BisonNotes AI 3.0 – User Guide

BisonNotes AI

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

Version 3.0

Contents

  1. Getting Started
  2. Recording Features
  3. AI Engine Configuration
  4. Transcription Configuration
  5. Beta Features
  6. Working with Summaries
  7. Audio Playback
  8. Setup & Configuration
  9. Accessibility
  10. Privacy & Security
  11. Troubleshooting
  12. Advanced Features
  13. Best Practices
  14. External Resources
  15. Guides for Other Versions
What’s new in 3.0:
  • Beta Features. A new page in Settings collects features that are still being finished. Turn on Beta Features, then each feature you want to try. See Beta Features.
  • Summary Prompt (beta). Choose Business Meeting, Personal Notes, or up to five prompts of your own for AI summaries. Each summary remembers the prompt it was made with. See Summary Prompt.
  • Transcript Cleanup is now a beta feature. If you already used it, it stays on. Summaries now use whichever version of a transcript you saved, Original or Cleaned, and cleanup pauses in the background and picks up where it left off. See Transcript Cleanup.
  • Trim Recording. Keep just the part of a recording you want, saved as a new recording. See Trimming a Recording.
  • Nemotron 3 speaker labels (experimental). A new on-device speaker-label method from NVIDIA for groups of up to 8 speakers.
  • More reliable processing. A finished summary or transcript is never redone or billed twice because of a problem after it was saved, and recordings recover more cleanly after interruptions.
What changed in 2.5 and 2.4
  • 2.5: on-device English transcript cleanup, deletions that survive a crash, clearer messages when a device is nearly full, and safer cache cleanup.
  • 2.4: much faster iCloud sync, sync that respects iCloud’s requests to wait, one coordinated recovery after a phone call, a microphone fallback for Mac meeting recordings, and reclaimed storage from model downloads.

Guides for earlier versions are listed in Guides for Other Versions.

Getting Started

First Launch Setup

  1. Install the App — Download BisonNotes AI from the App Store.
  2. 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. Uses MLX Swift for summaries on 4GB+ devices and Parakeet for transcription. Models download once, then run locally.
    • Advanced & Other Options: Configure providers manually. Includes Google AI Studio, Mistral AI, Compatible API, and Ollama on native macOS. 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”.
  3. 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
  4. Automatic Migration — On first launch, the app scans for existing audio files and migrates them into the database.

Your First Recording

  1. Start Recording — Tap the large microphone button on the main screen.
  2. 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).
  3. Recording Status — You’ll see a red recording indicator, live timer, and location indicator (if enabled).
  4. Pause & Resume — Tap the Pause button to pause without ending the file; tap Resume to continue. Works on iPhone, iPad, Apple Watch mute/resume, and Mac.
  5. Stop Recording — Tap the stop button to end.
  6. 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

Current 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
  1. Access Recording — After stopping, you’ll see it in the Recordings list.
  2. 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.
  3. Progress — You’ll see processing status and an estimate. You can continue using the app while it processes.
  4. View Results — Open the Transcripts tab to read the full transcript with editable text and confidence indicators.
Generate Your First Summary
  1. Prerequisites — You need a transcript first.
  2. Start Summary — Open the transcript (Transcripts tab) and tap “Generate Summary”. A second “Generate Summary” button is also available directly on the transcript row.
  3. 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
  4. 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” — Eligible recordings, transcripts, summaries, and selected settings sync across your devices through your private iCloud account. BisonNotes shows a HIPAA notice before enabling this.
  • “Keep Local Only” — Content stays on this device only. Better for privacy-sensitive content. Can be changed later.
  • Per-recording exclusions — Use Keep on This Device from a recording row or audio player to keep that recording, transcript, and summary out of BisonNotes iCloud sync and backup.
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

Native Mac App

BisonNotes AI is a native macOS app for Apple silicon Macs running macOS 15 or later. It shares its library with the earlier Mac Catalyst version, so updating keeps your existing recordings.

