diegoquinteiro / podcast-summarizer

podcast-summarizer

Summarizes a podcast from an audio or transcription using ChatGPT.

Instalation

pip install podcast-summarizer

Usage

# Summarize a podcast audio from an URL.
podcast-summarizer http://.../audio.mp3

# Summarize a podcast audio from an YouTube video.
podcast-summarizer https://www.youtube.com/watch?v=...

# Summarize a podcast audio from local file.
podcast-summarizer audio.mp3

# Summarize a podcast audio and save transcription and summary to files.
podcast-summarizer -t transcription.txt -s summary.txt audio.mp3

# Summarize an already transcribed podcast
podcast-summarizer transcription.txt

Setup

You'll need to install ffmpeg before running the script.

# on Ubuntu or Debian
sudo apt update && sudo apt install ffmpeg

# on Arch Linux
sudo pacman -S ffmpeg

# on MacOS using Homebrew (https://brew.sh/)
brew install ffmpeg

The script expects an environment variable called OPEN_API_KEY.

1. Get an OpenAI API Key
2. Add the key to your OPEN_API_KEY environment variable:

• If you use bash:

  echo 'export OPENAI_API_KEY={your api key}' >> ~/.bash_profile && source ~/.bash_profile

• If yu use zsh:

  echo 'export OPENAI_API_KEY={your api key}' >> ~/.zshenv && source ~/.zshenv

podcast-summarizer's Issues

Portuguese podcast transcribed to English

Steps to reproduce:

1. Get a youtube video in portuguese: https://www.youtube.com/watch?v=JJ7NQRcLvd8
2. Call podcast-summarizer as: podcast-summarizer https://www.youtube.com/watch?v=JJ7NQRcLvd8

Expected result:

1. yt-audio.txt generated in portuguese

Observed result:

1. yt-audio.txt generated in english