Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Input Streaming for Lower Latency
LLM-based Customizability
Max Audio Duration
10 hours
Max Monthly Characters
7000000000
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
Production Ready Infrastructure
Sample Finetuning Scripts
Sliding Window Detokenizer
Streaming Inference Speed
Faster than playback on A100 40GB for 3B model
Supported Bitrates
320k256k192k128k96k64k48k32k16k
Supported Language List
US EnglishUK EnglishMandarin ChineseHindiSpanishPortugueseJapaneseFrenchItalian
Text-to-Speech API
/stream/speech/synthesisTasks/streamWithTimestamps
Training Data Volume
100k+ hours of speech, billions of text tokens