What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

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 or 720p. Supports optional mask images to target specific faces and text prompts for additional guidance. Use when the user wants to animate a face with audio or create talking avatar videos.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

2.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 2.0.1release · observed Sep 5, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17epnq4kcsv1261rq3e9gvwcx8dth5q:wavespeed-infinitetalk-avatar

Install using `clawhub skill install s17epnq4kcsv1261rq3e9gvwcx8dth5q:wavespeed-infinitetalk-avatar` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/wavespeed/wavespeed-infinitetalk-avatar before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-infinitetalk-avatar/snapshot"

Documentation

CLAWHUB

27,633 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: wavespeed-infinitetalk
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 or 720p. Supports optional mask images to target specific faces and text prompts for additional guidance. Use when the user wants to animate a face with audio or create talking avatar videos.
metadata:
  author: wavespeedai
  version: "2.0"
---

# WaveSpeedAI InfiniteTalk

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 with natural facial animations.

## Setup

Install the open-source CLI once and sign in; the CLI stores the key, so never ask the user to paste an API key into the chat:

```bash
npm install -g @wavespeed/cli
wavespeed login          # opens https://wavespeed.ai/accesskey and stores the key
wavespeed status         # confirms you are signed in
```

For CI or one-off shells, `WAVESPEED_API_KEY` in the environment also works.

Prefer MCP tools over shell commands? The same platform is exposed by [`@wavespeed/mcp`](https://github.com/WaveSpeedAI/mcp-server) (`npx -y @wavespeed/mcp`; tools `search_models`, `get_model_schema`, `get_price`, `upload_file`, `run_model`, `get_prediction`). It shares the CLI's stored login. Every example below maps one-to-one onto `run_model` with the same model id and input fields.

## Quick Start

```bash
# Upload local image and audio files
OUTPUT_URL=$(wavespeed run wavespeed-ai/infinitetalk \
  -i image=@./portrait.png \
  -i audio=@./speech.mp3 \
  --json | jq -r '.outputs[0]')
```

Existing URLs work as-is:

```bash
OUTPUT_URL=$(wavespeed run wavespeed-ai/infinitetalk \
  -i image="https://example.com/portrait.jpg" \
  -i audio="https://example.com/speech.mp3" \
  --json | jq -r '.outputs[0]')
```

## API Endpoint

**Model ID:** `wavespeed-ai/infinitetalk`

Animate a portrait image with lip-synced audio to produce a talking head video.

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `image` | string | Yes | -- | URL of the portrait image to animate |
| `audio` | string | Yes | -- | URL of the audio to drive the animation |
| `mask_image` | string | No | -- | URL of a mask image to specify which person to animate. **Warning:** The mask should only cover the regions to animate — do not upload the full image as `mask_image`, or the result may render as fully black. |
| `prompt` | string | No | -- | Text prompt for additional guidance. Keep it short; English recommended to avoid noisy results. |
| `resolution` | string | No | `480p` | Output resolution. One of: `480p`, `720p` |
| `seed` | integer | No | `-1` | Random seed (-1 for random). Range: -1 to 2147483647 |

### Example

```bash
OUTPUT_URL=$(wavespeed run wavespeed-ai/infinitetalk \
  -i image=@./portrait.png \
  -i audio=@./speech.mp3 \
  -i resolution="720p" \
  -

_meta.json

{
  "ownerId": "kn733k72mbe41a710dd1kfpg2s8257bs",
  "slug": "wavespeed-infinitetalk-avatar",
  "version": "2.0.1",
  "publishedAt": 1788625722481
}

skill-card.md

## Description:

Generate lip-synced talking head videos from portrait images and audio using WaveSpeed AI's InfiniteTalk model.

This skill is ready for commercial/non-commercial use.

## Publisher:

[wavespeed](https://clawhub.ai/user/wavespeed)

### License/Terms of Use:

MIT-0

## Use Case:

External users and developers use this skill to create talking avatar videos from a portrait image and speech audio. It supports optional face masks, prompt guidance, resolution selection, and repeatable seeds for WaveSpeed AI InfiniteTalk generation.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Unpinned npm CLI and MCP setup can change behavior between installs or runs.

Mitigation: Pin reviewed versions of @wavespeed/cli and @wavespeed/mcp in controlled environments and inspect the live model schema before generation.

Risk: Portrait images, audio, mask images, and media URLs may be uploaded or sent to WaveSpeed for generation.

Mitigation: Use only approved user-provided media and avoid sensitive portraits or audio unless the user has confirmed they are comfortable sending them to WaveSpeed.

Risk: API keys could be exposed if pasted into chat or command transcripts.

Mitigation: Use wavespeed login or the WAVESPEED_API_KEY environment variable, and do not ask users to paste secrets into chat.

Risk: Video generation has usage costs and incorrect full-image masks can produce black outputs.

Mitigation: Quote pricing before long runs, start with lower resolution when appropriate, and use masks that cover only the face region to animate.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/wavespeed/skills/wavespeed-infinitetalk-avatar)
- [WaveSpeed MCP server](https://github.com/WaveSpeedAI/mcp-server)
- [WaveSpeed access key login](https://wavespeed.ai/accesskey)

## Skill Output:

**Output Type(s):** [Shell commands, Configuration, Guidance]

**Output Format:** [Markdown with bash command examples, parameter tables, and operational guidance]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Guides an agent to call the WaveSpeed InfiniteTalk model and return generated video URLs or downloaded video files.]

## Skill Version(s):

2.0.1 (source: server release metadata; artifact frontmatter says 2.0)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular