AI Promo Creation Time
less than 15 seconds
Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Input Streaming for Lower Latency
Jingle Generation Time
10 seconds
LLM-based Customizability
Model Tokenizer Type
Non-streaming (CNN-based) tokenizer
Multiple Jingles Per Voiceover
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
Sound Effects Library
750
Streaming Inference Speed
Faster than playback on A100 40GB for 3B model
Training Data Volume
100k+ hours of speech, billions of text tokens