Conversation Analysis
Key Insights ExtractionStructured DataSentiment Analysis
Dynamic Data Substitution
Emotion Tags
normalslowcryingsleepysighchuckle
Empathetic Conversation Handling
Enterprise-ready Phone Agents
Guided Emotion and Intonation
Input Streaming for Lower Latency
Knowledge Base Integration
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)
Post-call Automation
CRM ToolsEmailsOther Tasks
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
Training Data Volume
100k+ hours of speech, billions of text tokens
Workflow Triggers
CRMAPIScheduled Campaigns