Fact · Speech recognition
In the whisper.cpp streaming example, setting the step argument to 0 switches the program to a sliding-window mode that transcribes after voice activity is detected.
Checked against its source on October 17, 2026
In the source's own words
“Setting the `--step` argument to `0` enables the sliding window mode”
whisper.cpp stream example README, ggml-org, GitHub (ggml-org/whisper.cpp), n.d., Sliding window mode with VAD.
Open the original- What it measures
- The example transcribes live microphone audio, and the README documents this mode as a second way to run it.
- What it does not show
- This is a sample program. The README warns that the output format depends on the step setting, and that the flags may change between releases.