Skip to main content

local-tts

Generates high-quality speech from text locally using VoxCPM2, supporting voice design and cloning without API calls.

Install this skill

or
79/100

Security score

The local-tts skill was audited on May 23, 2026 and we found 9 security issues across 3 threat categories. Review the findings below before installing.

Categories Tested

Security Issues

medium line 78

Template literal with variable interpolation in command context

SourceSKILL.md
78```bash
medium line 54

Access to hidden dotfiles in home directory

SourceSKILL.md
54The skill expects a Python venv at `~/.local-tts/venv` with the `voxcpm` package installed. If missing, create it:
low line 57

Access to hidden dotfiles in home directory

SourceSKILL.md
57mkdir -p ~/.local-tts
low line 58

Access to hidden dotfiles in home directory

SourceSKILL.md
58python3.12 -m venv ~/.local-tts/venv
low line 59

Access to hidden dotfiles in home directory

SourceSKILL.md
59~/.local-tts/venv/bin/pip install --upgrade pip voxcpm
medium line 62

Access to hidden dotfiles in home directory

SourceSKILL.md
62First generation downloads ~10 GB of model weights to `~/.cache/huggingface/`. Subsequent runs load the cache in ~30s.
low line 69

Access to hidden dotfiles in home directory

SourceSKILL.md
69ls ~/.local-tts/venv/bin/python && echo "venv OK" || echo "Run setup first"
low line 79

Access to hidden dotfiles in home directory

SourceSKILL.md
79VENV=~/.local-tts/venv
low line 213

External URL reference

SourceSKILL.md
213- Model card: https://huggingface.co/openbmb/VoxCPM2
Scanned on May 23, 2026
View Security Dashboard
Installation guide →