Elite Plan Templates
All Templates
Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Industry Leading Accuracy
Input Streaming for Lower Latency
LLM-based Customizability
Model Tokenizer Type
Non-streaming (CNN-based) tokenizer
Open Source Release Planned
Orpheus Speech Models
Medium (3B)Small (1B)Tiny (400M)Nano (150M)
Pretrained and Finetuned Models
Pretrained modelsFinetuned models
Real-Time Suggestions and Corrections
Sample Finetuning Scripts
Seamless Workflow Integration
Sliding Window Detokenizer
Starter Plan Templates
29
Streaming Inference Speed
Faster than playback on A100 40GB for 3B model
Team Seats Lower Plans
Included
Training Data Volume
100k+ hours of speech, billions of text tokens
Wide Voices Variation & Languages