Agents

Generate character-consistent selfie images and videos, send via OpenClaw messaging channels. Character reference image and description come from per-agent env.

Send voice/song audio to Feishu — voice.sh does plain TTS (MiniMax or Volcengine); sing.sh generates a full song with melody via MiniMax music-2.6

Transcribe user-sent voice messages via local OpenAI Whisper (no API key, runs offline)

Resolve Feishu image_key to a local file path so the agent can Read the image natively