Celebrity Types
ActorsAthletesMusiciansCrypto PersonalitiesCartoon CharactersRoyalty
Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Input Streaming for Lower Latency
LLM-based Customizability
Model Tokenizer Type
Non-streaming (CNN-based) tokenizer
Number of Messages Generated
1000000
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
Supported Message Types
Custom messages spoken by celebrity voices
Supported Personalities
Morgan FreemanSpongeBobBen PasternakImran KhanThread GuyAnatoly YakovenkoAnsemVirat KohliDavid GogginsJustine MoorePatrickQueen Elizabeth IIIce SpiceDrakeOrangieMurad
Training Data Volume
100k+ hours of speech, billions of text tokens