Lark (Feishu) Voice

核心功能是将文本转换为语音并发送飞书语音消息，适用于用户要求发送语音或语音回复的场景。需依赖ffmpeg和TTS源，系统会自动检测可选TTS源，无指定时自动选择或让用户挑选；生成音频后转换为飞书支持的opus格式，最终发送为语音消息气泡，输入为待转文本内容。

cheerwhy

热度 59.43

最近更新 2026-05-11 17:36:45

分类：自动化依赖：代码执行 / 读写文件 / MCP 服务 / 内部调用大模型 / 第三方 API应用场景：自动化脚本 / 工作流

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add lark-voice

Metadata

name: lark-voice
description: 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.
metadata: {"openclaw":{"requires":{"bins":["ffmpeg"]}}}

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")