Commercial Rights Ownership
Conversational Speech Generation
Dataset Size
1 million hours
Emotional Expression Support
30
Industry Use Cases
PodcastsYouTubeAudiobooksE-learningAdvertisementsCorporate TrainingMarketingSocial Media
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
Royalty-Free Image Generation
Subjective Metrics
Comparative Mean Opinion Score
Supported Countries
United StatesUnited KingdomChinaIndiaSpainMexicoNigeriaEthiopiaPhilippinesUnited Arab EmiratesEgyptPakistanPortugalBrazilBangladeshRussian FederationJapanGermanyIndonesiaKorea, Republic ofVietnamFranceCanadaItalyTurkeyAfghanistanPolandUkraineMyanmarThailand
Supported Language List
100
Video and Audio Synchronization
Voice Generation Hours Tracking