WaveSpeedAI Infinitetalk Talking Avatar Video Generation

Generate talking head videos from a portrait image and audio using WaveSpeed AI's InfiniteTalk model. Produces lip-synced video up to 10 minutes long at 480p...

This skill appears to actually require a WaveSpeed API key and a client library even though the registry metadata doesn't list them. Before installing or enabling it: 1) Verify the skill's publisher and source (there's no homepage or repository listed). 2) Confirm where WAVESPEED_API_KEY will be stored and who/what will have access to it — do not paste secrets into public prompts. 3) Ask the publisher to update metadata to declare the required credential and any install steps so you can audit them. 4) Consider privacy and misuse risks (deepfakes) for uploaded images/audio; avoid providing sensitive personal data. 5) If you don't trust the source, do not enable autonomous invocation or provide an API key.

Type: OpenClaw Skill Name: wavespeed-infinitetalk-avatar Version: 1.0.0 The skill bundle appears benign. It provides functionality to generate talking head videos using the WaveSpeed AI service, requiring local file uploads or remote URL fetching for image and audio inputs. While the skill involves network calls to an external AI service and implied local file system access, these capabilities are directly aligned with its stated purpose. Crucially, the `SKILL.md` file includes a 'Security Constraints' section that explicitly warns against 'arbitrary URL loading' from untrusted sources and advises on API key security and input validation, indicating developer awareness of potential risks and an intent to guide users towards secure practices, rather than exploit vulnerabilities.