Hedra

Generate images, videos, and lip-synced talking avatar videos from text prompts using Hedra AI models via the OpenClaw plugin.

Security Scan

The plugin's code and README are coherent with a Hedra integration (it only talks to api.hedra.com and requires a Hedra API key), but registry metadata omits the required credential and the package's origin/homepage is unclear — review before installing.

Purpose & Capability

The plugin implements Hedra image/video/avatar generation and only requires a Hedra API key and optional default model IDs — this is coherent with the stated purpose. However, the registry metadata at the top of the submission incorrectly lists no required environment variables/credentials while the package and SKILL.md explicitly require HEDRA_API_KEY (and openclaw.plugin.json documents it). The capability itself is appropriate for the name/description, but the metadata mismatch is suspicious.

Instruction Scope

SKILL.md and the plugin code restrict actions to Hedra API calls (base URL https://api.hedra.com/web-app/public). Runtime instructions focus on generating assets, listing models/voices, polling generation status, and configuring the Hedra API key. The instructions do not ask to read unrelated system files or exfiltrate data to other endpoints.

Install Mechanism

This is an instruction-only/packaged plugin with source files included; there is no download-from-arbitrary-URL install step. package.json lists only a small dependency (@sinclair/typebox) and normal dev deps. No high-risk install operations (remote archives, unknown hosts) are present.

Credentials

The plugin legitimately requires a single service credential (HEDRA_API_KEY) which is proportionate to its functionality. The concern is that the registry summary incorrectly states 'Required env vars: none' and 'Primary credential: none' while both SKILL.md and openclaw.plugin.json expect HEDRA_API_KEY — this inconsistency could lead to misconfiguration or surprise when the plugin fails at runtime or when users inadvertently expose keys. No other unrelated secrets or system paths are requested.

Persistence & Privilege

The skill does not request always:true, does not modify other skills, and only uses its own plugin config / environment variable. It registers tools for on-demand use and does not demand persistent elevated privileges.

What to consider before installing

This plugin's code and docs show it only talks to Hedra (https://api.hedra.com) and needs a Hedra API key (HEDRA_API_KEY or plugin config). However, the registry metadata omitted that credential — treat that as a packaging/metadata red flag. Before installing: 1) Verify the plugin origin (README references a GitHub repo; confirm the publisher and repository contents match the packaged files). 2) Only provide a Hedra API key scoped/minimal for the required operations and avoid placing it in global/shared env vars if possible. 3) Inspect the included source (dist/src) or compare with upstream repo to ensure no hidden callbacks or alternate endpoints have been added. 4) If you rely on this in a sensitive environment, consider running it in an isolated environment or network with egress limited to Hedra domains. If the publisher cannot explain the metadata mismatch and origin, consider this suspicious and avoid installing until clarified.

Hedra Plugin for OpenClaw

AI video and image generation plugin for OpenClaw powered by Hedra. Generate talking avatars, videos from text prompts, and images — all from your agent.

Features

• Image generation — create images from text prompts with configurable aspect ratios and resolutions
• Video generation — text-to-video and image-to-video with optional start/end keyframes
• Talking avatars — lip-synced avatar videos from a portrait image + audio or text-to-speech
• Voice listing — browse available TTS voices for avatar generation
• Model listing — discover available Hedra models and their capabilities
• Credit tracking — check your Hedra credit balance

Requirements

• Hedra Creator plan or above
• Hedra API key from https://www.hedra.com/api-profile

Configuration

Set your API key in openclaw.json:

{
  "plugins": {
    "entries": {
      "hedra": {
        "enabled": true,
        "config": {
          "apiKey": "sk_h_your-key-here"
        }
      }
    }
  }
}

Or use the HEDRA_API_KEY environment variable.

Setting	Default	Description
apiKey		Hedra API key (falls back to HEDRA_API_KEY env var)
defaultVideoModel		Default model for video generation
defaultImageModel		Default model for image generation

Registered Tools

Tool	Description
hedra_generate_image	Generate images from text prompts
hedra_generate_video	Generate videos from text prompts, optionally with a start image
hedra_generate_avatar	Generate talking avatar videos from a portrait + audio/TTS
hedra_generation_status	Check generation status and get result URLs
hedra_list_models	List available Hedra AI models
hedra_list_voices	List available TTS voices for avatars
hedra_credits	Check credit balance

Usage Examples

Generate an image

"Generate a photo-realistic image of a mountain lake at sunset"

The agent calls hedra_list_models to choose the best image model, then hedra_generate_image with the prompt and returns the result URL.

Generate a video

"Create a 5 second video of ocean waves crashing on a beach"

The agent calls hedra_list_models to choose the best video model, then hedra_generate_video with the prompt and duration.

Create a talking avatar

"Make this portrait say 'Hello, welcome to our product demo'"

The agent calls hedra_list_voices to pick a voice, then hedra_generate_avatar with the portrait asset ID, TTS text, and voice ID.