Skip to main content

YouTube video transcription using OpenAI Whisper with a beautiful web interface

Project description

Whisper Scribe

YouTube video transcription using OpenAI Whisper with a beautiful web interface.

Features

  • Simple Web Interface - Clean, modern UI with real-time progress tracking
  • YouTube Support - Just paste any YouTube URL to transcribe
  • AI Analysis - Get summaries, key takeaways, and topic extraction
  • Translation - Translate transcriptions to 12+ languages
  • Multiple Export Formats - Download as TXT, SRT, or VTT subtitles
  • Batch Processing - Queue multiple videos for transcription
  • History - Browse and search your past transcriptions
  • Automatic Chunking - Handles long videos by splitting audio automatically

Installation

pip install whisper-scribe

Prerequisites

  • Python 3.9 or higher
  • FFmpeg (required for audio processing)
  • OpenAI API key

Installing FFmpeg

macOS:

brew install ffmpeg

Ubuntu/Debian:

sudo apt update && sudo apt install ffmpeg

Windows: Download from ffmpeg.org or use:

choco install ffmpeg

Quick Start

  1. Start the server:

    whisper-scribe
    
  2. Open your browser: The app will automatically open at http://localhost:8000

  3. Configure your API key: Click the Settings icon and enter your OpenAI API key

  4. Transcribe: Paste a YouTube URL and click Transcribe!

Command Line Options

whisper-scribe --help                 # Show all options
whisper-scribe --port 9000            # Use custom port
whisper-scribe --host 0.0.0.0         # Listen on all interfaces
whisper-scribe --no-browser           # Don't open browser automatically
whisper-scribe --reload               # Enable auto-reload (development)

Configuration

Settings are saved in ~/.whisper-scribe/config.json:

  • OpenAI API Key: Required for transcription and AI analysis
  • Output Directory: Where transcription files are saved (default: ~/.whisper-scribe/transcriptions/)

AI Features

Analysis

After transcription, click "Analyze with AI" to get:

  • Summary - A concise overview of the video content
  • Key Takeaways - The main points and insights
  • Topics - Main themes discussed in the video

Analysis responses are in the same language as the original video.

Translation

Translate your transcriptions to:

  • English, Spanish, French, German, Italian, Portuguese
  • Russian, Japanese, Chinese, Korean, Arabic, Hindi

API

Whisper Scribe exposes a REST API at /api:

  • POST /api/transcribe - Start a transcription job
  • GET /api/status/{job_id} - Check job status
  • GET /api/result/{job_id} - Get transcription result
  • POST /api/analyze/{item_id} - AI analysis
  • POST /api/translate/{item_id} - Translation
  • GET /api/history - List past transcriptions
  • GET /api/export/{item_id} - Export in various formats

License

MIT License - see LICENSE for details.

Author

Created by Issam Alameh

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

whisper_scribe-1.0.0.tar.gz (74.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

whisper_scribe-1.0.0-py3-none-any.whl (80.0 kB view details)

Uploaded Python 3

File details

Details for the file whisper_scribe-1.0.0.tar.gz.

File metadata

  • Download URL: whisper_scribe-1.0.0.tar.gz
  • Upload date:
  • Size: 74.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for whisper_scribe-1.0.0.tar.gz
Algorithm Hash digest
SHA256 d9851da7bd3bfa3cf654a668069a61ce2ffb55cf63ebbd4d1968f5023b711ca4
MD5 764c5c76e6d2b861de1840f1a08734be
BLAKE2b-256 d3f1696f9ab7b249441c69195c1578272ce69051187de0a22f5ca7e6eb3a8b35

See more details on using hashes here.

File details

Details for the file whisper_scribe-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: whisper_scribe-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 80.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for whisper_scribe-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5923468b2649965eadd34c395449eb5dd118cf2c4ab4197fbcb8737d6be01fc1
MD5 d1deefbffec35f149285345375e47586
BLAKE2b-256 98f3b3c5c627697729fb07ecbe0aa3e20ee082d433606739bfe719db2da57249

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page