Advanced Speech Features
emotional inflectionrhythm controlmultilingual support
API Sample Rate Support
44100
Audio AI Features
end-to-end editingnoise cancellationAI-powered refinement
Comprehensive Documentation
Creative Suite Tools
PodcastingVideo AIAudio AIVoice AI
Emotion Tags
normalslowcryingsleepysighchuckle
Guided Emotion and Intonation
Infinite Voice Styles
Infinite
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)
Podcasting Features
audio enhancementnoise reductionvoice conversion
Pretrained and Finetuned Models
Pretrained modelsFinetuned models
Quick Implementation
<10 minutes
Sample Finetuning Scripts
Sliding Window Detokenizer
Streaming Inference Speed
Faster than playback on A100 40GB for 3B model
Supported Language List
20+
Supported Use Cases
Customer ServiceGame DevelopmentDigital MarketingDigital PublishingPatient CommunicationConversion OptimizationConversational AI / AgentsGlobal ReachDigital Humans / AI AvatarsSupply ChainTalent AcquisitionInclusive Design
Training Data Volume
100k+ hours of speech, billions of text tokens
Video AI Features
intelligent video editingautomatic captioningvisual enhancement
Voice AI Tools
text-to-speechvoice cloning
Voice Cloning Sample Duration
3
Voice Model Version
asyncFlow v1.0
Voice Output Emotional Styles