Character Limit Expandable
Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Industry Use Cases
YouTubePodcastAudiobooksE-learningRadioCorporate training
Input Streaming for Lower Latency
LLM-based Customizability
Longer Audio Files Limit
12000
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
Streaming Inference Speed
Faster than playback on A100 40GB for 3B model
Supported Language List
140
Training Data Volume
100k+ hours of speech, billions of text tokens
Voice Inflections Control