  • Mac-native workspace — Summaries, transcripts, players, library views, location details, and processing views can use movable and resizable windows. Settings opens in its own Mac Settings window.
  • Commands and shortcuts — Standard File and Edit menus provide import, export, navigation, and editing commands where available.
  • Data continuity — Existing Mac recordings, transcripts, summaries, settings, and iCloud configuration remain in the shared app container.
  • 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. BisonNotes remembers that preference through a temporary disconnect and reselects the device when it returns.
  • Device-change recovery — BisonNotes monitors the selected/default input. If an input changes or disconnects, it preserves completed PCM segments and attempts a bounded reconnection or fallback to the system default.
  • Record Meeting Audio — Optionally capture audio playing from other Mac apps while your microphone records your local speech. BisonNotes combines usable tracks into one M4A recording.
  • macOS permission — Meeting audio capture requires Screen & System Audio Recording permission. The setting explains why access is needed, opens the correct System Settings pane if necessary, and tells you when to quit and reopen BisonNotes. BisonNotes records audio only and does not save screen video.
  • Meeting transcription — When Live Transcription is enabled for a meeting-audio recording, BisonNotes queues transcription from the finalized combined file instead of transcribing only the live microphone.
  • Track-safe finalization — Microphone and system audio are checked independently. If only one track is usable, that track is saved instead of discarding the entire meeting. Failed source media is retained in Application Support for recovery and is listed in exported diagnostic logs.
  • Mac Share extension — Send supported audio and transcript files to BisonNotes from the macOS Share menu. The Mac and iOS extensions use the same protected, authorized import handoff.
  • Desktop recording widget — Add the small or medium BisonNotes widget to the Mac desktop or Notification Center, then select Record to open the app and begin a new audio note.
  • Focused player — The Mac app keeps one recording player window and reuses it when you open a different recording, avoiding conflicting playback controls.
  • Unsaved-edit protection — Closing an edited transcript asks for confirmation instead of silently discarding changes.
  • Local AI — On Device AI uses MLX Swift by default. Macs with 16 GB or more RAM can select Ternary Bonsai 27B (~8.5 GB).
  • Archive and export — Security-scoped archive locations survive relaunch, and native Mac RTF/PDF export and AppKit sharing are available.

Pause & Resume Recording

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, Apple Watch mute/resume, and Mac. On Mac the underlying pipeline uses AVAudioEngine for a clean pause boundary.

iPhone Action Button Integration

Available on: any iPhone with an Action Button (iPhone 15 Pro and later).

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

How to Configure the Action Button
  1. Open the Settings app on your iPhone.
  2. Navigate to Action Button.
  3. Select Shortcut as the Action Button function.
  4. Tap “Choose a Shortcut” → Search for “Start Recording” or “BisonNotes AI” → Select it.
  5. 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

  1. Tap “Import Audio Files” on the main screen.
  2. Select audio files from your device.
  3. Files are automatically added to your recordings library.
Use web addresses: BisonNotes can import direct links to audio, video, and transcript files. On Mac, use File → Import From Link; on iPhone and iPad, use Import From Link on the Recordings screen.
  1. Paste a URL — Enter an HTTPS link to an audio/video file, transcript document, or YouTube video.
  2. Choose import type — Leave Automatic selected, or choose Audio or Video / Transcript when you know what the link contains.
  3. Review the result — Audio and video links become recordings; transcript links become imported transcripts that can be summarized immediately.

Supported web link types:

  • Audio: M4A, MP3, WAV, CAF, AIFF, AIF
  • Video: MP4, MOV, M4V, AVI, MKV. BisonNotes extracts the audio to M4A.
  • Transcripts/documents: TXT, MD, VTT, SRT, PDF, DOC, DOCX
YouTube note: YouTube audio/video is not downloaded directly. BisonNotes tries to import public captions as a transcript. If YouTube blocks the caption request, BisonNotes shows directions, an Open YouTube Video button, and a pasted-transcript box so you can copy the transcript from YouTube and import it for summary generation.
Security: Public HTTP links are blocked. Use HTTPS, localhost, or private-network addresses.

Archive Audio to iCloud Drive

  1. Select one or more recordings, or choose the archive option for recordings older than a selected age.
  2. Choose an iCloud Drive location when the document picker opens.
  3. Optionally remove the local audio after export. Transcripts, summaries, tasks, reminders, and metadata remain in BisonNotes.
  4. 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.

