What makes Tencent VOD Intl. notable?

1.3K downloads. Trust evidence available

How should Tencent VOD Intl. be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

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

Tencent VOD Intl.

Tencent Cloud VOD (Video on Demand) command generation assistant. Must trigger whenever the user's request involves any VOD operation: [Upload] local/URL pull upload, expiration/SessionId/storage path; [Media Processing] transcode/TESHD/screenshot/sprite/enhance/real-person/drama/scene/remux/HLS/GIF

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.3k

Updated

Oct 10, 2026

Version

1.1.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.

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 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.3K downloadsadoption · observed Oct 10, 2026
Latest release: 1.1.3release · observed Aug 9, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s172dymwd68zz4gb81ansjp35x83k7pr:tencent-vod-intl

Install using `clawhub skill install s172dymwd68zz4gb81ansjp35x83k7pr:tencent-vod-intl` 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/tencent-mpaas-skills/tencent-vod-intl before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-tencent-mpaas-skills-tencent-vod-intl/snapshot"

Documentation

CLAWHUB

153,987 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: tencent-vod-intl
description: "Tencent Cloud VOD (Video on Demand) command generation assistant. Must trigger whenever the user's request involves any VOD operation: [Upload] local/URL pull upload, expiration/SessionId/storage path; [Media Processing] transcode/TESHD/screenshot/sprite/enhance/real-person/drama/scene/remux/HLS/GIF/adaptive bitrate/review/procedure; [Media Query] FileId query details/transcode/subtitles/cover/metadata; [AIGC] text2img/text2video/img2video (Kling/Hunyuan/Vidu/GG/GV/Hailuo/MJ/Qwen/SI/OG/Jimeng/Mingmou/OS/Seedance/PixVerse), LLM chat (GPT/Gemini models, streaming), scene AIGC/outfit change/image expansion/product image/custom elements; [AIGC Audio] text-to-sfx/video-to-sfx/text-to-music/BGM/ASMR (Kling/MiniMaxMusic/GL); [AIGC Token/Usage] token management, usage stats; [Search] name/semantic/knowledge base; [Image] super-res/denoise/enhance/understand; [Sub-app/Task] sub-app query, task status. Do NOT trigger: MPS operations, COS direct upload, live streaming."
metadata:
  version: "1.1.3"
---

# Tencent Cloud Video on Demand (VOD) Service

## Role Definition

You are a professional assistant for Tencent Cloud VOD (Video on Demand), helping users generate correct Python script commands.

## Output Specification

1. **Output commands only** — no explanations, no filler text
2. Command format: `python3 scripts/<script-name>.py [subcommand] [parameters]`
3. All scripts support `--dry-run` (simulate execution)
4. **Links output after task completion (pre-signed download links, playback URLs, etc.) must be presented in Markdown hyperlink format**, i.e. `[description](URL)` — must not be output as code blocks or plain text.

> 💰 **Cost Notice**: This Skill calls Tencent Cloud VOD services and will incur charges, including transcoding fees, AI processing fees, storage fees, etc. When a task has not yet returned a result, do not manually re-submit the request, as this will result in duplicate charges. For detailed pricing, refer to [Tencent Cloud VOD Pricing](https://cloud.tencent.com/document/product/266/2838). A cost notice **must** be given each time a **processing script** is called (transcoding/enhancement/screenshot/AIGC/image processing/knowledge base import, etc.); no notice is needed for query scripts (vod_describe_task/vod_describe_media/vod_search_media/vod_describe_sub_app_ids) or upload scripts (vod_upload/vod_pull_upload). **Before invoking any processing script, you must first restate the exact command to the user and obtain explicit confirmation ("Proceed?") before submission; when parameters are uncertain or for high-cost operations (e.g. AIGC video generation, long-video transcoding, batch image processing, knowledge base import), prefer running with `--dry-run` first to preview**. Users are also advised to configure budget alerts and monthly caps at the [Tencent Cloud Billing Center](https://console.cloud.tencent.com/expense) to prevent runaway spend.

Tencent Cloud's official Python SDK is used

_meta.json

{
  "ownerId": "kn70yhz47k5f2a22dsfdhthzqx83k6t0",
  "slug": "tencent-vod-intl",
  "version": "1.1.3",
  "publishedAt": 1786282114378
}

references/vod_aigc_audio.md

# vod_aigc_audio.py Reference

VOD AIGC audio generation task tool, based on the `CreateAigcAudioTask` API.
Supports text-to-sound-effect / video-to-sound-effect (Kling), text-to-music (MiniMaxMusic / GL(Google Lyria)).

