Fact · Speech recognition
Unlike openai-whisper, faster-whisper does not need FFmpeg installed on the system, because it decodes audio with PyAV, which bundles the FFmpeg libraries.
Checked against its source on October 17, 2026
In the source's own words
“Unlike openai-whisper, FFmpeg does **not** need to be installed on the system.”
faster-whisper: README (GitHub, SYSTRAN), SYSTRAN, GitHub (SYSTRAN/faster-whisper), 2026, Requirements.
Open the original- What it measures
- The README says audio is decoded with the Python library PyAV, which bundles the FFmpeg libraries in its package.
- What it does not show
- This removes the separate ffmpeg step only for faster-whisper. The openai-whisper package still needs the ffmpeg command-line tool.