Every word captured.
Nothing leaves your device.
Dictation, transcription, and meeting notes. On-device with Whisper and NVIDIA Parakeet.
14-day free trial · No account needed
$49 one-time purchase· 2 devices included
Works in every app
You think at 150 WPM.
You type at 40.
3.5x faster
Close the gap between thinking and writing.
THREE TOOLS, ONE APP
Dictation. Transcription. Meetings.
SPEECH-TO-TEXT
Hold a key. Speak. Release.
Push-to-talk dictation that works in every app. 30 languages, guided model setup, grammar correction.
- ✓ Whisper + Parakeet models
- ✓ 30 languages
- ✓ Grammar correction
- ✓ Voice notes
- ✓ Screenshot smart paste
Learn more →
TRANSCRIPTION
Drop a file or paste a URL.
Transcribe audio files or URLs from 1,800+ sites. Timestamped transcripts with AI-powered summaries.
- ✓ Drag-and-drop files
- ✓ 1,800+ URL sources
- ✓ AI summaries
Learn more →
MEETING INTELLIGENCE
Record any meeting.
Capture system audio + mic from Zoom, Meet, or Teams. Get AI-structured summaries with action items.
- ✓ System audio + mic
- ✓ AI meeting notes
- ✓ Markdown export
- ✓ Auto-detects Zoom, Meet, Teams
Learn more →
INSIDE THE APP
Your voice work in one place.
Dictation stats, waveform controls, and notes — all from a single dashboard.
TESTIMONIALS
What users are saying
“I've tried almost every dictation tool out there, but VoxBee is the first one that actually stuck. As someone who needs to move fast, it's become an essential part of my daily workflow. I'm using it for everything from quick iMessage replies to drafting long-form docs. It completely closes the gap between thinking and writing. The fact that it works 100% offline gives me total peace of mind regarding my data, and the speed of the on-device transcription is honestly unmatched. It's rare to find an app that's this powerful and stays completely out of your way!”
Avinash Parida
Director, Product Design at Meta
CUSTOMIZATION
Choose your model. Make it yours.
Pick from on-device Whisper and NVIDIA Parakeet models, or bring your own API key for cloud providers. Customize your workflow with 8 color themes, 8 waveform styles, flexible hotkeys, screenshot smart paste, and a personal dictionary.
7 Whisper Models
From Tiny (75MB, instant) to Large v3 (2.9GB, most accurate)
NVIDIA Parakeet Models
Fast English dictation and multilingual European transcription with on-device FastConformer models
11 Cloud Providers (BYO Key)
Prefer a hosted model? Bring your own API key for OpenAI, Deepgram, AssemblyAI, ElevenLabs, Groq, xAI Grok, Mistral Voxtral, Cohere, Speechmatics, Alibaba Qwen3-ASR, or Soniox. A purple cloud badge stays visible whenever audio leaves the device.
On-Device Auto-Format (Beta)
On macOS 26 with Apple Intelligence, an on-device Apple Foundation Models pass adds punctuation, capitalization, and list cues. Local-only, off by default.
Text-to-Speech & Audio Studio
Read notes, summaries, transcripts, and history aloud from a floating dock. Six engines — System (free, on-device), OpenAI, ElevenLabs, Deepgram Aura, Groq PlayAI, Cartesia. Paste text into Audio Studio to preview voices and export to MP3 or WAV.
Google Drive Sync
Mirror your VoxBee library — meetings, transcriptions, and notes — to a folder in your own Drive. Scoped to files VoxBee creates (drive.file). Drag the folder anywhere in Drive and sync keeps working.
Unified Provider Keys
Drop in your OpenAI key once and it powers Whisper STT, GPT summaries, and TTS — no triple entry. One Keychain entry per provider, shared across STT, LLM, and TTS.
8 Color Themes
Ocean, Sunset, Aurora, Lavender, Ember, Mint, Monochrome, Neon
8 Waveform Styles
Classic bars, glow orb, particles, liquid blob, and more
Configurable Hotkeys
Option, Fn, or Control — your choice
Screenshot Smart Paste
Capture your screen while dictating. Image auto-pastes into Slack, VS Code, browsers, and 20+ apps.
Personal Dictionary
Teach VoxBee your name, jargon, and domain terms. Phonetic matching catches even misheard words.
Your words never leave your device.
While others send your audio to the cloud, VoxBee processes everything locally on your Mac or Linux machine.
Powered by WhisperKit — open-source on-device inference
COMPARE
Why go offline?
See how VoxBee compares to cloud-based alternatives.
| VoxBee | Otter.ai | Fireflies | Whisper CLI | |
|---|---|---|---|---|
| Works offline | ✓ | ✗ | ✗ | ✓ |
| Data stays on device | ✓ | ✗ | ✗ | ✓ |
| System-wide dictation | ✓ | ✗ | ✗ | ✗ |
| Personal dictionary | ✓ | ✗ | ✗ | ✗ |
| Meeting recording | ✓ | ✓ | ✓ | ✗ |
| AI meeting summaries | ✓ | ✓ | ✓ | ✗ |
| File transcription | ✓ | ✓ | ✓ | ✓ |
| No account required | ✓ | ✗ | ✗ | ✓ |
| Price | $49 once* | $8/mo† | $10/mo† | Free |
| Desktop app | ✓ | Web only | Web only | ✓ |
| Mac & Linux | ✓ | Any (web) | Any (web) | ✓ |
* $49 one-time purchase — no subscription.
† Billed annually (lowest paid tier). Otter Pro: $8.33/mo annual, $16.99/mo monthly. Fireflies Pro: $10/mo annual, $18/mo monthly.
Pricing verified March 2026.
FAQ
Frequently asked questions
And we're just getting started.
More accuracy, more media types, more intelligence — coming soon.
Windows Support
VoxBee on Windows — same on-device dictation, file transcription, and meeting recording, with a native install experience.
Voice Cloning
Capture a short sample of your own voice and use it inside Audio Studio. Read scripts, voicemails, and drafts back in the voice that sounds like you.
Read Aloud Anywhere
A global hotkey that reads whatever text you have selected — in any app — using VoxBee's TTS engines. Same floating dock, same six voices, from anywhere on your Mac.
One price. Yours forever.
No subscriptions. No cloud fees. Just yours.
One-time purchase · 2 devices included
- ✓Speech-to-text dictation
- ✓Audio file transcription
- ✓Meeting recording & AI summaries
- ✓Personal dictionary
- ✓Voice notes with AI templates
- ✓Whisper + Parakeet models
- ✓30 supported languages
- ✓8 themes & 8 waveforms
- ✓Grammar correction
- ✓Lifetime updates
- ✓Mac & Linux
No monthly fees. No accounts. No cloud.