Custom Keyboard Shortcuts
Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Input Streaming for Lower Latency
LLM-based Customizability
Manual Re-transcribe Option
Model Tokenizer Type
Non-streaming (CNN-based) tokenizer
Multilingual Support
EnglishChineseSpanishGermanFrenchJapaneseKoreanRussianArabicHindiPortugueseItalianDutchTurkishIndonesianVietnameseThaiCzechPolishUkrainianSwedish
No Recording Length Limit
Open Source Release Planned
Orpheus Speech Models
Medium (3B)Small (1B)Tiny (400M)Nano (150M)
Pretrained and Finetuned Models
Pretrained modelsFinetuned models
Sample Finetuning Scripts
Sliding Window Detokenizer
Streaming Inference Speed
Faster than playback on A100 40GB for 3B model
Training Data Volume
100k+ hours of speech, billions of text tokens
Whisper Large V3 Turbo Model
Whisper Large V3 Turbo