pywayne-tts

Convert text to opus or mp3 audio using macOS say or gTTS.

8|Updated Feb 2, 2026

Search Tags:#text-to-speech #macos #audio #ffmpeg #tts #gtts

Ready to run

npx skills add https://github.com/wangyendt/wayne-skills --skill pywayne-tts

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pywayne-tts
Source: https://github.com/wangyendt/wayne-skills/tree/main/pywayne/tts
Command: npx skills add https://github.com/wangyendt/wayne-skills --skill pywayne-tts

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Text-to-speech tooling that converts written content into high-quality audio files (opus or mp3), enabling accessibility, narration, and voice-enabled apps.

Core Features & Use Cases

Opus and MP3 output formats: Generate audio in two common formats and perform conversion with ffmpeg.
Platform options: Native macOS 'say' command with fallback to gTTS on other platforms.
Automation & cleanup: Temporary files are automatically removed after generation.
Use Case: Add voice narration to tutorials or convert chat transcripts to audio summaries.

Quick Start

Convert text to speech for a given string and save it as an audio file (opus or mp3) using macOS 'say' when available or gTTS otherwise.

Frequently Asked Questions about pywayne-tts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert text to speech audio files on macOS?▼

To convert text to speech on macOS, this tool uses the built-in 'say' command to generate audio, then processes the output with ffmpeg to produce opus or mp3 files. Temporary files are automatically cleaned up after the conversion is complete.

Can I use gTTS for text-to-speech when native macOS options are unavailable?▼

Yes, you can use gTTS for text-to-speech when native macOS options are unavailable. The tool automatically falls back to Google's gTTS for online voice synthesis on non-macOS platforms, requiring an internet connection to generate the audio.

Do I need ffmpeg installed to generate opus or mp3 audio from text?▼

Yes, you need ffmpeg installed to generate opus or mp3 audio from text. This text-to-speech tool relies on ffmpeg to handle the audio conversion process, transforming the synthesized speech into your desired output format.

What is the best way to automate voice narration for tutorials using text-to-speech?▼

The best way to automate voice narration is using a text-to-speech tool that outputs opus or mp3 files. This tool converts written content into high-quality audio, making it ideal for adding voice narration to tutorials or converting chat transcripts to audio summaries.

Does this text-to-speech tool clean up temporary files after audio generation?▼

Yes, this text-to-speech tool cleans up temporary files automatically after audio generation. Whether using the macOS 'say' command or the gTTS fallback, intermediate files are removed during the process, leaving only the final opus or mp3 output.