This is a submission for the AssemblyAI Challenge : Sophisticated Speech-to-Text.
What I Built
An Application that allow from an Audio concerning a discussion, a meeting, etc ... to generate a "meaningful mind-map diagram", that represent the touched key points. This representation joined with summary provide a more complete and understandable informations
Demo
The application in available here for access to full functionality you need both an AssemblyAI Api Key and a OpenAI Api Key. Below there are some representative screenshots
Settings
Upload Audio
Transcribe Audio
Generate Mindmap Diagram
Journey
To implement process from audio to diagram I have developed several "skilled agents" described below:
transcribe-from-audio: this agent use AssemblyAI transcripts API to transcribe the provided audio.
keypoints-from-transcript: this Agent use OpenAI (got-4o-mini) to extract the Keypoints inside the given transcription
summary-to-mindmap: this agent use OpenAI (got-4o-mini) to arrange the key points in a kind of ontology providing a hierarchical representation of information
mindmap-to-mermaid: last agent transform the mind-map representation in a mermaid syntax ready for the visualization
Diagram of Agentic Architecture
I can think of several long-winded, recorded meetings in which key ideas presented in a schema like this would be highly beneficial. Nice job