Dream LipSync

Video lip synchronization using LipSync 2.0 API. Automatically synchronizes audio with lip movements in videos. Powered by Dreamface - AI tools for everyone....

Security Scan

The skill's requests and instructions are coherent with a lip‑sync API plugin, but it uploads user media to a third‑party OSS endpoint and the package metadata/source are minimal — verify the provider and avoid uploading sensitive videos without review.

Purpose & Capability

Name and description (LipSync 2.0) align with the declared requirement (DREAMLIPSYNC_API_KEY) and the SKILL.md describes the expected API endpoints. Minor inconsistency: public branding links reference Dreamface/dreamfaceapp.com while the API endpoints use api.newportai.com; this can be legitimate but worth verifying the provider relationship.

Instruction Scope

Instructions require uploading local files to a provider OSS host (dreamapi-oss.oss-cn-hongkong.aliyuncs.com) and then calling async API endpoints. That means user video/audio files will be transmitted to the external storage/service; if you plan to process sensitive media this is a privacy risk. Otherwise instructions are narrowly scoped to file upload, task creation, and polling — no unrelated system files or extra env vars are referenced.

Install Mechanism

No install spec or code is included (instruction-only). This minimizes local installation risk because nothing is downloaded or executed by the skill itself.

Credentials

Only one credential is required (DREAMLIPSYNC_API_KEY), which is appropriate for an API service. Keep in mind the API key grants the skill access to the provider account (task creation, file access) so treat it as sensitive and scope/rotate appropriately.

Persistence & Privilege

Skill is not always-enabled and does not request elevated platform privileges. The SKILL.md shows an example openclaw config patch to store the API key in agent config; storing its own credential is normal but you should ensure the agent stores credentials securely.

Assessment

This skill appears to do what it says, but before installing: 1) Verify the API provider (api.newportai.com vs dreamfaceapp.com) and review their privacy/security policy. 2) Understand that local videos/audio are uploaded to a third‑party OSS endpoint (dreamapi-oss.oss-cn-hongkong.aliyuncs.com) — do not upload sensitive or private media unless you trust the provider. 3) Protect the DREAMLIPSYNC_API_KEY: only grant least privilege, rotate if exposed, and prefer a test key for initial trials. 4) The package has no code (instruction-only), so risks are limited to network/data disclosure; test with non-sensitive files first. 5) If you need higher assurance, ask the publisher for official docs or a homepage and confirm the relationship between Dreamface and NewportAI.

Dream LipSync 2.0 - Video Lip Synchronization

Synchronize lip movements in videos with audio using the LipSync 2.0 API.

Quick Start

1. Get API Key

Before using this skill, you need a DreamAPI API key. Visit https://api.newportai.com/api-reference/get-started to sign up and get your API key.

For more AI tools, please visit: https://tools.dreamfaceapp.com/home

2. Configure API Key

openclaw config patch --json '{"skills": {"entries": {"dream-lipsync": {"env": {"DREAMLIPSYNC_API_KEY": "your-api-key-here"}}}}}'```

### 3. Usage

#### Parameters:
- **srcVideoUrl**: Source video URL (mp4)
- **audioUrl**: Audio URL (mp3, wav)
- **videoParams** (optional): Video processing options
  - **video_width**: Output video width (0=keep original)
  - **video_height**: Output video height (0=keep original)
  - **video_enhance**: Face enhancement (0=no, 1=yes)

#### Request Format (Example):
```json
{
  "srcVideoUrl": "https://example.com/video.mp4",
  "audioUrl": "https://example.com/audio.mp3",
  "videoParams": {
    "video_width": 0,
    "video_height": 0,
    "video_enhance": 0
  }
}

API Details

1. Get Upload Policy (for local files)

Upload your local files to OSS first (get upload policy, then upload).

POST https://api.newportai.com/api/file/v1/get_policy

Request Body:

{
  "scene": "Dream-CN"
}

Response:

{
  "code": 0,
  "message": "success",
  "data": {
    "accessId": "LTAI5t...",
    "policy": "eyJ...",
    "signature": "G2...",
    "dir": "tmp/dream/2026-03-17/xxxxxx/",
    "host": "https://dreamapi-oss.oss-cn-hongkong.aliyuncs.com",
    "expire": "1732005888",
    "callback": "eyJ..."
  }
}

2. Upload File to OSS

Upload to the host URL with form data (policy, OSSAccessKeyId, signature, key, callback, file).

Uploaded file URL: {host}/{dir}{filename}

3. LipSync 2.0 API

POST https://api.newportai.com/api/async/lipsync/2.0

4. Polling for Result

POST https://api.newportai.com/api/getAsyncResult

Implementation Notes

• All API calls require Authorization header
• Local files must be uploaded to OSS first
• Tasks are async, poll for results
• Poll every 2-3 seconds, timeout ~60 seconds
• Status: 0=pending, 1=processing, 2=processing, 3=completed, 4=timeout
• video_enhance=1 improves face clarity