Import via Share Extension

Share from other apps: Import audio and transcript files directly from Voice Memos, Files, and other apps using the iOS share sheet.
  1. Open the source app — Voice Memos, Files, or any app with the audio or transcript file.
  2. Tap Share — Select “BisonNotes AI” from the share sheet.
  3. Automatic Import — The file is saved and BisonNotes AI opens to import it.
  4. 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, VTT, SRT, 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
  1. Select recordings — Go to Recordings tab → tap “Select” → check two recordings.
  2. Tap “Combine” — A “Combine” button appears when two are selected.
  3. Choose order — The app recommends chronological order. Tap the “First” card to swap if needed.
  4. Review & confirm — Check combined duration preview, tap “Combine Recordings”.
  5. 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

Trimming a Recording

When to use: Keep only the part of a recording you need — for example, to cut silence after a meeting ended. The trimmed part is saved as a new recording, and the original is not changed.
  1. Open Trim — Tap Trim in the audio player, or touch and hold a recording in the Recordings list and choose Trim Recording…. The recording’s audio must be on this device.
  2. Choose the part to keep — Move the start and end points. The sheet shows how long the kept part will be.
  3. Find trailing silence (optional) — Tap Find Trailing Silence. If speech appears to end before the recording does, tap Use Suggested End.
  4. Save — Tap Save as New Recording. Transcribe and summarize the new recording as usual.

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 18.5+ or native macOS 15+, with a Parakeet model download. No additional Local Speaker Labels RAM/device guarantee is published without measured evidence.
  • AI Summary (MLX Swift): 4GB+ RAM. Uses Ternary Bonsai models scaled to your device.
  • Storage: MLX models are about 470 MB to 2.3 GB on iPhone and iPad. Native macOS also offers an optional 27B model of about 8.5 GB. Parakeet transcription downloads separately.

MLX Models (by RAM)

  • 4GB+: Ternary Bonsai 1.7B (~470 MB) — Compact local summaries for lower-memory devices
  • 6GB+: Ternary Bonsai 4B (~1.1 GB) — Default model for most supported devices
  • 8GB+: Ternary Bonsai 8B (~2.3 GB) — Slower but higher-quality summaries
  • Native macOS, 16GB+: Ternary Bonsai 27B (~8.5 GB) — Laptop-class reasoning available only in the native Mac app
Migration: Existing installations with a legacy llama.cpp selection are moved to the closest MLX model tier. Known legacy GGUF files and legacy settings are removed to reclaim storage. Stale selections on devices below 4GB use the Mistral AI fallback because MLX requires 4GB+ RAM.

Best for: Privacy-conscious users, offline use, and local summaries without sending transcript text to a cloud provider.

2. 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

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

Available Models

  • Gemini 3.7 Flash (Default) — Fast and efficient
  • Gemini 3.5 Flash Lite — Lightweight variant for quick processing

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

3. Compatible API — LiteLLM, llama.cpp, Groq, etc.
Cloud/Local Flexible

Type: Compatible chat-completion 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 compatible chat-completion endpoint

Setup

  1. Go to Setup → AI Settings → Compatible API
  2. Enter API key and base URL for your provider.
  3. Select model (use your provider’s exact model name, e.g., llama-3.1-70b-versatile for Groq).
  4. 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

4. 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:

  1. 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”
  2. Create account — The wizard opens console.mistral.ai in an in-app browser. Sign up with email and verify your phone number.
  3. Generate API key — The wizard opens the API keys page. Create a key named “BisonNotes” and copy it.
  4. Paste & validate — Paste your key (or use the clipboard button), then test the connection.
  5. 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
  • Mistral Small 4 (26.03) — Efficient hybrid instruct/reasoning model with a controllable light reasoning pass (Standard)
  • Mistral Medium 3.5 — Current medium model with adjustable reasoning effort and a 128K app context cap (Standard)
  • 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)

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

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

5. 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

  1. Go to Setup → AI Settings.
  2. Select Apple Native from the engine library.
  3. 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+

6. Ollama — Local LLM Server (native Mac only)
Local Free

Type: Local server on the native Mac app • Cost: Free • Privacy: 100% local • Internet: Required for installation and model downloads only

Mac only: Ollama is available in BisonNotes only on native macOS. It is not offered as an iPhone or iPad engine. BisonNotes connects to Ollama running on the same Mac through the loopback address http://localhost:11434.
Existing iPhone/iPad users: If an older version saved Ollama as your engine, BisonNotes automatically switches to the best available on-device engine when you next launch the app. If the device cannot run an on-device model, it uses another configured fallback.

