Pocket Tts

Generate high-quality English speech offline on CPU using 8 built-in voices or custom voice cloning with Kyutai's Pocket TTS model.

This skill is coherent with a local TTS tool but note: (1) despite marketing language about being 'fully offline', the first run will download the model from Hugging Face and you must accept a gated model license — that requires Internet access and possibly a Hugging Face account. (2) install.sh will pip-install torch and huggingface_hub (large packages); run in a virtualenv. (3) test.sh references a hardcoded path (/home/clawdbot/...) which is environment-specific — it’s not harmful but may fail on your machine. (4) There is a small bug risk in the included cli.py (uses wavfile.write but doesn't import wavfile alias), so expect occasional runtime errors; review/patch before deploying. If you need strict offline operation, pre-download the model and dependencies and verify the code uses local model files only. Otherwise this skill appears benign.

Type: OpenClaw Skill Name: pocket-tts Version: 1.0.1 The skill bundle is benign. All files (SKILL.md, install.sh, test.sh, cli.py) are clearly aligned with the stated purpose of providing local text-to-speech functionality using the `pocket-tts` library. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts against the agent. The `install.sh` script installs standard Python dependencies, and `cli.py` uses `os.system` only for a hardcoded, local command (`pocket-tts serve`) to start a local HTTP server, which is a documented feature and not indicative of malicious intent or arbitrary command execution.