Feishu Audio Message

Send TTS audio as a proper playable audio message (not file attachment) to Feishu chats. Use when asked to send voice messages, TTS audio, speech announcemen...

Security Scan

The skill's purpose (send TTS audio to Feishu) matches what the code does, but the metadata and SKILL.md underreport required binaries/credentials and the script reads a root-level config file — these mismatches warrant caution before installing.

Purpose & Capability

The skill's described purpose (send TTS audio as msg_type=audio to Feishu) matches the included script behavior. However the package metadata declares no required environment variables or binaries while the script clearly expects FEISHU_APP_ID/FEISHU_APP_SECRET (or to read /root/.openclaw/openclaw.json) and relies on curl, python3, and a local TTS binary (/app/openclaw/node_modules/.bin/node-edge-tts). The missing declarations are an inconsistency.

Instruction Scope

SKILL.md and the script stay on-task: generate or accept audio, obtain a Feishu tenant token, upload with file_type=opus, and send msg_type=audio. The only notable instruction is to auto-read /root/.openclaw/openclaw.json for Feishu credentials, which is consistent with OpenClaw deployments but is a privileged read of a config file.

Install Mechanism

No install spec (instruction-only + script) — nothing is downloaded or written by an installer. The script is bundled with the skill; there is no external install URL or archive to evaluate.

Credentials

The script requires Feishu app credentials (FEISHU_APP_ID and FEISHU_APP_SECRET) and will attempt to read them from /root/.openclaw/openclaw.json if env vars are not set. The skill metadata, however, lists no required env vars or primary credential. Reading a root-level OpenClaw config file can expose other channel credentials if the config structure differs; the TTS binary path (/app/openclaw/node_modules/.bin/node-edge-tts) and use of system tools (curl, python3) are not declared either. These omissions reduce transparency about what secrets and system tools the skill accesses.

Persistence & Privilege

The skill does not request persistent or always-on privileges (always:false) and does not modify other skills or system-wide settings. It runs when invoked and cleans up temp files.

What to consider before installing

This skill appears to do what it claims (generate/send Feishu audio messages), but the package metadata underreports what the script actually uses. Before installing: 1) Inspect /root/.openclaw/openclaw.json yourself — it will be read for Feishu creds; ensure you are comfortable with the skill reading that file or set FEISHU_APP_ID and FEISHU_APP_SECRET ENV vars instead. 2) Verify the presence and trustworthiness of the TTS binary (/app/openclaw/node_modules/.bin/node-edge-tts) and confirm you have curl and python3 available. 3) Ask the publisher to update metadata to declare required env vars and binaries so the skill's requirements are transparent. 4) If you require stronger isolation, run the script in a sandbox/container or create a dedicated Feishu account with limited permissions. If you cannot confirm these items, consider this skill suspicious and avoid installing it on sensitive hosts.

feishu-audio

Send TTS audio to Feishu as a playable audio message (msg_type=audio), not a file attachment.

Why This Skill Exists

OpenClaw's message tool sends audio as a generic file. Feishu requires a two-step API flow to display it as a playable voice message:

1. Upload with file_type=opus
2. Send with msg_type=audio

Quick Usage

bash /root/.openclaw/skills/feishu-audio/scripts/send_audio.sh \
  "要说的内容" \
  "<chat_id or user open_id>" \
  [voice]          # optional, default: zh-CN-XiaoyiNeural

receive_id_type is always chat_id. For group chats use oc_xxx; for DMs use ou_xxx (open_id).

Common Voices

Language	Voice
Chinese (F)	zh-CN-XiaoyiNeural (default)
Chinese (M)	zh-CN-YunxiNeural
English (F)	en-US-AriaNeural
English (M)	en-US-GuyNeural

Credentials

Auto-read from /root/.openclaw/openclaw.json → channels.feishu.accounts.main. No manual setup needed in standard OpenClaw deployments.

Two-Step API Flow (for custom integrations)

# Step 1: Upload (file_type=opus is required regardless of actual format)
curl -X POST "https://open.feishu.cn/open-apis/im/v1/files" \
  -H "Authorization: Bearer $TOKEN" \
  -F "file_type=opus" -F "file_name=voice.opus" -F "file=@audio.mp3"
# → returns file_key

# Step 2: Send (msg_type=audio, NOT file)
curl -X POST "https://open.feishu.cn/open-apis/im/v1/messages?receive_id_type=chat_id" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -d '{"receive_id":"oc_xxx","msg_type":"audio","content":"{\"file_key\":\"...\"}"}' 

Key pitfalls:

• file_type must be opus (not mp3) or upload returns 234001
• msg_type must be audio (not file) or it shows as attachment