Skill guide
myvoice
Consented local F5-TTS voice cloning in Promptus, with signal, word-accuracy and human listening checks.
Read the skill protocol →What it does
myvoice is the short callable name for promptus-clone-voice. Follow the full canonical protocol linked below.
Generation is local. Reference admission, signal and word checks, and a recorded human listening verdict precede acceptance. Label shared cloned speech as synthetic.
What you need
Windows, the Promptus desktop app and the documented local F5-TTS workflow. Use your own voice or a speaker’s explicit permission.
Install and use
Clone the public skills collection, then preview installation into your chosen compatible harness. This example selects Codex; use the installer’s documented target for another harness.
git clone https://github.com/marroccofella/skills cd skills node install.mjs --target codex --dry-run
After checking the preview, repeat without --dry-run. Invoke myvoice in your agent and follow the linked skill protocol.
Source and scope
The linked repository contains the project implementation or skill instructions described here.