https://github.com/shjala/syncscribe
Audio transcription with interactive HTML viewer featuring real-time word highlighting and translations
https://github.com/shjala/syncscribe
audio-visualization interactive language-learning python speech-to-text synchronized transcription whisper word-highlighting
Last synced: about 1 month ago
JSON representation
Audio transcription with interactive HTML viewer featuring real-time word highlighting and translations
- Host: GitHub
- URL: https://github.com/shjala/syncscribe
- Owner: shjala
- Created: 2025-09-24T12:15:03.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2025-09-25T15:42:41.000Z (9 months ago)
- Last Synced: 2025-10-02T09:57:35.697Z (9 months ago)
- Topics: audio-visualization, interactive, language-learning, python, speech-to-text, synchronized, transcription, whisper, word-highlighting
- Language: HTML
- Homepage:
- Size: 28.7 MB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# SyncScribe 🎙️
SyncScribe takes an audio file and generates a standalone HTML viewer with embedded audio and synchronized transcription. Words are highlighted as they're spoken, and hovering over any word provides instant English translation. The generated file is fully self-contained and works completely offline, requiring no internet connection.
It uses local OpenAI's Whisper models via faster-whisper, if GPU-acceleration is available, it will be used. Checkout [sample page](https://defense.sh/syncscribe/sample-audio/sample_viewer.html) for a demonstration.
## Quick Start
### Generate Interactive Transcription Viewer
```bash
# Basic usage
./create_audio_viewer.sh your_audio.wav
# With custom model
./create_audio_viewer.sh --model medium
```
**Output:** Standalone HTML file in `out/` folder (or specified directory)
## Requirements
- **Python 3.8+**
- **NVIDIA GPU** (recommended) with CUDA support
## Installation
No manual installation needed, the scripts automatically:
1. Create Python virtual environment
2. Install all dependencies (faster-whisper, torch, librosa, etc.)
3. Configure GPU/CUDA settings
4. Download Whisper models to local cache
```bash
# Just clone and run
git clone
cd syncscribe
./create_audio_viewer.sh your_audio.wav
```
Everything is created and downloaded in the current directory for easy cleanup.