Call Transfer
Business lineSpecific personDepartmentTake messageSelf-service linkSchedule callback
Conditional Call Forwarding Support
Custom Agent Skills and Flows
Customizable Agent Behavior
Dedicated AI Phone Number
Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Human Review and Automated Checks
Input Streaming for Lower Latency
Lead Capture via Multiple Channels
LLM-based Customizability
Model Tokenizer Type
Non-streaming (CNN-based) tokenizer
No Engineering Dependencies
Open Source Release Planned
Operator Workflow for Escalation
Orpheus Speech Models
Medium (3B)Small (1B)Tiny (400M)Nano (150M)
Personalized Caller Greetings
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
Supports Both SMB and Enterprise
Training Data Volume
100k+ hours of speech, billions of text tokens