Feishu Voice — ListenHub TTS

Send high-quality Chinese voice messages on Feishu using ListenHub's TTS engine.

Prerequisites

• ffmpeg / ffprobe
• curl, python3
• ListenHub API key (get from https://listenhub.ai/settings/api-keys)
• Feishu app with im:message:send_as_bot and im:file permissions

Environment Variables

If FEISHU_APP_ID / FEISHU_APP_SECRET are not in env, extract from openclaw config:

export FEISHU_APP_ID=$(python3 -c "import json; print(json.load(open('$HOME/.openclaw/openclaw.json'))['channels']['feishu']['appId'])")
export FEISHU_APP_SECRET=$(python3 -c "import json; print(json.load(open('$HOME/.openclaw/openclaw.json'))['channels']['feishu']['appSecret'])")

Sending Voice Messages

scripts/feishu-voice-send.sh <text> <receive_id> [receive_id_type] [speaker_id]

• receive_id: target user open_id or chat_id
• receive_id_type: open_id (default) or chat_id
• speaker_id: override default speaker for this message

Listing Available Speakers

scripts/list-speakers.sh [language]

Examples:

scripts/list-speakers.sh zh    # Chinese voices only
scripts/list-speakers.sh en    # English voices only
scripts/list-speakers.sh       # All voices

Popular Chinese Speakers

TTS Modes

• direct — 原样朗读文本，不做修改（推荐日常用）
• smart — AI 优化文本后再朗读（适合粗稿）

Important Notes

• ListenHub TTS 是异步的，脚本会自动轮询等待（最长 60 秒）
• 生成的音频自动转为 opus 格式发送到飞书
• 中文语音质量非常高，特别是对话和叙事场景
• msg_type 必须是 "audio"，OpenClaw 的 asVoice 不可用于飞书