Install Ollama on your Mac

  1. Open the official Ollama for macOS download page. The current macOS app requires macOS 14 Sonoma or later.
  2. Open the downloaded disk image, drag Ollama to Applications, and launch it.
  3. Open Terminal and download at least one model, for example: 
    ollama pull llama3.2
    You can choose another model from the Ollama model library; larger models need more memory and storage.
  4. Leave Ollama running. If you use the command line instead of the Mac app, ollama serve starts the local server.

Connect BisonNotes to Ollama

  1. Go to Setup → AI Settings → Ollama.
  2. On the native Mac app, leave Server URL as http://localhost and Port as 11434. BisonNotes seeds these values when you choose Ollama unless you already configured a custom server.
  3. Choose Test Connection; once connected, the available model list loads. Select the model you downloaded, then save/dismiss Ollama Settings.
  4. Select Ollama in the Engine Library and generate a summary from a transcript.
Troubleshooting: If the connection test fails, open Ollama from Applications and try again. You can verify the local API in Terminal with curl http://localhost:11434/api/tags. The default loopback connection keeps transcript text on the Mac.

Best for: Privacy, customizable models, offline use

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

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

Available Engines

  • On Device (Parakeet) — Default. Free, private, works offline. Requires model download.
  • 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).

Transcription Engine Comparison

EngineTypeSpeakersCost
On-Device (Parakeet)LocalOptional Local Speaker Labels after completed audioFree (Default)
Mistral AI Free TierCloudYesFree tier included; paid tiers for higher limits (~$0.003/min transcription)
Whisper (local)LocalNoFree
On Device Transcription (Parakeet) — Default
v2.1: Parakeet is the default on-device transcription path. BisonNotes now keeps valid cached model files across app updates or settings resets, clears stale download state when files are missing, and avoids tiny final tail chunks on long local transcriptions.

Initial Setup

  1. Enable: Setup → Transcription Settings → select “On Device” → Parakeet is selected by default.
  2. Choose a model: Parakeet v2 is English-only with stronger long-form English recall. Parakeet v3 supports multilingual transcription across 25 European languages.
  3. Download the model: Tap “Download” to get the selected Parakeet model. Progress now shows checking, downloading, preparing, and ready states.
  4. Requirements: iOS 18.5+ or native macOS 15+, model download required.
Migration note: WhisperKit was removed in v1.8. Users who had WhisperKit selected are automatically migrated to Parakeet on first launch.
Benefits: Complete privacy, works offline, no API costs.

Local Speaker Labels (Optional)

Local Speaker Labels are opt-in and off by default. They run only after a completed Parakeet recording, imported audio file, or transcript re-run. They run once against the complete source audio after Parakeet ASR and reassembly; they never run during Live Transcription or in real time.

  1. Enable: In On Device settings, turn on Local Speaker Labels. Enabling the toggle does not download a model.
  2. Choose a method: Offline VBx — Recommended estimates the number of speakers without an app-side two- or three-speaker cap. Nemotron 3 — Experimental uses NVIDIA’s Nemotron 3 Diarization model and supports up to 8 speakers; a ninth voice is merged into another speaker rather than reported, so choose Offline VBx for larger groups. LS-EEND — Experimental uses the DIHARD3 500 ms model and supports up to 10 speakers; labels may be over-segmented or less stable, and LS-EEND is limited to complete files up to one hour.
  3. Prepare explicitly: Tap Download Speaker Model for the selected method. This is the initial HTTPS download; cached use works offline afterward, audio stays on the device, and no API key is required.
  4. Manage models: Parakeet, Offline VBx, Nemotron 3, and LS-EEND have independent readiness, cached files, unload, and delete state. Deleting a speaker model does not delete Parakeet or the other speaker models. Switching methods preserves caches and does not silently prepare a model.
  5. Rename speakers: Open the completed transcript, use its existing speaker controls to rename a speaker, and save. The saved mapping is used by speaker-aware transcript and summary views.
Fallback: If the selected model is missing, LS-EEND exceeds one hour, or timing/alignment/diarization fails, BisonNotes keeps the complete unlabeled Parakeet transcript and shows a visible warning. It does not silently switch methods or upload audio.
Measured limits: This guide does not publish model sizes, RAM/device guarantees, performance, or accuracy. Those claims require the opt-in model/accuracy gate in the regression regimen.
Whisper (Local Server) Setup
  1. Install a Whisper-compatible server: Run your preferred local server on port 9000, then configure its REST API or Wyoming endpoint below.
  2. 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.

