AI Music Generator From Text
Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Input Streaming for Lower Latency
LLM-based Customizability
Model Tokenizer Type
Non-streaming (CNN-based) tokenizer
Music Genre Coverage
EDMHouseDance PopCinematic ElectronicaSufi-ElectronicaGlobal FutureHip-HopR&BAfro-DrillRetro-FuturisticAnalog-DrivenAtmosphericPiano HouseDubstepBig RoomFolktronica
Open Source Release Planned
Orpheus Speech Models
Medium (3B)Small (1B)Tiny (400M)Nano (150M)
Prebuilt DNA Models
Piano HouseDubstepBig RoomEDMFolktronica
Pretrained and Finetuned Models
Pretrained modelsFinetuned models
Sample Finetuning Scripts
Signature DNA Styles
EDMHouseDance PopCinematic ElectronicaSufi-ElectronicaGlobal FutureHip-HopR&BAfro-DrillRetro-FuturisticAnalog-DrivenAtmospheric
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