use cases · intermediate · 20 minutes
Audio Processing & Transcription
A guide to extracting, transcribing, and searching audio from video files using OpenAI Whisper and Pixeltable.
Topics Covered
audiotranscriptionwhisperspeech to-text
Notebook Preview
Open fullscreenRelated notebooks
- RAG Demo: Build a Complete RAG System
Modality: Document
Computed column: Chunk, embed, and similarity search
Docs - Object Detection in Videos with YOLOX
Modality: Video
Computed column: frame_iterator view plus a detection column
Docs - 10-Minute Tour: Pixeltable Basics
Modality: Table
Computed column: Computed columns on a first table
Docs
Related Articles
Try This Notebook Now
Run this notebook in Google Colab with zero setup. All code is ready to execute.