How do I install the Whisper Cpp skill?

Run npx skillmds@latest add dvcrn/whisper-cpp in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Whisper Cpp safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Whisper Cpp?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Whisper Cpp free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Whisper Cpp?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Whisper Cpp by dvcrn — Agent Skill

Name: Whisper Cpp
Rating: 4.666666666666667 (3 reviews)
Author: dvcrn

Whisper Cpp

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.

dvcrn Updated Sep 8, 2026 32 repo stars

File contents

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.sh

Send 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, medium
large-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 small

For 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/audio

Models are stored in: ~/.cache/whisper.

Cleanup (optional)

After install (whisper-cli + libs are in ~/.local/):

bash scripts/cleanup_build.sh

Troubleshooting

Confirm OpenClaw is using the wrapper:

which openclaw-whisper-stt
openclaw config get tools.media.audio.models

Test the wrapper directly:

openclaw-whisper-stt /path/to/audio.ogg
OPENCLAW_WHISPER_MODEL=small openclaw-whisper-stt /path/to/audio.ogg

Follow gateway logs while sending a Telegram voice note:

openclaw logs --follow

Files

Wrapper source: bin/openclaw-whisper-stt.sh (linked to ~/.local/bin/openclaw-whisper-stt)
OpenClaw config patcher: scripts/patch_openclaw_audio.sh

---name: whisper-cppdescription: 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.## DependenciesYou need build tools (`git`, `cmake`, compiler toolchain) + `curl` and `ffmpeg` (to decode Telegram OGG/Opus → WAV).## InstallFrom this skill directory:```bashbash scripts/install_whisper_cpp.shbash scripts/download_models.shbash scripts/install_wrapper.shbash scripts/patch_openclaw_audio.sh```Send a Telegram voice note to test.## Tuning### Model choiceThis setup uses **ggml Whisper models** stored in `~/.cache/whisper`.Common model names you can download:- `tiny`, `base`, `small`, `medium`- `large-v1`, `large-v2`, `large-v3` (bigger/slower, usually more accurate)By default we download: `base` + `small`.To download specific models:```bashbash scripts/download_models.sh tiny base small```For the OpenClaw wrapper, you can select:```bashOPENCLAW_WHISPER_MODEL=small openclaw-whisper-stt /path/to/audio```- Default language: auto-detect (`OPENCLAW_WHISPER_LANG=auto`)- Force a language (example): ```bash OPENCLAW_WHISPER_LANG=en openclaw-whisper-stt /path/to/audio ```Models are stored in: `~/.cache/whisper`.## Cleanup (optional)After install (whisper-cli + libs are in `~/.local/`):```bashbash scripts/cleanup_build.sh```## TroubleshootingConfirm OpenClaw is using the wrapper:```bashwhich openclaw-whisper-sttopenclaw config get tools.media.audio.models```Test the wrapper directly:```bashopenclaw-whisper-stt /path/to/audio.oggOPENCLAW_WHISPER_MODEL=small openclaw-whisper-stt /path/to/audio.ogg```Follow gateway logs while sending a Telegram voice note:```bashopenclaw logs --follow```## Files- Wrapper source: `bin/openclaw-whisper-stt.sh` (linked to `~/.local/bin/openclaw-whisper-stt`)- OpenClaw config patcher: `scripts/patch_openclaw_audio.sh`

Frequently asked questions