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

Beta Features

Beta features might not work as intended. They are features we are still finishing. Try them on recordings you can afford to redo, and report anything that goes wrong.

Turning beta features on

  1. Open the Beta Features page — On iPhone and iPad, go to Settings → Configuration → Beta Features. On Mac, open Settings and choose the Beta tab.
  2. Turn on Enable Beta Features — BisonNotes asks you to confirm first.
  3. Turn on each feature you want — Each feature has its own switch and settings on the same page.

Turning Enable Beta Features off returns everything to the standard behavior. Your choices for each feature are kept, so turning it back on restores them.

Summary Prompt

A summary prompt tells the AI what kind of summary to write. Pick the default for new summaries on the Beta Features page:

  • Default — The standard summary, with Summary Detail and Comedy Mode applied as usual.
  • Business Meeting — Decisions, owners, and next steps.
  • Personal Notes — Ideas, reflections, and things to remember.
  • Your own prompts — Up to five, each with a name, your wording, and a recording type: Auto-detect, Meeting, or Personal Notes.

Choose Edit prompts to change the wording of Business Meeting and Personal Notes (with an option to restore the original), or to add, rename, and delete your own prompts.

  • Only the summary changes. Tasks, reminders, and suggested titles always use the standard prompts.
  • Each summary remembers its prompt. The summary shows which prompt made it. Regenerate starts with that prompt and lets you pick another, and always uses the prompt’s current wording. If you delete a prompt, its summaries regenerate with Default.
  • Your own prompts take over format and tone. Summary Detail and Comedy Mode are not used with a custom prompt.

Transcript Cleanup

Speech-to-text writes down exactly what was said, which is not always easy to read. Transcript Cleanup rewrites a finished English transcript into written English: it adds punctuation and sentence breaks, removes fillers such as “um” and “uh”, and resolves spoken corrections. It runs entirely on your device using S1-mini by Superwhisper; nothing is uploaded.

Your original transcript is always kept. The cleaned text is stored next to the original, along with the original timing and speaker labels.

Setting it up

  1. Turn on Transcript Cleanup on the Beta Features page.
  2. Download S1-mini from the same page, or from the transcript editor. BisonNotes never downloads it on its own.
  3. Turn on Clean up transcripts automatically (English only) if you want every new file transcript cleaned. You can also clean one transcript at a time with Clean up English transcript in the transcript editor, including imported transcripts.

Original and Cleaned

  • When a transcript has cleaned text, the editor lets you switch between Original and Cleaned. It opens on the version you last saved, and a finished cleanup saves Cleaned.
  • Summaries, copy, share, and text export use the version you saved.

How automatic cleanup runs

  • The raw transcript is always saved first, so cleanup never holds it up.
  • Cleanup runs while BisonNotes is open. iOS does not allow on-device AI in the background, so it pauses when you leave the app and continues from where it stopped when you come back. It also waits while you are recording or transcribing.
  • The editor shows progress, such as “Cleaning… 12 of 40 passages”.
  • If a passage cannot be cleaned, it keeps its original text and the rest of the transcript is still cleaned. The editor says how many passages were kept.

Where it works

Transcript Cleanup needs a Mac with Apple silicon or a supported iPhone or iPad. It is not available on Apple Watch or in the iOS Simulator. On a device that cannot run it, the setting explains why.

What it will not do

  • It does not translate. Transcripts in other languages are left alone, with a note explaining why.
  • It does not change speaker labels or timing.
  • It does not add facts or summarize.
  • It never runs on Live Transcription text.

