- name
- whisper-cpp
- description
- Install and use whisper.cpp (local, free/offline speech-to-text) with OpenClaw. Supports downloading different ggml model sizes (tiny/base/small/medium/large-*) and configuring tools.media.audio to transcribe inbound voice notes without paid provider APIs.
whisper-cpp (Local Whisper STT for OpenClaw)
This skill sets up local whisper.cpp STT for inbound Telegram voice notes.
Dependencies
You need build tools (git, cmake, compiler toolchain) + curl and ffmpeg (to decode Telegram OGG/Opus → WAV).
Install
From this skill directory:
bash scripts/install_whisper_cpp.sh
bash scripts/download_models.sh
bash scripts/install_wrapper.sh
bash scripts/patch_openclaw_audio.shSend a Telegram voice note to test.
Tuning
Model choice
This setup uses ggml Whisper models stored in ~/.cache/whisper.
Common model names you can download:
tiny,base,small,mediumlarge-v1,large-v2,large-v3(bigger/slower, usually more accurate)
By default we download: base + small.
To download specific models:
bash scripts/download_models.sh tiny base smallFor the OpenClaw wrapper, you can select:
OPENCLAW_WHISPER_MODEL=small openclaw-whisper-stt /path/to/audio- Default language: auto-detect (
OPENCLAW_WHISPER_LANG=auto) - Force a language (example):
OPENCLAW_WHISPER_LANG=en openclaw-whisper-stt /path/to/audioModels are stored in: ~/.cache/whisper.
Cleanup (optional)
After install (whisper-cli + libs are in ~/.local/):
bash scripts/cleanup_build.shTroubleshooting
Confirm OpenClaw is using the wrapper:
which openclaw-whisper-stt
openclaw config get tools.media.audio.modelsTest the wrapper directly:
openclaw-whisper-stt /path/to/audio.ogg
OPENCLAW_WHISPER_MODEL=small openclaw-whisper-stt /path/to/audio.oggFollow gateway logs while sending a Telegram voice note:
openclaw logs --followFiles
- Wrapper source:
bin/openclaw-whisper-stt.sh(linked to~/.local/bin/openclaw-whisper-stt) - OpenClaw config patcher:
scripts/patch_openclaw_audio.sh