Pywayne Tts

Text-to-speech conversion tool. Use when converting text to speech audio files (opus or mp3 format). Supports macOS native 'say' command and Google TTS (gTTS...

Security Scan

The SKILL.md describes a Python module and CLI-like commands but the skill contains no code or install instructions for the referenced pywayne.tts package, making the bundle internally inconsistent.

Purpose & Capability

The declared purpose (text-to-speech) matches the described behavior (macOS 'say', gTTS, ffmpeg conversion). However, the documentation shows Python calls (from pywayne.tts import ...) and CLI-like commands (text_to_speech_output_opus ...) but the skill bundle contains no code files and no install instructions (no pip package name or how to obtain 'pywayne'). That means the examples can't run as-is and the skill's claimed capability is not deliverable from the provided artifacts.

Instruction Scope

SKILL.md instructs use of a Python module and platform-dependent commands (macOS 'say', gTTS over the network, ffmpeg conversion). It does not ask for unrelated files or credentials, but it implicitly expects the agent/user to have or obtain a 'pywayne.tts' package and ffmpeg/gtts. The Quick Start uses function names as shell commands without clarifying a CLI wrapper. The instructions are therefore vague and grant broad discretion (install/obtain a package from an unspecified source).

Install Mechanism

There is no install spec (instruction-only), which is low-risk from an install perspective. However, the document references dependencies (gtts, ffmpeg, and a Python module 'pywayne') but provides no guidance how to install the Python package or whether it is available on PyPI or elsewhere — a usability/coherence issue rather than an immediate install risk.

Credentials

The skill requests no environment variables or credentials. It does require network access for gTTS and filesystem write permissions for output files, which are proportionate to a TTS tool.

Persistence & Privilege

The skill does not request always:true, does not require persistence, and does not modify other skills or system-wide settings according to the provided files.

What to consider before installing

This skill's README/example code references a Python package (pywayne.tts) and shows Python and CLI-style usage, but the skill bundle contains no code and offers no install instructions — you would not be able to run the examples as-is. Before installing or using this skill, ask the author to: (1) provide the source code or a pip package name and a trustworthy upstream (PyPI/GitHub release), (2) give explicit install steps (pip install <package> or a link to a release), and (3) clarify the intended CLI invocation if any. Also confirm you are comfortable granting network access for gTTS and that ffmpeg will be installed from a trusted source. If the package is to be installed from an unknown/unverified location, treat that as higher risk because arbitrary code could run on install.

Text-to-speech (TTS) tool that converts text to audio files (opus or mp3 format).

Functions

text_to_speech_output_opus - Convert text to Opus format

from pywayne.tts import text_to_speech_output_opus

# Output: test.opus
text_to_speech_output_opus("你好，世界", "test.opus")

Parameters:

• text - Text to convert
• opus_filename - Output .opus filename
• use_say - If True, use macOS 'say' command; otherwise use gTTS (default True)

Behavior:

• On macOS, prefers native 'say' command when use_say=True
• On other platforms, uses Google TTS (gTTS) service
• Uses ffmpeg to convert audio to opus format (16kHz, mono channel)
• Automatically cleans up temporary files

text_to_speech_output_mp3 - Convert text to MP3 format

from pywayne.tts import text_to_speech_output_mp3

# Output: test.mp3
text_to_speech_output_mp3("你好，世界", "test.mp3")

Parameters:

• text - Text to convert
• mp3_filename - Output .mp3 filename
• use_say - If True, use macOS 'say' command; otherwise use gTTS (default True)

Behavior:

• On macOS, prefers native 'say' command when use_say=True
• On other platforms, uses Google TTS (gTTS) service
• Uses ffmpeg to convert audio to mp3 format
• Automatically cleans up temporary files

Quick Start

# Convert text to Opus format (default: macOS uses 'say')
text_to_speech_output_opus "你好，世界" "test.opus"

# Convert text to MP3 format
text_to_speech_output_mp3 "你好，世界" "test.mp3"

# Force use gTTS instead of macOS 'say'
text_to_speech_output_mp3 "你好，世界" "test.mp3" use_say=False

Requirements

• ffmpeg: Required for audio conversion
  • macOS: brew install ffmpeg
  • Windows: Download from https://ffmpeg.org and add to PATH
  • Linux: sudo apt install ffmpeg or package manager
• gtts: Python library for Google TTS service

Platform Detection

Module automatically detects platform and prompts for ffmpeg installation if missing.

Audio Formats

• Opus: Better quality, smaller file size, suitable for voice calls
• MP3: Better compatibility, suitable for multimedia playback

Notes

• Requires network connection for gTTS service
• Temporary files are automatically cleaned up
• Ensure output directory has write permissions