What problem does it solve? Turning written text into natural-sounding spoken audio normally requires picking a TTS service, choosing voices, handling authentication, and managing output files. This Skill wraps the ListenHub CLI into a guided workflow that converts text to speech with sensible voice defaults and persistent user preferences. ## Core Features & Use Cases - Quick Mode: Single-voice, low-latency synchronous speech generation for reading snippets, notifications, or casual text aloud. - Script Mode: Multi-speaker generation with per-character voice assignment for dialogue, audiobooks, and scripted narration, including subtitles and duration metadata. - Voice & Config Persistence: Saves default speakers per language and output mode (inline link or downloaded MP3) to a local config file so repeat runs need no setup. - Use Case: Ask the agent to create a two-person Chinese dialogue voiceover; it parses the script, assigns default voices, submits the job, polls until complete, and saves a topic-named MP3 to the working directory. ## Quick Start Ask the agent to read a piece of text aloud or generate a multi-character dialogue voiceover, and confirm the proposed voice and text before generation.
