Compliance Support
Code of Conduct auditsCommunity policy guidanceUser report correlationTransparency reporting (EU AI Act, DSA)Userbase risk assessmentsCOPPA compliancePCI-DSS complianceInternal risk assessmentsSecurity posture review
Cost Reduction at Scale
Up to 100x
Customizable Prioritization
Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Input Streaming for Lower Latency
LLM-based Customizability
Model Tokenizer Type
Non-streaming (CNN-based) tokenizer
Multilingual Support
18+ languages
Open Source Release Planned
Orpheus Speech Models
Medium (3B)Small (1B)Tiny (400M)Nano (150M)
Pretrained and Finetuned Models
Pretrained modelsFinetuned models
Proactive Threat Detection
Real-Time Voice Moderation
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