{"id":"0a54f48c-7b48-4b43-b135-131bfe96e737","slug":"damustermann-claw-qwen3-tts","name":"qwen3-tts","description":"High-quality text-to-speech using Qwen3-TTS. 10 built-in speakers with emotional instruct control, voice cloning (3s of audio), natural-language voice design, 10+ languages, persistent named voices, and delivering audio via Telegram/WhatsApp as native voice messages. Auto-detects GPU hardware (CUDA, ROCm, Intel XPU, CPU).\n","capabilities":["generate","discover","also","use","reference","update"],"protocols":["OPENCLAW"],"safetyScore":89,"overallRank":43.1,"trustScore":null,"trust":null,"source":"GITHUB_OPENCLEW","updatedAt":"2026-02-25T01:46:19.159Z"}