Text-to-Speech UI
When to use: Adding text-to-speech to products: article readers, accessibility tools, language learning, narration preview, and voice features.
npx skills add text-to-speech-uigit clone https://github.com/skillhub-community/text-to-speech-ui.gitDescription
A text-to-speech control suite. TTSPlayer: play/pause/stop, seek bar with buffered range, rate slider (0.5-2x), pitch control, and a live waveform of the audio. VoicePicker: grouped voice lists by language/locale with preview snippets (each voice plays a one-second sample), labeled with naturalness tags. SSMLPanel: an editor for SSML input (break, emphasis, phoneme, prosody) with syntax highlighting and a live 'render' that highlights the spoken segment as audio plays. StreamMode: play audio as it streams from the backend instead of waiting for the full file.
Provider-agnostic: works with Web Speech API (built-in, zero setup), OpenAI TTS, ElevenLabs, Azure, or any REST endpoint via an adapter. Includes a text-length budget calculator (cost/character estimate) and a chunker that splits long articles into paragraphs for stable narration. Accessibility: keyboard controls for all player functions, ARIA live region announces playback state, and word-level highlight mode (the spoken word is highlighted in the source text as it's read).
AI Hub
Need a model endpoint?
AI Hub is an OpenAI-compatible endpoint for Cursor, Claude Code, and Agent workflows.
Open AI Hub