Voice2text

Offline speech-to-text conversion using Vosk local model; input audio file path, output transcript text.

Security Scan

The skill's code, instructions, and requirements match its stated purpose (offline Vosk-based speech-to-text); it asks for no credentials and contains no obvious exfiltration or unrelated actions.

Purpose & Capability

Name/description (offline Vosk STT) align with included files: main.py uses vosk.Model and expects a local 'model' directory; requirements list vosk and pytest. No unrelated credentials, binaries, or services are requested.

Instruction Scope

SKILL.md and README instruct running main.py with an audio path and installing Python deps. The runtime only reads the provided WAV file, loads the local Vosk model, and performs transcription — no access to other files, env vars, or network calls is present in the code.

Install Mechanism

There is no automated install spec; this is instruction-only with code included. Dependencies are standard Python packages (vosk, pytest). No downloads from untrusted URLs or archive extraction are performed by the skill.

Credentials

The skill declares no required env vars, credentials, or config paths. The code does not attempt to read environment secrets or external configs.

Persistence & Privilege

Skill is user-invocable and not set to always; it does not modify other skills or system settings and does not request persistent privileges.

Assessment

This skill appears internally consistent, but it runs publisher-provided Python code locally — review and run it in an isolated environment. Before using: 1) ensure you have a compatible 16kHz mono 16‑bit WAV and a trusted Vosk model placed in a 'model' directory (the package does not include the model); 2) install dependencies from requirements.txt in a virtualenv; 3) inspect main.py yourself (it is short and straightforward) and avoid running untrusted models; 4) if you need stronger isolation, run inside a container or VM. The tests are placeholders and do not create sample audio, so functional testing requires providing a real WAV and a Vosk model.

slug: voice2text title: Voice to Text description: Offline speech-to-text skill using Vosk local model. author: lxxtad license: MIT

入口: main.py implements run(params) – pass {"audio":"path/to.wav"} and get {"text":"transcript"}.

依赖: vosk, pytest.

使用示例:

clawhub install voice2text
clawhub run voice2text '{"audio":"sample.wav"}'