To reclaim the space, choose Remove Download. Transcripts you already cleaned keep their cleaned text.

Working with Summaries

Viewing Summaries

  1. Tap the “Summaries” tab.
  2. Browse recordings with AI-generated summaries.
  3. 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

  1. Go to the “Recordings” tab.
  2. Tap any recording to play.
  3. 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: Mistral AI, On Device AI, or Advanced
  • Preserves settings when switching

Additional Settings

Full control over all options.

  • All current AI engines, including On Device AI (MLX Swift), cloud providers, Ollama on native macOS, and Apple Native
  • All transcription engines
  • Microphone selection
  • Preferences, iCloud, background processing, diagnostics, and experimental model 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: Pause without ending the file; resume to keep adding to the same recording

AI Settings

  • Engine Selection — Choose from local, cloud, compatible API, Ollama on native macOS, and Apple Native engines
  • Summary Detail — Choose Brief, Balanced, or Detailed narrative output; tasks, reminders, titles, and content type remain factual metadata.
  • Summary Thinking — Choose Off or Light. Light is applied only when the selected model has a known safe thinking control; reasoning text is not shown in the final summary.
  • Model Configuration — Temperature, max tokens, and supported model-specific controls.
  • 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 Snarky or Funny, and supported engines will rewrite only the narrative summary in that voice. A custom Summary Prompt replaces Comedy Mode. Tasks, reminders, titles, and facts remain grounded in the transcript. Disable it to return to the standard, neutral summary style.

Accessibility

Accessibility goal: BisonNotes AI is designed so common recording, transcription, summary, setup, settings, and watch recording tasks can be completed with Apple accessibility features where the platform supports them.

Supported accessibility features

  • VoiceOver: Main controls, rows, playback actions, setup options, settings, transcripts, summaries, and Apple Watch recording controls include labels, values, and hints.
  • Voice Control: Common buttons and repeated row actions use clear names, often with the recording, transcript, or summary title included.
  • Larger Text: BisonNotes uses SwiftUI system text styles and wrapping layouts across the main app surfaces.
  • Reduced Motion: Recording indicators on iPhone, iPad, and Apple Watch avoid relying on pulsing animation when Reduce Motion is enabled.
  • Contrast and non-color state: Important states such as recording availability, local-only status, transcript/summary availability, and sync state are exposed as text, not color alone.
  • Keyboard access: Native Mac and iPad keyboard users should be able to move through standard buttons, lists, settings, dialogs, and forms with keyboard navigation and Full Keyboard Access.

Common accessible workflows

Recording and playback

Start recording, pause/resume, stop, browse recordings, play/pause audio, skip, scrub in 15-second accessibility increments, rename, export, and manage Keep on This Device state.

Transcripts and summaries

Open transcript rows, generate summaries, edit transcript text, review summary sections, export reports, update titles, manage tasks/reminders, and edit date or location metadata.

Setup and settings

Select processing method, open Additional Settings, adjust transcription/AI/iCloud options, review background processing, and export diagnostic logs.

Apple Watch

The main watch button announces ready, recording, paused, saving, transferring, and unavailable states. Mute, transfer progress, low battery, and error recovery are also labeled.

Platform notes

  • iPhone and iPad: Accessibility coverage includes setup, recording, imports, recordings, playback, transcripts, summaries, and settings. Control Center and Action Button recording still require a supported real device.
  • Native macOS: The shared SwiftUI surfaces use the same accessibility labels and values as iPad, with Mac-native windows, menus, and Settings. For releases, also test macOS VoiceOver, Full Keyboard Access, keyboard navigation, file import, microphone recording, and window resizing on a real Mac.
  • Apple Watch: The watch app supports VoiceOver-friendly recording state and reduced motion behavior, but watch flows must be verified on a physical watch.

Known limitations

  • Transcripts are not the same as synchronized captions. Do not treat BisonNotes transcripts as caption tracks for all media playback.
  • Audio descriptions are not supported.
  • External provider account pages, system permission prompts, Files pickers, and share sheets are controlled by Apple or the provider and may have separate accessibility behavior.
  • Hardware-dependent flows such as microphone capture, Apple Watch transfer, iCloud sync, Control Center, and Action Button recording require real-device testing.
Feedback: If an accessibility task does not work as expected, include your device model, OS version, BisonNotes AI version, the accessibility feature you were using, and the task that failed when reporting the issue.

