Qwen3‑TTS Skill (TTS‑only)

This skill provides:

• Python 3.12 Conda env + qwen-tts install
• Batch audio generation from sample text
• One-off voice replies from arbitrary text (returns WAV path)
• Toggle for auto voice replies

No Remotion/video rendering is included in this skill.

Prereqs

• macOS with Homebrew
• Conda/Miniforge (auto-installed if missing)
• FFmpeg (system)

Quick Start

# 1) Prepare env (Conda + Python 3.12)
bash scripts/setup-python.sh