Turn audio into transcripts on your own computer.
Turns audio and video recordings into local transcripts, subtitles, and speaker-labeled text using faster-whisper.
When to use it
Use for transcribing recordings, generating subtitles, identifying speakers, or translating speech into English.
Give it recordings or an audio URL; it returns transcript text, or saves requested subtitle and data formats to files.
What you provide
The shell setup requires Python 3.10 or later.
The shell setup exits if ffmpeg is missing, despite the documentation describing it as unnecessary for basic transcription.
This skill
HuggingFace
Downloads transcription models
audio URLs
Downloads audio from supplied URLs