Scribe’s models are trained on hundreds of hours of financial conversations to achieve greater accuracy for financial English other engines.
Scribe automatically detects speaker transitions in audio files, improving accuracy and creating a logical, timestamped transcript.
Scribe uses proprietary decoding techniques to transcribe audio 10x faster, enabling transcription of hour long audio in minutes allowing fast turnaround.
Scribe uses proprietary natural language processing libraries called Asset Class Interpreters to extract quote & trade data from a conversation.
Scribe’s Historical Transcription engine creates time-stamped, searchable, speaker separated transcripts from audio files. GreenKey’s engine can be used via our public API or in an on-premise environment through our Docker container image. You can even dial Scribe into your phone calls and automatically receive transcriptions to your email account.
Scribe’s TradeTicket engine listens to audio streams in real-time and uses our Asset Class Interpreters to extract quote or trade metadata to populate a ticket or capture for general compliance purposes or more specifically for MiFID II compliance. GreenKey’s engine can be used via our TradeTicket application or through our websocket API, with audio streaming from a computer microphone or turret.
GreenKey’s Insight engine allows us to focus on keywords set by your organization and display them if thy are used in any conversation.
The word cloud will provide a visual representation of what is spoken, where the size of the word represents the occurrence rate.
Additionally, GreenKey’s sentiment chart gives a visual representation of the mood of the conversation, and allows the user to click on a section of the graph to see the point in the conversation where the mood was positive or negative.