1:1 Consultation Hours
2 hours/month
Advanced Prompt Engineering
Brand Guideline & Governance Consulting
Concurrent Inbound Calls Limit
Concurrent Outbound Calls Limit
Custom Automation Development
Automatic SMSEmailVoicemailSummary GenerationQuote Creation
Custom Development & Integrations
Emotion Tags
normalslowcryingsleepysighchuckle
Employee Types
ReceptionistsSpeed-to-LeadMass Outbound Calling
Form Collection & Summaries
Guided Emotion and Intonation
Human-like Voice
Hyper human-like
Implementation Speed
48 hours
Industry Use Cases
SalesCustomer serviceAppointment settingLead qualification
Input Streaming for Lower Latency
Lead Contact Speed
< 1 minute
LLM-based Customizability
Maximum Calls Per Day
10,000+
Maximum Calls Per Minute
1500+
Model Tokenizer Type
Non-streaming (CNN-based) tokenizer
Objection Handling Optimization
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
Simple Intuitive Interface
Sliding Window Detokenizer
Streaming Inference Speed
Faster than playback on A100 40GB for 3B model
Support Question Handling Optimization
Training Data Volume
100k+ hours of speech, billions of text tokens
Ultra Low Latency
Sub-1500ms
Voice Customization Options
Extensive tone & speed control
Weekly Group Support Calls
2 per week