Audio and video transcription for interviews, meetings and podcasts
Local AI notetaker for Mac that records meetings without a bot and writes notes on-device
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
RO
Pricing model
Freemium
Free trial
Pricing
Free: 2 files, 30 minutes per day. Pay as you go: $4.99 one-time for 20 hours of standard transcription (credits never expire). Pro: $7.99/month with 120 standard hours per billing month and 10 separate advanced hours. Creator: $14.99/month with 250 standard hours per billing month and 25 separate a
Free: up to 15 minutes per recording. Unlocked: one-time purchase, no subscription.
Key features
Upload audio and video files in multiple formats
Automatic timestamps for each speaker
Edit and correct transcript text
Export as TXT and SRT files
Import captions from public YouTube videos
Multilingual recording support
Cross-device transcript sync with account
Advanced exports in VTT and DOCX format
AI summaries and chapter generation
Records any call without joining as a bot
Automatic meeting notes with decisions, key points and action items
Speaker-labeled transcripts in 99 languages
Search all meetings in plain language with source lines
Works with Zoom, Teams, Meet, Slack, FaceTime, Webex, Discord, WhatsApp and browser tabs
Integration with ChatGPT and Claude via Model Context Protocol
All processing runs on-device, nothing uploaded
Works offline after model download
Export transcripts as Markdown, text, SRT or WebVTT
Eight-hour recording limit per session
What makes it different
No account required to start transcribing
Free tier with 30 minutes daily and no credit card
Non-expiring credits for pay-as-you-go option
Supports up to 500 MB file size per upload
No bot joins your call, preserving meeting authenticity and security
All AI processing runs locally on your Mac, nothing leaves your device
One-time purchase model with no subscription, seat or recurring fees
Works with any meeting app through audio capture, no integrations needed
Automatic speaker identification and voice recognition across meetings