Authenticated Access Only
Conversational Speech Generation
Data Not Used for AI Training
Data Security & Encryption
Dataset Size
1 million hours
Model Sizes
Tiny: 1B backbone, 100M decoderSmall: 3B backbone, 250M decoderMedium: 8B backbone, 300M decoder
Multiple Speaker Handling
Objective Metrics
Word Error RateSpeaker SimilarityHomograph DisambiguationPronunciation Consistency
Partial Multilingual Support Planned
Planned for 20+ languages
SOC 2 Compliance In Progress
Subjective Metrics
Comparative Mean Opinion Score
Supported Use Cases
Personal journalingDoctor appointmentsCreative ideasLecture notesHome projectsRecord and preserve memoriesSales & client callsProject progress loggingCustomer supportTeam management & collaborationInterviews & recruitingEOD reports
Transcription Accuracy
More accurate than Apple and Otter
Transcription Supported Languages
100
Unlimited Notes & Meetings