首页龙虾技能列表 › Miranda SAG (ElevenLabs TTS say-UX) — 技能工具

🗣️ Miranda SAG (ElevenLabs TTS say-UX) — 技能工具

v1.0.0

[自动翻译] ElevenLabs text-to-speech with mac-style say UX.

0· 546·1 当前·1 累计
by @jeffpignataro·MIT-0
下载技能包
License
MIT-0
最后更新
2026/2/26
安全扫描
VirusTotal
无害
查看报告
OpenClaw
安全
high confidence
The skill is internally coherent for ElevenLabs TTS: it requires the sag CLI and an ElevenLabs API key, and its instructions only describe using that CLI to generate local audio files.
评估建议
This skill is coherent for ElevenLabs TTS: it expects the sag CLI and your ElevenLabs API key. Before installing, verify the Homebrew tap (steipete/tap) and inspect that formula to ensure it comes from a trusted source. Be aware the CLI writes audio to /tmp (temporary files) and that any audio file path you include will be served to the user. If you want to limit exposure, create or rotate an API key with minimal scope for this use. Note the SKILL.md mentions alternate env names (SAG_API_KEY, EL...
详细分析 ▾
用途与能力
The name/description (ElevenLabs TTS with mac-style say UX) match the declared requirements: a 'sag' binary and ELEVENLABS_API_KEY. Requiring the sag CLI and an ElevenLabs API key is proportionate to the stated purpose.
指令范围
SKILL.md is instruction-only and simply shows CLI usage (generating audio to /tmp and embedding as MEDIA:/tmp/...). It does not instruct reading unrelated files or exfiltrating data. Minor note: the docs mention additional env vars (SAG_API_KEY, ELEVENLABS_VOICE_ID, SAG_VOICE_ID) that are supported by the CLI but not declared in requires.env.
安装机制
Install uses a Homebrew formula (steipete/tap/sag) which will create the sag binary. Homebrew installs are common, but this uses a third-party tap (steipete) rather than an official central formula—worth verifying the tap's trustworthiness before installing.
凭证需求
Only ELEVENLABS_API_KEY is declared as required and is the primary credential—this is appropriate. The SKILL.md also references optional/alternate env names (SAG_API_KEY, ELEVENLABS_VOICE_ID, SAG_VOICE_ID) which are not declared; this is a minor mismatch but not inherently dangerous.
持久化与权限
always is false, the skill does not request permanent presence or elevated privileges, and there are no instructions to modify other skills or system-wide settings.
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

latestv1.0.02026/2/21

Mac-style TTS with ElevenLabs. Audited.

● 无害

安装命令 点击复制

官方npx clawhub@latest install miranda-sag
镜像加速npx clawhub@latest install miranda-sag --registry https://cn.clawhub-mirror.com

技能文档

Use sag for ElevenLabs TTS with local playback.

API key (required)

  • ELEVENLABS_API_KEY (preferred)
  • SAG_API_KEY also supported by the CLI

Quick start

  • sag "Hello there"
  • sag speak -v "Roger" "Hello"
  • sag voices
  • sag prompting (model-specific tips)

Model notes

  • Default: eleven_v3 (expressive)
  • Stable: eleven_multilingual_v2
  • Fast: eleven_flash_v2_5

Pronunciation + delivery rules

  • First fix: respell (e.g. "key-note"), add hyphens, adjust casing.
  • Numbers/units/URLs: --normalize auto (or off if it harms names).
  • Language bias: --lang en|de|fr|... to guide normalization.
  • v3: SSML not supported; use [pause], [short pause], [long pause].
  • v2/v2.5: SSML supported; not exposed in sag.

v3 audio tags (put at the entrance of a line)

  • [whispers], [shouts], [sings]
  • [laughs], [starts laughing], [sighs], [exhales]
  • [sarcastic], [curious], [excited], [crying], [mischievously]
  • Example: sag "[whispers] keep this quiet. [short pause] ok?"

Voice defaults

  • ELEVENLABS_VOICE_ID or SAG_VOICE_ID

Confirm voice + speaker before long output.

Chat voice responses

When Peter asks for a "voice" reply (e.g., "crazy scientist voice", "explain in voice"), generate audio and send it:

# Generate audio file
sag -v Clawd -o /tmp/voice-reply.mp3 "Your message here"

# Then include in reply: # MEDIA:/tmp/voice-reply.mp3

Voice character tips:

  • Crazy scientist: Use [excited] tags, dramatic pauses [short pause], vary intensity
  • Calm: Use [whispers] or slower pacing
  • Dramatic: Use [sings] or [shouts] sparingly

Default voice for Clawd: lj2rcrvANS3gaWWnczSX (or just -v Clawd)

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