A REST API service that transcribes Hebrew audio from YouTube videos using Whisper AI.
- Clone this repository
- Install dependencies:
pip install -r requirements.txt- Create a
.envfile with your API key:
REPLICATE_API_KEY=your_replicate_api_key
Request:
{
"url": "https://www.youtube.com/watch?v=your_video_id"
}Response:
{
"status": "success",
"title": "Video Title",
"transcript": "Hebrew transcript with RTL formatting"
}- Create a new Web Service
- Connect your repository
- Set environment variables:
REPLICATE_API_KEY: Your Replicate API key
- Set build command:
pip install -r requirements.txt - Set start command:
gunicorn main:app
- Create a new Custom App in Make.com
- Set Base URL to your Render.com deployment URL
- Create a new module:
- Method: POST
- Endpoint: /api/transcribe
- Request Body:
{"url": "{{youtube_url}}"}