Overview
Build a TypeScript app that transcribes audio and video files using OpenAI Whisper and Howler.js. Learn how to set up your environment, process media from sources like Google Drive or LinkedIn, integrate transcription APIs, and convert speech into accurate, structured text.
Syllabus
- Course 1: Getting Started with OpenAI Whisper API in TypeScript
- Course 2: Processing and Transcribing Audio with Howler.js
- Course 3: Scraping and Transcribing Remote Videos
- Course 4: Real-Time Audio Transcription with Web Audio API
Courses
-
Learn how to build a video transcription system using TypeScript and OpenAI's GPT-4o Transcription API. This course covers environment setup, audio playback with Howler.js, video scraping, and generating video summaries.
-
This unit builds a backend-controlled audio player using Howler.js for playback. The backend transcribes a segment of the selected audio file based on when the user starts and stops playback.
-
Learn how to fetch and process videos from remote sources like Google Drive or LinkedIn. This course walks you through downloading, extracting audio, and generating accurate transcriptions and summaries using the Whisper API.
-
Discover how to build real-time browser-based transcription tools with the Web Audio API and Whisper. You’ll capture microphone input, process it in chunks, and use Whisper’s advanced features for segment timing, contextual cues, and multilingual transcription.