Batch Normalization in Model
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)
Pretrained and Finetuned Models
Pretrained modelsFinetuned models
Sample Finetuning Scripts
Sliding Window Detokenizer
Speech to Speech Translation
Speech-to-Speech & Style Transfer
Streaming Inference Speed
Faster than playback on A100 40GB for 3B model
Supports 50+ Languages & Accents
50
Training Data Volume
100k+ hours of speech, billions of text tokens
Ultra-Low Latency Neural Voice Model
Ultra-Realistic Emotion Synthesis
Use Cases: Movies, Documentaries, Content Creation
Movies DubbingDocumentaryContent Creator
Voice Customization Options