AI Rewriter for Fast Speech
Conversational Speech Generation
Dataset Size
1 million hours
Languages Supported
GermanFrenchKoreanPortugueseSpanishTurkishJapanese
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
One-stop Shop for Localization
Partial Multilingual Support Planned
Planned for 20+ languages
Seamless Audio Integration
Self-Service and Expert Options
Source Language Flexibility
Subjective Metrics
Comparative Mean Opinion Score
Video Source Format Flexibility