Uydi Voice

Use the Uydi voice platform from any agent: voice design (text description → new voice), voice cloning (audio sample → digital voice), and text-to-speech synthesis, all through a single zero-dependency CLI script.

Requirements

• Node.js 18 or newer (node --version) — the script uses only built-in modules.
• A Uydi account (register free at https://uydi.com).
• All commands run as: node scripts/uydi.mjs <command> (relative to this skill directory).

What the skill can do

• Design a new AI voice from a natural-language brief and generate a WAV preview.
• Clone a voice from a 10–20 second WAV, MP3, or M4A sample when the user owns the voice or has explicit permission.
• Synthesize speech from text with a selected Uydi voice and save a WAV file.
• Manage the authenticated account's voice list, synthesis history, and credit balance.