據 AlphaMoat 統計,截至 2026-09,Local Whisper 累計下載 4,425 次、獲 0 個星標,在全部 5,078 個 AI 技能中排名第 2,199 位,在「設計創意」分類(512 個)中排名第 215 位。

累計安裝

200

累計下載

4425

星標

全站排名

#2,199

全站前 44% · 「設計創意」前 42%

平台	累計安裝	累計下載	星標	評論
ClawHub ↗	34	1280	-	-
SkillHub ↗	200	4425	-	—

各平台的計數口徑不同,統計時間不一致。

這個技能是做什麼的

主文介紹將 Telegram 語音訊息轉寫為文字，使用本地 whisper.cpp 模型，並說明所需構建工具、音訊解碼依賴與模型選擇。

資料釋出於 2026-10-27

可以用來做什麼

在本地轉寫收到的 Telegram 語音訊息

什麼時候用

需要在本地處理語音而不呼叫付費語音服務時

示例提示詞

以下是根據技能文件生成的示例,不代表實際執行結果。

為這條收到的 Telegram 語音訊息生成文字稿

月度資料趨勢

累計下載4425

星標-

2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。

月份	累計下載	環比	星標
2026-09	4425	—	-
2026-08	3057	+45.6%	-
2026-07	2100	+33.8%	-
2026-06	1569	+16.7%	-
2026-05	1344	—	-
2026-03	734	—	-

SKILL.md 原文

以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。

2.1 KB · ClawHub v1.0.2

---
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

展開全部(共 93 行)


You need build tools (`git`, `cmake`, compiler toolchain) + `curl` and `ffmpeg` (to decode Telegram OGG/Opus → WAV).

## Install

From this skill directory:

```bash
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
bash scripts/download_models.sh tiny base small
```

For the OpenClaw wrapper, you can select:

```bash
OPENCLAW_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/`):

```bash
bash scripts/cleanup_build.sh
```

## Troubleshooting

Confirm OpenClaw is using the wrapper:

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

Test the wrapper directly:

```bash
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:

```bash
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`