It provides API to store and transcribe audio files. OpenAI model is used to transcript audio.
Tip
To start:
- add OpenAI token to env variables
export OPENAI_API_KEY=your-toke-here- build and start containers
docker-compose up --buildTip
Save and transcribe audio:
curl http://localhost:8080/audio -F file=@your_audio_file_pathTip
Get transcript by audio id:
curl http://localhost:8080/transcript/{audio-id-here}