Automatic Language Detection
Conversation Intelligence Analytics
Speaker Talk-timeAI FiltersSentiment AnalysisTopic Trackers
Download Meeting Assets
SummaryTranscriptMeeting AudioVideo
Emotion Tags
normalslowcryingsleepysighchuckle
Enterprise Security Certifications
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
Real-Time Speech Transcription
Sample Finetuning Scripts
Sliding Window Detokenizer
Smart Transcription Accuracy
95%
Streaming Inference Speed
Faster than playback on A100 40GB for 3B model
Summary Output Formats
OverviewBullet PointsAction ItemsCustom Notes
Task, Contact, Knowledge Management
Training Data Volume
100k+ hours of speech, billions of text tokens
Use Case Templates
SalesRecruitingMarketingUser ResearchEngineeringFinanceHealthcareMedia & PodcastingVenture Capital
Zero Data Retention Policy