Automatic Audio-Supercuts with Python

Sam Lavigne hat sein Videogrep-Script aufgebohrt: „Audiogrep is a python script that transcribes audio files and then creates audio 'supercuts' based on search phrases. It uses CMU Pocketsphinx for speech-to-text, and pydub to splice audio segments together.“

Hier zum Beispiel alle Ansagen zu „Private Wealth“ in der Audiobook-Version von Thomas Pikettys Capital in the Twenty-first Century: