← Back to Skills Marketplace
2142
Downloads
3
Stars
6
Active Installs
2
Versions
Install in OpenClaw
/install pocket-tts
Description
Generate high-quality English speech offline on CPU using 8 built-in voices or custom voice cloning with Kyutai's Pocket TTS model.
Usage Guidance
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.
Capability Analysis
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.
Capability Assessment
Purpose & Capability
Name, SKILL.md, and code all describe a local Pocket TTS integration that loads a Kyutai model via the huggingface hub and exposes CLI and Python usage. The requested files and commands are proportionate to a TTS skill.
Instruction Scope
SKILL.md repeatedly claims 'fully local / offline' but also notes and the code imply an initial model download (uses hf:// URIs and requires accepting a Hugging Face license). test.sh prints a hardcoded path (/home/clawdbot/...) which is environment-specific but not overtly dangerous. The CLI uses os.system('pocket-tts serve') to start a server; otherwise the instructions do not read unrelated secrets or contact unexpected endpoints beyond Hugging Face/GitHub links.
Install Mechanism
There is no registry install spec; included install.sh installs standard Python packages (torch, scipy, huggingface_hub) via pip. No downloads from untrusted URLs or archive extraction are present.
Credentials
The skill declares no required env vars or credentials. It does require the user to accept a gated model license on Hugging Face (may require a Hugging Face account), which is consistent with downloading a gated model. No unrelated credentials are requested.
Persistence & Privilege
always is false and the skill does not request persistent platform privileges or modify other skills. It only includes local install/test scripts and a CLI.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pocket-tts - After installation, invoke the skill by name or use
/pocket-tts - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Update summary with better description
v1.0.0
- Initial release of Pocket TTS Skill.
- Provides fully local, offline text-to-speech using Kyutai’s Pocket TTS model—no API calls required.
- Supports 8 built-in voices plus custom voice cloning from WAV files.
- Features fast CPU-only performance (~6x real-time) and low-latency streaming output.
- Includes CLI and Python API for flexible integration.
- Requires accepting the model license on Hugging Face before installation.
Metadata
Frequently Asked Questions
What is 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. It is an AI Agent Skill for Claude Code / OpenClaw, with 2142 downloads so far.
How do I install Pocket Tts?
Run "/install pocket-tts" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Pocket Tts free?
Yes, Pocket Tts is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Pocket Tts support?
Pocket Tts is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Pocket Tts?
It is built and maintained by sherajdev (@sherajdev); the current version is v1.0.1.
More Skills