AI dictation for Mac that turns natural speech into clear, polished text
TikTok video transcript generator that turns public social videos into editable text
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Free: 3,000 text units per week, all features included. Unlimited: $6.99/month or $59.99/year (equivalent to $5/month). Prepaid credits: CNY 9.90 one-time for 30,000 usage units.
Free: 3 transcripts daily, up to 5 minutes each. Starter: $4.99 USD for 150 credits (one-time, valid 12 months). Creator: $19.99 USD for 800 credits (one-time, valid 12 months). 1 credit per started minute. Free transcripts can be upgraded to paid formats (SRT, VTT, DOCX) with 1 additional credit.
Key features
Multilingual voice-to-text with automatic language detection
Translation into 28 target languages
AI text cleanup that preserves tone and style
Personal dictionary with learning from corrections
Optional Screen Context for spelling hints
System-wide text insertion with copy fallback
Dictation history and transcript recall
Custom keyboard shortcuts
Native Swift app for macOS
Lightweight 6.5 MB application
Transcribe public TikTok, Instagram, Facebook and X videos from links
Speech recognition from audio track, works without captions
Edit individual timestamped segments
Export as TXT, SRT, VTT or DOCX formats
Batch transcription of up to 20 videos
Upload MP3, MP4, WAV or M4A audio and video files
Free allowance of 3 daily transcripts up to 5 minutes each
Paid transcription supports videos up to 60 minutes
Create public sharing links with private snapshots
Cross-device sync for account holders
What makes it different
Works in any Mac app where you're typing without switching applications
Cloud-powered processing with no audio storage
Learns and improves from your corrections
All features available on the free plan
One-minute setup with minimal configuration
No sign-up required for free transcripts
One-time credit purchases with no auto-renewal or subscription
Failed transcripts cost zero credits
Works from audio speech recognition rather than captions or descriptions
Editable transcript with automatic timestamp preservation