
by Oumnya
07/09/2024
Deploy this template to create your own app and start your journey with CloudStation.

YTAutoMate is a Docker image that automates various aspects of YouTube video processing. It utilizes FFmpeg for video manipulation and Whisper AI for speech recognition.
Video upload to S3/Minio buckets
Audio analysis
SRT subtitle file generation
Video transcript creation
Editing assistance report generation
The tool processes videos uploaded to specified S3 or Minio buckets. It can run on both CPU and GPU, with GPU offering faster processing for compatible tasks.
FFmpeg: Video compression and manipulation
Whisper AI: Speech recognition and transcription
Python: Core processing logic and automation
YTAutoMate is designed to integrate with workflow management tools and can be incorporated into larger content creation pipelines.
YTAutoMate is a Docker version of VoiceScribe. It encapsulates all the functionalities of VoiceScribe in a containerized environment, making it easier to deploy and scale.
YTAutoMate exposes the following API endpoints:
GET /
Returns the index page (upload.html)
POST /check_api_key
Validates the provided API key
Request body: { "api_key": "your_api_key_here" }
POST /upload
Handles file uploads
Requires API key authentication in the Authorization header
Request body: multipart/form-data with 'file' field
POST /convert_and_transcribe
Initiates audio conversion and transcription
Requires API key authentication in the Authorization header
Request body: { "filename": "your_file.mp4" }
GET /job_status/<job_id>
Retrieves the status of a conversion job
Requires API key authentication in the Authorization header
GET /health
Health check endpoint