Conversational Speech Generation
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
Personalized Audio Creation
Select Ambient Sound or Music
Select Binaural Beats Frequency
Subjective Metrics
Comparative Mean Opinion Score
Supported Audio Types
SubliminalsAffirmationsAskfirmationsSelf-HypnosisSleep StoriesGuided MeditationPrayer