Conversational Speech Generation
Dataset Size
1 million hours
Global Distribution Focus
Human-in-the-Loop Labeling
Intro/Outro Music Support
Model Sizes
Tiny: 1B backbone, 100M decoderSmall: 3B backbone, 250M decoderMedium: 8B backbone, 300M decoder
Multilingual Content Translation
Multiple Speaker Handling
Number of Hosts per Episode
4
Objective Metrics
Word Error RateSpeaker SimilarityHomograph DisambiguationPronunciation Consistency
Partial Multilingual Support Planned
Planned for 20+ languages
Subjective Metrics
Comparative Mean Opinion Score
Supported Language List
EnglishSpanishFrenchHindiPortugueseChineseGermanJapaneseArabicRussianKoreanIndonesianItalianDutchTurkishPolishSwedishFilipinoMalayRomanianUkrainianGreekCzechDanishFinnishBulgarianCroatianSlovakTamil
Supported Source Quantity
70+
Supported Source Types
WebsitesBlogsPDFsPowerPointsOther FilesSpreadsheetsYouTube Videos
User Content Ownership
Users own the content they create