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 — Compatible API keys, Mistral keys, Google AI 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.
  • iCloud settings backup — Sensitive settings (API keys) 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 (compatible API, Ollama on native macOS, and 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, and similar providers) 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
  • Mac meeting audio missing: Enable Record Meeting Audio in BisonNotes Settings → Recording, grant BisonNotes access in macOS System Settings → Privacy & Security → Screen & System Audio Recording, then quit and reopen BisonNotes. If permission or mixing fails, the app still saves microphone audio.
  • A call interrupted a recording: The completed portion is preserved and appears in Recordings. If iOS would not return the microphone while BisonNotes was in the background, recovery is deferred — open the app to let it finish, then start a new recording if you still need one.
  • Mac meeting recording has system audio but no microphone: The microphone could not start or was lost during capture, and BisonNotes deliberately saved the usable track. Check macOS microphone permission and the selected input, reconnect the device, and make a short test recording.
  • Preferred Mac microphone disappeared: Reconnect the USB, Bluetooth, or interface input. BisonNotes temporarily uses the system default while it is absent and reselects the saved microphone when it returns.
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
  • A model stays “not ready” after an interrupted download: A multi-part model interrupted mid-copy is now correctly reported as incomplete. Start the model setup again; the retained download cache lets it resume rather than start over.
  • Parakeet says a model is missing: Open Transcription Settings and re-download the selected Parakeet model. BisonNotes will reuse valid cached files when they exist, but clears stale settings if the files were removed.
Transcript Cleanup Problems
  • The cleanup setting is unavailable: This device cannot run the on-device model — for example an Intel Mac, a device without enough memory, or the Simulator. The setting shows the reason. Check that Beta Features and Transcript Cleanup are both turned on.
  • A transcript finished but was not cleaned: S1-mini may not be downloaded on this device, the text may not be confirmed as English, or the app was in the background. Cleanup resumes when you return to the app; the transcript itself is always saved.
  • The language could not be confirmed as English: Very short transcripts do not give the language check enough to work with. Use Clean up English transcript in the editor to run it anyway; text that is clearly another language is still refused.
  • Some passages were kept as they were: S1-mini could not clean those passages, so they keep their original text. The rest of the transcript is cleaned.
  • Cleanup is slow on a long recording: It works through the transcript one passage at a time and waits while you record or transcribe. Leave BisonNotes open to let it finish.
Data Issues
  • Missing Recordings: Use Data Migration tools
  • Corrupted Data: Clear and re-import data
  • Sync Problems: Check iCloud settings
  • A backup says it is waiting: An automatic sync was already running. Your request starts as soon as that run finishes; leave the app open.
  • Sync reported as deferred: iCloud asked BisonNotes to wait before sending more requests. The work is kept and retried — most common right after a large first sync.
  • A deleted item came back: Since 2.5, a deletion and the note telling your other devices about it are saved together, so deleted items stay deleted. If one reappears from a device still on an older version, update that device and delete the item once more.
  • Not enough space to upload audio: BisonNotes tells you once and keeps syncing text, summaries, and settings. Audio uploads resume when there is free space.

