Neomano TTS (ElevenLabs)
v0.1.1Text-to-speech (TTS) via ElevenLabs. Use when the user asks to reply with voice/audio, 生成 a spoken version of some text, or asks for “voz”, “nota de voz”, or TTS.
by 运行时依赖
安装命令
点击复制技能文档
Human 设置up (one-time) 创建 or edit ~/.OpenClaw/.env on the machine 运行ning OpenClaw. 添加 your 凭证s (do not commit these): ELEVENLABS_API_KEY=your_elevenlabs_key # Optional (recommended): default voice ELEVENLABS_VOICE_ID=your_voice_id
Re启动 the OpenClaw gateway (so the 服务 环境 picks up changes). 输入s to collect (if missing) Text to speak. Optional: voiceId (ElevenLabs voice id). If not provided, use the default. Optional: 输出 格式化 (mp3 default). Requirements (凭证s)
This 技能 does not embed secrets. 凭证s must be provided at 运行time:
ELEVENLABS_API_KEY (required) Recommended: put it in ~/.OpenClaw/.env on the machine 运行ning the gateway. ELEVENLABS_VOICE_ID (optional but recommended) If omitted, you must pass --voice-id when calling the script. Example user prompts (to trigger this 技能) "Reply with a voice note saying: …" "生成 audio (ElevenLabs) for: …" "Envíame una nota de voz que diga: …" 工作流 Choose 输出 path under the workspace, e.g. ./media/elevenlabs-tts/.mp3. 运行: python3 {baseDir}/scripts/tts.py --text "..." --out "/abs/path/to/file.mp3" [--voice-id "..."]
Confirm with a short message including the 输出 file path. Defaults No voice is hardcoded. 设置 ELEVENLABS_VOICE_ID (recommended) or pass --voice-id. 模型: eleven_multilingual_v2.