minimax_ttsvoicereponse_feishu

Convert text to speech using MiniMax API and send voice bubble messages on Feishu upon user voice reply requests.

This skill will call MiniMax's TTS API and convert the returned audio to OGG using ffmpeg — that part is implemented in scripts/voice_reply.py. However: (1) the script does NOT send the resulting audio to Feishu; SKILL.md claims Feishu messaging but the code only prints an OGG path. If you expect automatic posting to Feishu, confirm how OpenClaw or another integration will actually upload/send the file. (2) The registry metadata omitted declaring the required MINIMAX_VOICE_API_KEY — you should not install or run the script until metadata correctly lists this required credential. (3) Prefer setting the API key as an environment variable rather than storing it in config.txt (plaintext). (4) Ensure ffmpeg is installed and review the script before running; it writes to ~/.openclaw/workspace/voice_reply.ogg and may create that directory. Recommended actions before installing: verify or add Feishu-posting code/steps, update registry metadata to declare MINIMAX_VOICE_API_KEY, inspect the code yourself (or have a reviewer) to confirm there are no hidden endpoints, and store the API key securely (env var or secret store) rather than in config.txt.

Type: OpenClaw Skill Name: minimax-voicereponse-feishu Version: 1.0.0 The skill provides a legitimate text-to-speech (TTS) service using the MiniMax API and FFmpeg for audio conversion. The main script, scripts/voice_reply.py, handles API authentication via environment variables or a local config file and uses subprocess.run safely to invoke FFmpeg without shell injection risks. No evidence of data exfiltration, malicious execution, or prompt injection was found.