How ombharatiya/transcript-ai works
TranscriptAI provides two transcription interfaces: a browser app with demo or OpenAI API mode, and a Python CLI using local Whisper. The CLI workflow accepts files and options, transcribes singly or in batches, then saves text and optional detailed JSON; the web workflow selects a file and settings, calls the chosen mode, presents results, and offers downloads. The README documents multilingual translation, model selection, and batch support. Evidence is limited to the README and sampled source excerpts, so unsampled subsystem links are omitted.
Main entry points: audio_transcriber.py Transcription engine · app.js Web interface
Components 13
Browser interface
- Web interface
web/src/app.js
CLI transcription
- CLI arguments
cli/src/audio_transcriber.py - Batch processing
cli/src/audio_transcriber.py - Audio inspection
cli/src/audio_transcriber.py - Transcription engine
cli/src/audio_transcriber.py
Results and export
- Text and JSON files
cli/src/audio_transcriber.py - Browser result view
web/src/app.js - Text download
web/src/app.js
Other components
- Browser user
- OpenAI transcription API
- CLI user
- Whisper model
- FFmpeg
Connections 12
- Browser user → Web interface: selects audio
README.md - Web interface → OpenAI transcription API: posts audio
web/src/app.js - Web interface → Browser result view: shows result
web/src/app.js - Browser result view → Text download: exports text
web/src/app.js - CLI user → CLI arguments: provides files
README.md - CLI arguments → Batch processing: dispatches batch
cli/src/audio_transcriber.py - CLI arguments → Audio inspection: requests details
cli/src/audio_transcriber.py - CLI arguments → Transcription engine: transcribes files
cli/src/audio_transcriber.py - Batch processing → Transcription engine: processes files
cli/src/audio_transcriber.py - Transcription engine → Whisper model: loads and runs
cli/src/audio_transcriber.py - Transcription engine → FFmpeg: checks availability
cli/src/audio_transcriber.py - Transcription engine → Text and JSON files: writes results
cli/src/audio_transcriber.py