Conversational Speech Generation
Dataset Size
1 million hours
Faster Reading
3x faster than reading
Handles Accents and Dialects
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
Premium Voices (Enterprise)
Over 200 human-quality voices
Subjective Metrics
Comparative Mean Opinion Score
Upload Content
ArticlesPDFsCamera ScansEbooksAudiobooksTextbooksDocumentsEmails