首页 › 龙虾技能列表 › Voice Memo — 语音备忘录

🎙️ Voice Memo — 语音备忘录

v0.1.2

语音备忘录工具。

0· 416·0 当前·0 累计
by @amzzzzzzz·MIT-0
下载技能包
License
MIT-0
最后更新
2026/4/13
安全扫描
VirusTotal
可疑
查看报告
OpenClaw
安全
medium confidence
The skill's code and runtime instructions match its stated purpose (sending iMessage voice bubbles via ElevenLabs + BlueBubbles); the main concern is an authoring/metadata inconsistency and the usual need to trust local env/config values it reads.
评估建议
This skill appears to do what it claims: generate ElevenLabs TTS, convert to Opus CAF, and post to a BlueBubbles Private API to create native iMessage voice bubbles. Before installing: (1) verify the skill's source (homepage is a GitHub repo) and inspect ~/.openclaw/.env to ensure it only contains the expected ELEVENLABS_API_KEY and BLUEBUBBLES_PASSWORD; (2) ensure BLUEBUBBLES_URL points to a trusted local BlueBubbles instance (default is http://127.0.0.1:1234); (3) treat the ElevenLabs API key ...
详细分析 ▾
✓ 用途与能力
The script implements exactly what the skill describes: it calls ElevenLabs TTS, converts audio with afconvert to Opus CAF, and posts to a BlueBubbles Private API to produce native iMessage voice bubbles. Required binaries (curl, afconvert) and the two service credentials are appropriate for this functionality.
✓ 指令范围
SKILL.md and the script confine actions to generating audio, converting it, and sending it to the BlueBubbles endpoint. The script sources ~/.openclaw/.env for credentials and does not attempt to read unrelated system files or exfiltrate arbitrary data. It documents how transcriptions integrate into conversation context and notes that transcriptions are not auto-persisted.
✓ 安装机制
No install spec (instruction-only) and a small included shell script. No downloads, archive extraction, or third-party package installs — low install-time risk.
ℹ 凭证需求
The script requires ELEVENLABS_API_KEY and BLUEBUBBLES_PASSWORD (proportionate to the task). However, registry metadata at the top of the submission lists no required env vars while SKILL.md and the script do — an inconsistency. Also note the script blindly sources ~/.openclaw/.env, which may contain additional secrets; ensure that file contains only intended credentials and is protected.
✓ 持久化与权限
always:false and no system-wide configuration changes. The skill can be invoked autonomously (platform default), which is expected for skills; it does not request persistent elevated privileges or modify other skills' configs.
安全有层次，运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发，无需署名。

运行时依赖

无特殊依赖

版本

latestv0.1.22026/2/26

Version 0.1.2 of imessage-voice-memo-skill - No file changes detected in this release. - No functional, documentation, or metadata updates. - Behavior and usage remain unchanged from the previous version.

● 可疑

安装命令 点击复制

官方npx clawhub@latest install imessage-voice-memo-skill
镜像加速npx clawhub@latest install imessage-voice-memo-skill --registry https://cn.clawhub-mirror.com

技能文档

Send native iMessage voice bubbles (not file attachments) using ElevenLabs TTS and BlueBubbles.

Quick 开始

Run the script with text and recipient:

scripts/send-voice-memo.sh "Your message here" +14169060839

This will:

  • Generate TTS audio 通过 ElevenLabs (Rachel voice 由 默认)
  • Convert 到 Opus CAF @ 24kHz (iMessage native 格式)
  • 发送 作为 native voice bubble 通过 BlueBubbles

Requirements

  • BlueBubbles running locally 带有 私有 API 已启用
  • ElevenLabs API 键 (对于 TTS)
  • macOS (对于 afconvert audio conversion)
  • Environment variables 在...中 ~/.openclaw/.env:
  ELEVENLABS_API_KEY=your-key-here
  BLUEBUBBLES_PASSWORD=your-password-here
  # Optional overrides:
  ELEVENLABS_VOICE_ID=21m00Tcm4TlvDq8ikWAM  # Rachel (default)
  ELEVENLABS_MODEL_ID=eleven_turbo_v2_5      # Turbo v2.5 (default)

Working Formula

Critical parameters discovered 2026-02-19:

ParameterValueWhy
chatGuidany;-;+PHONENOT iMessage;-; (causes timeouts)
methodprivate-apiRequired for native bubble
isAudioMessagetrueRequired
Audio formatOpus @ 24kHz in CAFiMessage native format
Pre-convertYesDon't let BlueBubbles convert (wrong codec)

Voice Options

默认 voice: Rachel (ElevenLabs)

  • Voice ID: 21m00Tcm4TlvDq8ikWAM
  • 模型: eleven_turbo_v2_5 (fast, natural)
  • Cost: ~$0.04 per 30s 消息

Expressive tags:

  • [laughs] — natural laughter
  • [sighs] — expressive sigh
  • [excited] — energetic delivery

Example: "[excited] Oh my god, it worked!"

For full voice list and IDs, see VOICES.md.

Bidirectional Voice Memos

Sending (Amz → Amy): Use this skill. Native voice bubbles appear with waveform UI.

Receiving (Amy → Amz): BlueBubbles auto-converts incoming voice memos to MP3. OpenClaw transcribes via Whisper. Transcribed text flows into conversation context automatically.

Memory note: Incoming voice memo transcriptions flow 进入 conversation context 点赞 任何 text 消息. 它们 不 automatically persisted 到 memory 或 files — agent 必须 explicitly choose 到 store them, 相同 作为 任何 conversation content. 如果 您 want 到 prevent transcriptions 从 正在 retained, instruct agent 不 到 记录 voice memo content 在...中 memory.

Troubleshooting

Voice bubble arrives 作为 file attachment:

  • Check 方法=私有-api 设置
  • 验证 chatGuid uses 任何;-; prefix (不 iMessage;-;)
  • Check 响应 有 "isAudioMessage": 真

API 乘以 out:

  • 使用 任何;-;+PHONE 格式 对于 chatGuid
  • 验证 BlueBubbles 私有 API 已启用
  • Restart BlueBubbles 如果 consistently slow

Audio 0 seconds / unplayable:

  • Ensure pre-conversion 到 Opus @ 24kHz
  • Don't 让 BlueBubbles convert (uses wrong codec)
  • 验证 带有: afinfo 输出.caf (应该 show opus @ 24000 Hz)
数据来源：ClawHub ↗ · 中文优化：龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制

免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制

了解定制服务