OpenClaw TTS Voice Switch
Use this skill when you need to change the ElevenLabs voice used by OpenClaw Gateway built-in TTS.
Version scope:
- - Verified against INLINECODE0
- Newer OpenClaw versions may change config keys, behavior, or restart flow, so this skill may not work without updates
Scope:
- - This skill only targets Gateway built-in TTS under INLINECODE1
- It does not target other speech systems, external plugins, call-specific overrides, or unrelated TTS integrations
Read references/tts-parameters.md when you need parameter meanings, file paths, or language/model guidance.
Use scripts/list_voices.sh when you need the actual voices and languages available in the current ElevenLabs account.
It updates:
It keeps these defaults unless the user explicitly wants something else:
- - INLINECODE5
- INLINECODE6
- INLINECODE7
Workflow
- 1. If the user asks which voices or languages are supported, run:
CODEBLOCK0
- 2. Confirm the target voice name or
voiceId. - If only a voice name is given, resolve it to a
voiceId from the script output. - Run:
CODEBLOCK1
- 5. Tell the user which file and parameter changed.
- Suggest a quick verification command:
CODEBLOCK2
Supported Inputs
- - Direct INLINECODE10
- Existing known Chinese-capable ElevenLabs INLINECODE11
- Optional INLINECODE12
- Optional INLINECODE13
- Optional INLINECODE14
If the user only gives a voice name, resolve it to a voiceId first.
OpenClaw TTS 语音切换
当你需要更改 OpenClaw 网关内置 TTS 所使用的 ElevenLabs 语音时,使用此技能。
版本范围:
- - 已验证兼容 OpenClaw v2026.3.13
- 较新版本的 OpenClaw 可能会更改配置键、行为或重启流程,因此此技能在未更新时可能无法正常工作
适用范围:
- - 此技能仅针对 messages.tts 下的网关内置 TTS
- 不针对其他语音系统、外部插件、特定通话覆盖设置或无关的 TTS 集成
当你需要参数含义、文件路径或语言/模型指导时,请阅读 references/tts-parameters.md。
当你需要当前 ElevenLabs 账户中可用的实际语音和语言时,请使用 scripts/list_voices.sh。
它会更新:
- - ~/.openclaw/openclaw.json
- messages.tts.elevenlabs.voiceId
除非用户明确要求其他设置,否则它会保留以下默认值:
- - messages.tts.provider = elevenlabs
- messages.tts.elevenlabs.modelId = elevenmultilingualv2
- messages.tts.elevenlabs.languageCode = zh
工作流程
- 1. 如果用户询问支持哪些语音或语言,运行:
bash
bash scripts/list_voices.sh
bash scripts/list_voices.sh zh
- 2. 确认目标语音名称或 voiceId。
- 如果只提供了语音名称,则从脚本输出中解析出对应的 voiceId。
- 运行:
bash
bash scripts/switchttsvoice.sh
bash scripts/switchttsvoice.sh
bash scripts/switchttsvoice.sh
bash scripts/switchttsvoice.sh
- 5. 告知用户哪个文件和参数已更改。
- 建议一个快速验证命令:
bash
/tts audio 今天天气不错,我们下午三点开会。
支持的输入
- - 直接 voiceId
- 已知支持中文的 ElevenLabs voiceId
- 可选的 languageCode
- 可选的 modelId
- 可选的 apiKey
如果用户只提供了语音名称,请先将其解析为 voiceId。