Performance Tips

  • Battery: Use local engines when battery is low
  • Memory: Close other apps during large file processing
  • Storage: Regularly clean up old recordings. Since v2.4, BisonNotes also sweeps its own caches in the background — unused local-model downloads and iCloud’s copies of transferred audio — so free space can keep increasing across the first launches after updating. Your recordings, transcripts, summaries, attachments, and archived audio are never touched by that sweep.
  • 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 — Local 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 reconciles superseded summaries during iCloud sync; local troubleshooting reports identify relationship issues without deleting content
  • Temporary audio cleanup (v2.1) — Conservative startup cleanup removes stale scratch, merge, and chunk files left by failed or interrupted audio workflows without touching active recordings.
File Management
  • Import/Export — M4A, MP3, WAV, CAF, AIFF, AIF, plus transcript documents such as TXT, MD, VTT, SRT, PDF, DOC, and DOCX
  • Import From Link (v2.3) — Import direct HTTPS links for audio/video files and transcript documents; YouTube links can import public captions or fall back to pasted transcript text when captions are blocked
  • 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 Extensions — Import supported audio and transcript files from iPhone, iPad, and Mac Share menus with one-time token authorization. If another import is already active, staged files remain available for a later retry instead of being discarded.
  • 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
Recording Widgets, Watch Complications & Control Center
  • Mac Recording Widget (v2.3) — Add the small or medium BisonNotes widget to the Mac desktop or Notification Center and select Record to open the app and start a new audio note.
  • 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 (v2.0) — Full standalone recording on Apple Watch with one large tap target: tap to record, tap to stop, and use mute to pause/resume the same file.
  • Watch Sync (v2.0) — The watch sends the finished audio file to iPhone with WatchConnectivity. The phone imports it, avoids duplicate imports, and sends queued success/failure confirmations back to the watch.
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 Sync Notice: BisonNotes AI and uploads to iCloud are not HIPAA-compliant. When iCloud Sync is enabled, eligible recordings, transcripts, summaries, and selected settings may be uploaded to your private iCloud account.
  • 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
  • Automatic cross-device sync — When iCloud Sync is enabled, BisonNotes reconciles eligible recordings, transcripts, and summaries when the app launches or becomes active. The Include audio files checkbox controls whether audio files are uploaded and restored.
  • CloudKit Sync — Optional summary synchronization across devices with paginated queries and schema-safe fallback for reliability
  • Batched sync (v2.4) — A routine pass reads the dataset in a small number of batched requests and issues one batched save and one batched delete, instead of a request per record. Deletion markers from other devices are worked out together and applied once.
  • Throttle-aware retries (v2.4) — BisonNotes honors the wait iCloud asks for. A long wait becomes a deferred run that is retried later; queued work is never dropped.
  • One operation at a time (v2.4) — Sync requests that arrive during a run join it or collapse into a single follow-up, and a backup or restore you start yourself reports that it is waiting rather than returning zeroed counts.
  • Metadata before audio (v2.4) — Recording details sync without waiting on audio uploads, and audio transfer is measured separately.
  • Mac, iPhone, and iPad sync — iOS, iPadOS, and native macOS use the shared iCloud container iCloud.Bison-Networking.BisonNotes-AI. Devices must use the same Apple ID and CloudKit environment. Local Debug builds use the CloudKit development environment, while TestFlight and App Store builds use production, so a Debug Mac build will not see production iPhone or iPad records until the build channel/environment matches.
  • Production schema required — TestFlight and App Store builds require the CloudKit production schema to include the app-managed backup record types before sync can save new backup records. Production clients cannot create new CloudKit record types at runtime.
  • Review iCloud Items — Current app versions mark synced content as active before it is automatically restored on other devices. Older cloud-only items that are not marked active are held in Settings, where they can be restored or deleted from BisonNotes iCloud sync records.
  • Keep on This Device — Mark an individual recording from its recording row or audio player to exclude that recording, transcript, and summary from BisonNotes iCloud sync and backup. When enabled, BisonNotes skips future app-managed iCloud sync/backup for that item and removes known app-created iCloud records when iCloud is available.
  • Deleted item cleanup — Deleting a recording writes an iCloud deletion marker and removes known app-created iCloud records. Other devices apply that marker before uploading so deleted items are not silently re-created. Active cloud-only records without a deletion marker are restored, while older untrusted cloud-only records are held for review.
  • Summary-only cleanup — Deleting a summary while keeping its recording/transcript queues removal of the summary’s live record, backup record, and content-index reference. If iCloud is unavailable, BisonNotes retries the queued removal later.
  • Sensitive data excluded (v1.11) — API keys 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 for eligible items; use Keep on This Device for items you want excluded from BisonNotes iCloud sync and 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.

Guides for Other Versions

This guide is for BisonNotes AI 3.0. To check your version on Mac, open Settings → Advanced. On iPhone and iPad, open BisonNotes AI in the App Store and check Version History. The Help buttons in the app always open the guide for the version you have installed.

Older versions open the guide for the current App Store version.

Written for BisonNotes AI 3.0. Features can vary by device, permissions, selected engine, and operating system version.