← 返回 Skills 市场
1367
总下载
0
收藏
4
当前安装
1
版本数
在 OpenClaw 中安装
/install elevenlabs-ai
功能描述
Access ElevenLabs APIs for text-to-speech, speech-to-speech, realtime speech-to-text, voice/model management, and dialogue workflows with direct HTTP calls.
使用说明 (SKILL.md)
ElevenLabs API Skill (Advanced)
Purpose
Provide a production-oriented guide for using ElevenLabs APIs via direct HTTPS (no SDK requirement), with clear auth, safety, and workflow guidance.
Best fit
- You need text-to-speech or speech-to-speech conversion.
- You want realtime speech-to-text with low latency.
- You prefer direct HTTP calls with predictable outputs.
Not a fit
- You require a full SDK integration and helpers.
- You need full conversational agents beyond audio I/O.
Quick orientation
- Read
references/elevenlabs-authentication.mdfor API keys and single-use tokens. - Read
references/elevenlabs-text-to-speech.mdfor TTS endpoints and payloads. - Read
references/elevenlabs-speech-to-speech.mdfor voice conversion. - Read
references/elevenlabs-speech-to-text-realtime.mdfor realtime STT WebSocket. - Read
references/elevenlabs-text-to-dialogue.mdfor multi-voice dialogue output. - Read
references/elevenlabs-voices-models.mdfor voice IDs and model discovery. - Read
references/elevenlabs-safety-and-privacy.mdfor zero-retention and safety rules.
Required inputs
- API key (xi-api-key) or a single-use token when needed.
- Voice IDs and model IDs for your target use case.
- Output format choice (audio codec/sample rate/bitrate).
Expected output
- A clear workflow plan, endpoint checklist, and operational guardrails.
Operational notes
- Keep a strict allowlist for downstream destinations of audio output.
- Cache voice IDs and model IDs server-side.
- Keep payloads small and retry with backoff on throttling.
Security notes
- Never log API keys or tokens.
- Use single-use tokens for client-side access.
安全使用建议
This skill appears to be a plain, textual guide for using ElevenLabs APIs and is internally consistent. Before installing or using it: (1) confirm how you'll provide the API key — prefer single-use tokens for client-side flows and avoid storing long-lived keys in the agent environment; (2) verify the skill (owner/slug) comes from a source you trust since the registry metadata lacks a homepage; (3) if you need stronger assurance, request the full text of any runtime workflow the agent will execute with your key (to ensure it won't be persisted or sent to other endpoints); and (4) follow the skill's own advice to redact keys from logs and employ retry/backoff and allowlists for downstream audio destinations.
功能分析
Type: OpenClaw Skill
Name: elevenlabs-ai
Version: 1.0.0
The skill bundle is a documentation-focused guide for interacting with ElevenLabs APIs. All files contain informational markdown, detailing API endpoints, authentication methods, and security considerations. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, obfuscation, or prompt injection attempts against the OpenClaw agent. The instructions are clearly aligned with providing guidance on using the ElevenLabs service.
能力评估
Purpose & Capability
The skill name and SKILL.md focus on ElevenLabs text-to-speech, speech-to-speech, realtime STT, voices/models and dialogue workflows. The inputs it describes (xi-api-key or single-use token, voice IDs, model IDs, output formats) are exactly what ElevenLabs API usage requires, so the requested capabilities match the stated purpose. Note: the manifest shows no declared required environment variables — the skill expects API keys as runtime inputs rather than baked-in env vars, which is a reasonable design but worth noting.
Instruction Scope
Runtime instructions reference only the included reference docs and ElevenLabs endpoints (api.elevenlabs.io, wss://api.elevenlabs.io). There are no instructions to read unrelated local files, harvest environment variables, or transmit data to unexpected endpoints. The SKILL.md also includes explicit safety guidance (do not log API keys, use single-use tokens) which limits scope creep.
Install Mechanism
This is an instruction-only skill with no install spec and no code files to execute. That presents a low installation risk (nothing will be written to disk or fetched during install).
Credentials
The skill legitimately needs an ElevenLabs API key or single-use token at runtime; this is proportionate to its function. However, the registry metadata declares no required env vars or primary credential. That is not necessarily malicious (the skill may expect the user to supply keys per-request), but users should confirm how they will provide credentials (ephemeral token vs. long-lived key) and whether the agent will persist them.
Persistence & Privilege
The skill does not request always:true and is user-invocable only. There is no install behavior, no evidence it modifies other skills or system-wide settings, and no persistent background presence. Autonomous invocation remains allowed by default, which is normal for skills and not a concern here by itself.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install elevenlabs-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/elevenlabs-ai触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of the ElevenLabs AI skill with production-focused guidance for ElevenLabs APIs.
- Supports direct HTTP integration for text-to-speech, speech-to-speech, realtime speech-to-text, and dialogue workflows.
- Provides detailed orientation with links to authentication, endpoint usage, safety, and privacy documentation.
- Clarifies required inputs (API keys, voice/model IDs, output format) and expected outputs (workflow plan, checklist, guardrails).
- Includes operational and security recommendations for safe API usage.
元数据
常见问题
Elevenlabs AI 是什么？
Access ElevenLabs APIs for text-to-speech, speech-to-speech, realtime speech-to-text, voice/model management, and dialogue workflows with direct HTTP calls. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1367 次。
如何安装 Elevenlabs AI？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install elevenlabs-ai」即可一键安装，无需额外配置。
Elevenlabs AI 是免费的吗？
是的，Elevenlabs AI 完全免费（开源免费），可自由下载、安装和使用。
Elevenlabs AI 支持哪些平台？
Elevenlabs AI 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Elevenlabs AI？
由 codedao12（@codedao12）开发并维护，当前版本 v1.0.0。
推荐 Skills