Transcribe audio

whisper.cpp

Open-source C/C++ port of OpenAI Whisper that transcribes audio to text locally, from a CLI or an HTTP server.

Rate limits

Rate limits: No account: runs on your machine; the server defines no rate limit option3

Other limits

Memory use: base model: 142 MiB on disk, about 388 MB in memory; large: 2.9 GiB on disk, about 3.9 GB1
Threads: 4 by default (-t N)3
Input format: whisper-cli runs only with 16-bit WAV files unless built with FFmpeg support1
Latest release: v1.9.5, published 2026-10-069

Read from ggml-org’s own pages on 2026-11-04. Every number links to the page a value came from. For agents, the same facts as markdown: /tools/transcribe-audio/whisper-cpp.md