Lark (Feishu) Voice
name: lark-voice
by cheerwhy · published 2026-04-01
$ claw add gh:cheerwhy/cheerwhy-lark-voice---
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
Usage
1. Discover TTS Source
Scan installed skills for names containing `tts`, and check if the OpenClaw built-in `tts` tool is available.
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.opus4. 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")More tools from the same signal band
Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).
Sign plugins, rotate agent credentials without losing identity, and publicly attest to plugin behavior with verifiable claims and authenticated transfers.
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your...