Data Insights (Coming Soon)
Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Industry Customization
HVACPlumbingElectricalCleaningSolarRoofingGarage Door
Industry-Specific Training
Input Streaming for Lower Latency
LLM-based Customizability
Model Tokenizer Type
Non-streaming (CNN-based) tokenizer
Multiple Voice Selection
American AccentSpanish Accent
Open Source Release Planned
Orpheus Speech Models
Medium (3B)Small (1B)Tiny (400M)Nano (150M)
Polished Branded Experience
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
Summaries and Transcriptions
Training Data Volume
100k+ hours of speech, billions of text tokens