Learn how to transcribe and translate video or audio files for free by running Whisper locally on your computer. You will create a local terminal-based transcription setup that avoids uploading files to third-party transcription sites. After about 5 minutes of initial setup, a gigabyte-sized, seven-minute video can take about two minutes to transcribe on a MacBook Pro.
published mar 2, 2026
Transcribe Any Video for Free with This Local AI
intermediateThe Rundown
Who This Is Useful For
- Video or podcast editors
- Privacy-conscious meeting recorders
- Anyone with hours of content to transcribe or translate
What You Will Build
You will build a local transcription setup that lets you transcribe any video or audio file with a single terminal command. You will also be able to translate non-English audio into English automatically.
- A reusable local Whisper install
- A one-command workflow for transcribing files
- Transcript and caption outputs such as .txt and .srt files
- An optional translation workflow for non-English audio
What You Need
- A Mac or Windows computer
- Python 3
- Homebrew on Mac or Chocolatey on Windows for installing ffmpeg
- A video or audio file you want to transcribe
- About 5 minutes for the initial setup
Going Further
- After transcribing a file, you can reuse the outputs as plain text transcripts, closed captions, or editor-ready subtitle files. You can also control the output folder and format, or batch process a folder of recordings to create transcripts for every file.
If pip3 is not recognized, try python3 -m pip install -U openai-whisper instead.