Official documentation
whisper.cpp stream example README
ggml-org, GitHub (ggml-org/whisper.cpp), n.d.
Read the originalRead on October 17, 2026
- What it is
- The README of the streaming example in whisper.cpp, which transcribes live microphone audio. It explains the sliding-window mode and the voice activity setting that decides when a chunk is transcribed.
- How much weight it carries
- Official project README, so it is authoritative for how the example works. It describes a sample program, not a finished dictation app, and the command-line flags may change between releases.
Facts taken from this source
- The whisper.cpp stream example samples the microphone audio every half a second and runs the transcription continuously.
“The `whisper-stream` tool samples the audio every half a second and runs the transcription continuously.” (Opening paragraph)
- 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.
“Setting the `--step` argument to `0` enables the sliding window mode” (Sliding window mode with VAD)