Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Inbound and Outbound Calls
Inbound CallsOutbound Calls
Industry Templates
Real EstateHuman ResourcesRetailLegalSales TeamsServices/UtilitiesHospitalityEducationHealthcare
Input Streaming for Lower Latency
International Availability
LLM-based Customizability
Model Tokenizer Type
Non-streaming (CNN-based) tokenizer
Multilingual Support
EnglishSpanishFrenchTurkishPortuguese
Open Source Release Planned
Orpheus Speech Models
Medium (3B)Small (1B)Tiny (400M)Nano (150M)
Outbound Campaign Automation
Pretrained and Finetuned Models
Pretrained modelsFinetuned models
Role-Based Access Control
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