
Network: Use local engines to reduce data usage

Advanced Features

Background Processing

Job Queue — Multiple operations queued and processed in order
Progress Tracking — Real-time updates with accurate status display
Error Recovery — Automatic retry for failures
Stale Job Detection (v1.7) — Intelligent detection and recovery of stuck jobs, with timeouts based on actual processing start time
Job Cancellation (v1.7) — Properly cancel and interrupt running jobs when the app is backgrounded or closed
On-Device AI Handling — On-device AI jobs are gracefully interrupted when the app is backgrounded, since GPU processing requires the app to stay open
Live Transcription (v1.8) — On-device speech-to-text streamed in real time during recording via SFSpeechRecognizer; transcript auto-saved when recording stops
Duplicate Summary Cleanup (v1.8) — Automatically detects and removes duplicate summaries; manual cleanup available in Database Tools
Explicit credential resolvers (v1.11) — Background AWS jobs always pull fresh credentials from the Keychain so stale process-environment values can’t leak in

File Management

Import/Export — M4A, MP3, WAV, CAF, AIFF, AIF
Audio Export (v1.8) — Share any recording as an audio file via the iOS share sheet
Clean Audio Export (v1.10) — Exports use a clean, user-friendly filename derived from the recording title
Audio Archive — Offload selected or older audio files to iCloud Drive, keep an in-app restore pointer, and remove the archived cloud copy after restore
Video Import (v1.8) — Import video files; audio is automatically extracted to M4A
Audio Cleanup (v1.8) — Optional pre-transcription DSP: high-pass filter, noise gate, dynamic normalization, peak limiting
Share Extension — Import from Voice Memos, Files, etc., with one-time token authorization (v1.11)
Combining Recordings — Merge two into one
PDF Export — Professional reports with metadata, maps, page numbers
File Relationships — Audio/transcript/summary links maintained
Orphaned File Detection — Find and clean disconnected files
Selective Deletion — Choose what to keep
File Protection (v1.11) — Recordings, attachments, notes, and the Core Data store are stored with explicit iOS file protection

Watch Complications & Control Center Widget

Apple Watch Complications (v1.9) — Surface live recording state on watch faces. Tap the complication to open the watch app.
Control Center Recording Widget (iOS 18+) — Add the BisonNotes recording control to Control Center to start/stop recordings without opening the app.
Watch App — Full standalone recording on Apple Watch with automatic sync back to iPhone via WatchConnectivity.

Location Intelligence

GPS Integration — Automatic capture
Reverse Geocoding — Coordinates to addresses
Smart Search — 3-tier fallback system
University Database — Built-in campus mapping
Interactive Maps — View recording locations
Manual Location — Add locations after recording

iCloud Backup & Sync

iCloud Backup — Full backup of all data to iCloud Drive
Audio Archive to iCloud Drive — Space-saving audio offload with tracked restore locations. Third-party Files providers are paused for archive targets for now.
Auto-Backup (v1.7) — Automatically backs up when new recordings are created
CloudKit Sync — Optional summary synchronization across devices with paginated queries and schema-safe fallback for reliability
Sensitive data excluded (v1.11) — API keys and AWS credentials are never written into iCloud settings backups; if a previous backup contained them, they are restored into the Keychain instead.
Prompted after generating your first summary

Data Migration

Legacy Import — Migrate from old file-based storage
Data Integrity — Validate and repair data relationships
Batch Operations — Process multiple files at once
Progress Tracking — Monitor migration progress

Best Practices

Recording

Quiet environment
Mic 6-12 inches away
Break long sessions into segments
Minimize background noise

AI Configuration

Local engines for sensitive content
Start free, upgrade as needed
Experiment with models
Have a backup engine ready

Data Management

Export important recordings as PDF
Use iCloud Backup
Archive older audio to iCloud Drive before deleting local copies
Clean up old recordings
Use descriptive titles

Performance

Local engines when battery is low
Monitor available storage
Local engines on slow networks
Close other apps when processing

External Resources

Cloud Services

Local / Self-Hosted

Ready to get started? BisonNotes AI transforms your spoken words into actionable intelligence with advanced AI processing. Download the app and start recording today!

Need help? Report issues on GitHub or use the in-app help documentation.

This documentation is regularly updated. For the latest information, check the app’s built-in help.

BisonNotes AI

Getting Started

First Launch Setup

Initial Setup Options

Your First Recording

First Transcript & Summary

Recording Features

Mac Catalyst (v1.11)

Pause & Resume Recording (v1.11)

iPhone Action Button Integration

Location Tracking

Import Existing Audio

Archive Audio to iCloud Drive

Import via Share Extension

Combining Recordings

AI Engine Configuration

Requirements

Recommended Models (by RAM)

Experimental Models (enable in settings)

Setup

Summarization Models

Transcription Models

Setup

Available Models

Supported Providers

Setup

Guided In-App Setup (Recommended)

Summarization Models

Transcription

Manual Setup (Alternative)

Available Models

Setup

Requirements

Setup

Limitations

Setup

Setup

Transcription Configuration

Engine Selection

Available Engines

Transcription Engine Comparison

Initial Setup

Large File Processing

Working with Summaries

Viewing Summaries

Summary Features

Search & Filtering

Date Filters

Editing Metadata

Recording Title

Custom Date & Time

Location

Audio Playback

Basic Playback

Advanced Playback

Setup & Configuration

Simple Setup vs Additional Settings

Simple Setup

Additional Settings

Audio Settings

AI Settings

Comedy Mode

Privacy & Security

How credentials are stored

File protection

Endpoint safety

Share Extension hardening

Troubleshooting

Performance Tips

Advanced Features

Best Practices

Recording

AI Configuration

Data Management

Performance

External Resources

Cloud Services

Local / Self-Hosted