Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Input Streaming for Lower Latency
LLM-based Customizability
Minimum Clone Audio Length
3
Model Tokenizer Type
Non-streaming (CNN-based) tokenizer
Open Source Release Planned
Orpheus Speech Models
Medium (3B)Small (1B)Tiny (400M)Nano (150M)
Planned Language Expansion
Pretrained and Finetuned Models
Pretrained modelsFinetuned models
Recommended Clone Audio Length
3-10 seconds
Sample Finetuning Scripts
Sliding Window Detokenizer
Streaming Inference Speed
Faster than playback on A100 40GB for 3B model
Support Contact Email
support@aivoicecloning.io
Supported Language List
EnglishMandarinJapaneseKorean
Training Data Volume
100k+ hours of speech, billions of text tokens