← Back to Skills Marketplace
368
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install wavespeed-infinitetalk-avatar
Description
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...
Usage Guidance
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.
Capability Analysis
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.
Capability Assessment
Purpose & Capability
The SKILL.md describes a coherent purpose (generate lip-synced talking-head videos via WaveSpeed InfiniteTalk) and the examples and parameters match that purpose. However, the registry metadata claims no required environment variables or credentials while the runtime instructions repeatedly show use of WAVESPEED_API_KEY and a wavespeed client library — this is an inconsistency.
Instruction Scope
The instructions stay within the stated purpose: uploading/pointing to image and audio assets, optional mask and prompt, and calling the InfiniteTalk model. They warn about untrusted URLs and API key security. There are no instructions to read unrelated files or exfiltrate data beyond calls to the WaveSpeed service.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, which minimizes on-disk installation risk. The SKILL.md references importing a 'wavespeed' client library but does not provide or require an install mechanism — that omission is a documentation gap but not an installation red flag by itself.
Credentials
The SKILL.md demonstrates use of WAVESPEED_API_KEY and client constructors that accept an API key, yet the skill metadata lists no required environment variables or primary credential. Requesting an API key for a third-party service is expected for this functionality, but the omission in metadata is an incoherence that could lead to unclear privilege/secret handling. No other unrelated credentials are requested.
Persistence & Privilege
The skill does not request always: true and defaults to normal invocation behavior. There is no indication it modifies other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install wavespeed-infinitetalk-avatar - After installation, invoke the skill by name or use
/wavespeed-infinitetalk-avatar - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of WaveSpeed InfiniteTalk: generate talking avatar videos from images and audio.
- Creates lip-synced talking head videos up to 10 minutes, at 480p or 720p resolution.
- Supports optional mask images for targeting specific faces in group photos.
- Allows text prompts for fine-tuning animation behavior.
- Provides both quick-start and advanced usage examples (including error handling).
- Includes security best practices and pricing details.
Metadata
Frequently Asked Questions
What is 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... It is an AI Agent Skill for Claude Code / OpenClaw, with 368 downloads so far.
How do I install WaveSpeedAI Infinitetalk Talking Avatar Video Generation?
Run "/install wavespeed-infinitetalk-avatar" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is WaveSpeedAI Infinitetalk Talking Avatar Video Generation free?
Yes, WaveSpeedAI Infinitetalk Talking Avatar Video Generation is completely free (open-source). You can download, install and use it at no cost.
Which platforms does WaveSpeedAI Infinitetalk Talking Avatar Video Generation support?
WaveSpeedAI Infinitetalk Talking Avatar Video Generation is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created WaveSpeedAI Infinitetalk Talking Avatar Video Generation?
It is built and maintained by C (@chengzeyi); the current version is v1.0.0.
More Skills