# video-transcriber > Converts video files to MP3 and transcribes them using OpenAI Whisper. Use when the user wants to get text from a video, transcribe a meeting recording, or extract speech from a video file. - Author: Luis Ortiz - Repository: leoo1995/skills-master - Version: 20260125162143 - Stars: 0 - Forks: 0 - Last Updated: 2026-02-06 - Source: https://github.com/leoo1995/skills-master - Web: https://mule.run/skillshub/@@leoo1995/skills-master~video-transcriber:20260125162143 --- --- name: video-transcriber description: Converts video files to MP3 and transcribes them using OpenAI Whisper. Use when the user wants to get text from a video, transcribe a meeting recording, or extract speech from a video file. --- # Video Transcriber This skill converts video files (e.g., .mp4, .mov) into audio (.mp3) and then transcribes the audio into text using OpenAI's Whisper model via the API. ## Prerequisites 1. **FFmpeg**: Must be installed an accessible in the system PATH. - Check with: `ffmpeg -version` 2. **OpenAI API Key**: Must be set as an environment variable `OPENAI_API_KEY`. 3. **Python Dependencies**: Install using the provided requirements file. ## Setup Run the following command to install the necessary python package: ```bash pip install -r scripts/requirements.txt ``` ## Usage To transcribe a video file, run the `transcribe.py` script: ```bash python scripts/transcribe.py ``` ### Options - `-o, --output `: Specify the output text file path. default is `.txt`. - `-k, --keep-audio`: Keep the temporary `.mp3` file after transcription (it is deleted by default). ### Example ```bash # Transcribe a video and save to default.txt python scripts/transcribe.py my_presentation.mp4 # Transcribe and specify output file python scripts/transcribe.py meeting.mov -o minutes.txt ``` ## Troubleshooting - **ffmpeg not found**: Ensure FFmpeg is installed. On macOS, use `brew install ffmpeg`. - **API Key Error**: Ensure `export OPENAI_API_KEY=sk-...` is set in your terminal session or .zshrc.