Open source dictation for Mac with local AI, instant speed and complete privacy
Free text to speech with AI voices, subtitles and no character limit
Stage
Not given
Not given
Founded
Not given
Not given
Based in
RO
Not given
Pricing model
Paid
Not given
Pricing
One Mac: $15 (or $9 for first 10 buyers); Three Macs: $20; Team (10 Macs): $79. 3-day free trial with everything unlocked. Free updates. 14-day refunds.
Free: 5 credits that never expire (up to 50 minutes of audio). Starter: $6.99/month or $69.99/year (100 credits per month, up to 1,000 minutes). Creator: $15.99/month or $159.99/year (300 credits per month, up to 3,000 minutes). Credit packs: 100 credits for $5 that never expire (available on paid p
Key features
Dictation into any app with one keyboard shortcut
Local speech processing in about 200 milliseconds
Automatic clean speech with filler word removal
Learn corrections to improve accuracy per user
21 vocabulary packs for specialized fields
Custom vocabulary packs from CSV or JSON files
Notes with searchable history and time-based reminders
Meeting mode with speaker labels and timestamps
Supports 25 European languages
Runs completely offline with no account required
50+ AI voices in 9 languages
Create custom voices by blending any two voices
Up to 10 minutes of audio per credit
No character limit for text input
Commercial use license included on all plans
Adjustable voice speed from 0.5x to 2x
Emotion tags like laugh and sigh for premium voices
MP3 and WAV output formats on paid plans
AI script tidy pass on paid plans
What makes it different
Open source GPL-3 code on GitHub you can read, build and verify
Complete privacy with no server, no account, no audio sent anywhere
Fastest local transcription at about 200 milliseconds latency
One-time purchase with free updates and no subscription
Works in terminal, code editors and AI coding agents
Subtitles are generated from the same render as the audio, ensuring perfect timing without manual adjustment
Free plan with 5 credits that never expire, sufficient for a full video or chapter
Over 23,000 voice combinations by blending 54 voices across languages
Server-side rendering allows long jobs to survive browser closure and phone rendering
Zumbo
TTSLark