AI-powered transcription for audio and video in 119 languages
Speech and singing engine with sixteen voices that runs on your CPU
Stage
Startup
Not given
Founded
2025
Not given
Based in
CA
Not given
Pricing model
Freemium
Open source
Pricing
Free: 3 transcriptions per day, 30 minutes max file length. Pro: $10/month billed annually or $20/month monthly subscription with unlimited transcriptions, 10 hour max file length. Team: $15/user/month billed annually, everything in Pro plus centralized billing and team management.
Not given
Key features
Support for 119 languages with accent and dialect recognition
Speaker diarization to label each speaker
Word-level timestamps for precise navigation
Multiple export formats including SRT, WebVTT, PDF, DOCX, TXT, CSV
Handle audio and video files up to 10 hours long or 5 GB in size
Processes faster than real-time speed
End-to-end encryption and privacy-first security
REST API for programmatic access
AI agent integrations via Model Context Protocol
Free browser-based media tools including converters, joiners, and trimmer
Sixteen voices for speech and singing
Piano roll music editor with syllable-based lyrics
MIDI file import and export with lyrics
Vibrato control and voice mixing
Runs in browser and natively on macOS and Linux
Python and command line interfaces
0.1 second latency to first sound
Parts and scores saved as plain text files
What makes it different
Accurate transcription even with multiple speakers, background noise, and accents
Files are encrypted and never used to train models
Unlimited transcriptions on Pro plan with no usage caps
24-hour support response guarantee from founders
Single transcription engine across web app, API, and AI agent integrations
Runs entirely on your CPU with no cloud dependency
12 times faster than real time on a single CPU core