← back to notebook
StudySlice screenshot
— · MLOPS

StudySlice

StudySlice cuts hours of lecture recordings down to the moments that actually matter. AWS Transcribe converts the audio to text, AWS Bedrock analyzes the transcript to separate real concept explanations from filler, and CLIP-based visual matching pairs each identified concept with the right video frame — all orchestrated through a FastAPI pipeline built around a system-design-first, ingestion/analysis/clip-generation architecture.

Stack
PythonFastAPICLIPAWS BedrockAWS TranscribeAWS S3Next.jsTypeScript
Highlights
  • AWS Bedrock analyzes lecture transcripts to flag high-value concept segments versus filler content
  • CLIP-based visual matching pairs identified concepts with the correct video frames
  • System-design-first architecture separates ingestion, analysis, and clip-generation into independently scalable stages