القائمة
Transcribe user-sent voice messages via local OpenAI Whisper (no API key, runs offline)
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
Generate character-consistent selfie images and videos, send via the active Nako messaging channel. Character reference image and description come from per-agent env.
Resolve Feishu image_key to a local file path so the agent can Read the image natively
Send voice/song audio through the active Nako messaging channel — voice.sh does plain TTS (MiniMax or Volcengine); sing.sh generates a full song with melody via MiniMax music-2.6
Control interactive BLE devices (scan/connect/playback/timeline) from terminal.
استنادا إلى تصنيف SOC المهني
| name | hearing |
| description | Transcribe user-sent voice messages via local OpenAI Whisper (no API key, runs offline) |
| allowed-tools | Bash(*/stt.sh:*) Bash(ls:*) |
用户发语音时，当前消息 runtime 会把 opus/m4a 等音频下到入站媒体目录。Hermes 默认是 ~/.hermes/media/inbound/；OpenClaw 默认是 ~/.openclaw/media/inbound/。本技能用本地 Whisper 把它转写成文字。无需 API key。
[Audio] / <media:audio> 占位符file_key 且上下文是语音（飞书语音消息）不要用于：普通文字对话、视频（视频有单独流程）。
# A. 根据 file_key 查 gateway.log 找文件并转写
bash "${NAKO_SKILLS_DIR:-$HOME/.openclaw/skills}/hearing/scripts/stt.sh" <file_key>
# B. 取最新一条入站音频（最常用）
bash "${NAKO_SKILLS_DIR:-$HOME/.openclaw/skills}/hearing/scripts/stt.sh" --latest
# C. 直接传绝对路径
bash "${NAKO_SKILLS_DIR:-$HOME/.openclaw/skills}/hearing/scripts/stt.sh" /path/to/media/inbound/xxx.opus
脚本把转写文本输出到 stdout，你把文本作为用户说的话理解即可。
| 变量 | 默认 | 说明 |
|---|---|---|
WHISPER_BIN | /opt/homebrew/bin/whisper | whisper CLI |
WHISPER_MODEL | turbo | tiny/base/small/medium/large-v3/turbo |
WHISPER_LANGUAGE | auto | zh/en/... 强制指定可加速并降低错识 |
turbo 模型对中英文已够用，速度最快| code | 含义 |
|---|---|
| 0 | 成功，stdout 为转写文本 |
| 2 | 找不到音频（日志被截断/还没下完/参数错） |
| 3 | 路径存在但文件已清理 |
| 4 | Whisper 运行失败 |