Fact · Speech recognition
The whisper.cpp command-line example runs only with 16-bit WAV files, so audio in other formats must be converted before transcription.
Checked against its source on October 16, 2026
In the source's own words
“currently runs only with 16-bit WAV files, so make sure to convert your input before running the tool.”
whisper.cpp README, Georgi Gerganov, GitHub, 2026, Usage (README).
Open the original- What it measures
- whisper.cpp is the C/C++ port of OpenAI's Whisper model that many Mac apps use. Its README gives ffmpeg as the example converter.
- What it does not show
- The README describes the command-line example, not every app built on whisper.cpp, which may convert audio for you.
Source
Cited on
- How to Transcribe Audio to TextGuide
- How to Run Whisper Locally on Your Own ComputerGuide
- Can you transcribe MP3, M4A, OGG and other audio files?Question
- How do you transcribe an audio file on Windows?Question
- How do you use Whisper for dictation on a Mac?Question
- Which audio formats and file sizes does Whisper accept?Question