Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Generates AI avatar videos using the Flyworks (HiFly) Digital Humans API. Supports public avatars with text-to-speech, talking photo videos from a single image, and voice cloning from audio samples. A free-tier token is available but adds watermarks and limits videos to 30 seconds.
Combining avatar selection, voice cloning, and video generation into a single CLI tool avoids juggling multiple APIs or web editors.
When to use it
- Create a product demo video with a realistic AI presenter
- Turn a CEO headshot into a talking video for quarterly updates
- Generate multilingual greeting videos using public avatars
- Clone your voice to narrate content without re-recording
- Produce talking photo videos from static profile images
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Create a talking photo video of me saying 'Welcome to my channel'
- 1Run list_public_voices to show available TTS options
- 2Ask user to select a voice or offer to clone one from an audio sample
- 3Run create_talking_photo with the provided image, text, and selected voice ID
- 4Poll check_task with the returned task ID until video is ready
- 5Offer to save the new avatar alias to memory.json for future use
A video file URL of the talking photo with the user's chosen voice
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.