Conversational Speech Generation
Dataset Size
1 million hours
Infinite Sound Variations
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
Priority Feature Requests
Priority Support
Creator/Pro: Priority, Starter: Priority email, Basic: Basic community support
Royalty-Free Sound Effects
Subjective Metrics
Comparative Mean Opinion Score
Supported Use Cases
MoviesSongsVideosPodcastsGamesAppsSocial mediaAds