edge-tts

The edge-tts skill provides text-to-speech conversion by using the `uvx edge-tts` command to generate spoken audio from text input. It is designed for situations where listening is more practical than reading, such as accessibility support, multitasking, or hands-free consumption of content while driving or cooking. Instead of requiring manual audio production, the skill converts provided text into audio output in MP3 format, making it useful for transforming written content into speech quickly and consistently.

Its main capabilities include generating high-quality speech audio, selecting from multiple available neural voices, and adjusting speech characteristics such as rate, volume, and pitch. The skill also supports subtitle generation alongside audio output. Voice selection includes multiple English, French, and Chinese options listed in the source content, with support for different voice personalities and content categories where available. Usage is command-based through `uvx edge-tts`, with examples showing standard audio generation, subtitle output, voice switching, and speech parameter customization.

This skill is suited for users who explicitly want text spoken aloud rather than displayed as text. Likely users include people seeking accessibility accommodations, users consuming content while occupied with other tasks, and anyone needing configurable synthesized speech output with language or voice preferences. It is also useful when a request includes a TTS trigger or keyword indicating spoken output is preferred. The skill is appropriate for generating narrated versions of messages or content where configurable voice playback is more effective than reading on screen.