Automated Business Processes
Business Case Integration
Video game humanoid voiceCall center communicationVirtual website communicationSmart home conversation
Cloud Computing Infrastructure
Cost Reduction for Coordination
Emotion and Tone Detection
Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Input Streaming for Lower Latency
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)
Pre-written Scenario Execution
Pretrained and Finetuned Models
Pretrained modelsFinetuned models
Sample Finetuning Scripts
Semantic Speech Recognition
Sliding Window Detokenizer
Streaming Inference Speed
Faster than playback on A100 40GB for 3B model
Tonality and Intonation in TTS
Training Data Volume
100k+ hours of speech, billions of text tokens