← 返回 Skills 市场

Lark (Feishu) Voice

Name: Lark (Feishu) Voice
Author: cheerwhy

作者 Cheer · GitHub ↗ · v0.1.2 · MIT-0

cross-platform ✓ 安全检测通过

260

总下载

当前安装

版本数

在 OpenClaw 中安装

/install lark-voice

功能描述

Send voice messages on Lark (Feishu) by converting text to speech. Use when the user asks to send a voice message or reply with voice.

使用说明 (SKILL.md)

Lark (Feishu) Voice

Convert text to speech and send as a voice message on Lark (Feishu).

Requirements

ffmpeg — audio format conversion
At least one TTS source (skill or built-in tool)

Usage

1. Discover TTS Source

Scan installed skills for names containing tts, and check if the OpenClaw built-in tts tool is available.

User specified a TTS source → use it directly
Not specified, only one available → use it directly
Not specified, multiple available → ask the user to choose
None available → use the OpenClaw built-in tts tool, and suggest installing a TTS skill for more voice options

2. Generate Audio

Call the selected TTS source to generate an audio file in wav/mp3 or other intermediate format, saved to /tmp/openclaw/.

3. Convert to Opus

Feishu voice messages only support the opus format (OGG container).

ffmpeg -y -i /tmp/openclaw/input.wav -c:a libopus -b:a 24k -ar 24000 -ac 1 /tmp/openclaw/voice.opus

4. Send Voice

Use the message tool to send. The openclaw-lark plugin automatically detects the .opus extension, parses the duration, and delivers it as a msg_type: audio voice bubble.

message(action=send, media="/tmp/openclaw/voice.opus", message="optional text")

安全使用建议

This skill appears to do what it says: it needs ffmpeg and a TTS provider (either another installed TTS skill or the built-in tts tool) and uses the message tool / openclaw-lark plugin to send the .opus audio. Before installing, ensure your environment has ffmpeg and a trusted message/Lark integration available — the SKILL.md assumes a `message` tool/openclaw-lark plugin exists but the registry metadata didn't explicitly declare that dependency. Also be aware the skill will look at the list of installed skills to find TTS providers and will write temporary files to /tmp/openclaw/. No secrets or external downloads are requested.

功能分析

Type: OpenClaw Skill Name: lark-voice Version: 0.1.2 The lark-voice skill provides instructions for an AI agent to convert text to speech and send it as a voice message on Lark (Feishu). It utilizes standard system tools like ffmpeg for audio conversion and relies on existing TTS and messaging plugins. No malicious patterns, data exfiltration, or suspicious command executions were found in SKILL.md or _meta.json.

能力评估

ℹ Purpose & Capability

Name/description, need for ffmpeg, use of a TTS source, and sending via the message tool align with the stated purpose. One minor omission: the SKILL.md expects a `message` tool / openclaw-lark plugin to be present but the skill metadata did not declare that dependency explicitly.

✓ Instruction Scope

Instructions are narrowly scoped: discover a TTS provider among installed skills or built-in tool, generate audio to /tmp/openclaw/, convert to opus with ffmpeg, and invoke the message tool to send. Scanning installed skills for TTS providers is justified by the feature but does require reading which skills are present.

✓ Install Mechanism

Instruction-only skill with no install spec and no downloads — minimal install risk.

✓ Credentials

No environment variables, no credentials, and no config paths are requested — the access requested is proportional to the functionality.

✓ Persistence & Privilege

Does not request always-on presence or modify other skills' configs. It reads installed-skill metadata at runtime (to find TTS providers), which is within normal agent behavior.

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 lark-voice
安装完成后，直接呼叫该 Skill 的名称或使用 /lark-voice 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

v0.1.2

No content changes

v0.1.1

Rename sections

v0.1.0

Initial release

元数据

Slug lark-voice

版本 0.1.2

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 3

常见问题