## Parameters

### Basic Parameters

| Parameter | Type | Required | Description |
|------|------|------|------|
| `--model` | enum | ❌ | Model name: `Kling` (sound effect) / `MiniMaxMusic` / `GL` (music) |
| `--model-version` | string | ❌ | Model version; **recommended to leave unset for Kling** (uses the system default stable version, shown empty in doc examples); `MiniMaxMusic` supports `2.0/2.5/2.6/3.0`; `GL` supports `3.0-clip/3.0-pro` |
| `--scene-type` | enum | ❌ | Scene type: `sfx` (sound effect, Kling-only) / `music` (music, MiniMaxMusic/GL-only) |
| `--prompt` | string | ❌ | Description (prompt) of the audio to generate |

### Reference Video Parameters (video-to-sound-effect scenario)

| Parameter | Type | Required | Description |
|------|------|------|------|
| `--video-id` | string | ❌ | VOD FileId of the reference video |
| `--video-url` | string | ❌ | URL of the reference video |
| `--video-infos` | string | ❌ | JSON array of multiple reference videos, format: `[{"Type":"Url","Url":"..."}]`; mutually exclusive with `--video-id`/`--video-url` (single-file form takes precedence) |

### Reference Audio Parameters (e.g. generating music from an input audio)

| Parameter | Type | Required | Description |
|------|------|------|------|
| `--audio-id` | string | ❌ | VOD FileId of the reference audio |
| `--audio-url` | string | ❌ | URL of the reference audio |
| `--audio-infos` | string | ❌ | JSON array of multiple reference audios, format: `[{"Type":"Url","Url":"..."}]` |

### AdditionalParameters Convenience Parameters

The `AdditionalParameters` field of `CreateAigcAudioTask` is used to pass model-specific scenario parameters (as a JSON string). The script provides the following convenience parameters, which are automatically merged into the same JSON:

| Parameter | Type | Description |
|------|------|------|
| `--bgm-prompt` | string | BGM generation prompt (**video-to-sound-effect scenario, Kling**), merged as `AdditionalParameters.bgm_prompt` |
| `--asmr-mode` | enum(`true`/`false`) | Whether to enable ASMR mode (enhances detailed sound effects, good for highly immersive content), merged as `AdditionalParameters.asmr_mode` (boolean) |
| `--lyrics` | string | Lyrics content (**text-to-music scenario, MiniMaxMusic**), merged as `AdditionalParameters.lyrics` |
| `--additional-parameters` | string | Reserved field, raw JSON string passthrough, merged with the convenience parameters above (convenience params take precedence) |

### Output Configuration Parameters

| Parameter | Type | Required | Description |
|------|------|------|------|
| `--output-storage-mode` | enum | ❌ | Storage mode: `Permanent` / `Temporary` (default) |
| `--output-media-name` | string | ❌ | Output file name, up to 64 characters |
| `--output-cla

references/vod_aigc_chat.md

# vod_aigc_chat — Detailed Parameters and Examples
> This file is generated by splitting references, corresponding script: `scripts/vod_aigc_chat.py`

### ⚠️ Common Parameter Errors

| Incorrect Usage | Correct Usage | Description |
|---------|---------|------|
| `--message "A" --message "B"` | `--messages '[{"role":"user","content":"A"},...]'` | For multi-turn conversations, use `--messages` JSON array; do not repeat `--message` |

## Parameter Reference
### General Parameters

| Parameter | Type | Description |
|------|------|------|
| `--token` | string | AIGC API Token (can also be set via environment variable `TENCENTCLOUD_VOD_AIGC_TOKEN`) |
| `--model` / `-m` | string | Model to use (default `gpt-5.1`, see supported models list) |
| `--json` | flag | Output full response in JSON format (only valid for `chat` subcommand; `stream` subcommand uses SSE streaming output, this parameter has no effect) |
| `--dry-run` | flag | Preview request body without sending the request |
| `--timeout` | int | Request timeout in seconds (default 120) |
| `--output-file` | path | Save response to specified file path (`chat` subcommand saves full response JSON; `stream` subcommand saves plain text content) |
| `--no-usage` | flag | Do not display token usage statistics |

### Message Content Parameters

| Parameter | Type | Required | Description |
|------|------|------|------|
| `--message` / `-q` | string | ✅* | User message content (simple single-turn conversation) |
| `--messages` | JSON | ✅* | Complete messages JSON array (multi-turn conversation, mutually exclusive with `--message`) |
| `--system` / `-s` | string | - | System prompt (sets AI role/persona; when used together with `--messages`, this parameter is ignored — system should be embedded in the messages JSON) |

### Multimodal Parameters

| Parameter | Type | Description |
|------|------|------|
| `--image-url` | string | Image URL (supported by both OpenAI and Gemini, size limit 70MB) |
| `--audio-base64` | string | Base64-encoded audio data (Gemini only) |
| `--audio-format` | mp3/wav | Audio format (default mp3) |
| `--file-url` | string | File/video URL (Gemini only, size limit 70MB) |
| `--file-name` | string | File name (used together with `--file-url`) |

### Generation Control Parameters

| Parameter | Type | Description |
|------|------|------|
| `--temperature` / `-t` | float | Output randomness (0~2; lower = more precise, higher = more creative; if not specified, server default is used, typically 0.7) |
| `--max-tokens` | int | Maximum number of tokens to generate |
| `--thinking` | flag | Enable reasoning/thinking mode (CoT); **Note: not supported by gpt-5.1/5.2/4o — a warning will be printed and the parameter will be automatically ignored** |
| `--reasoning-effort` | string | Thinking level: `none`/`minimal`/`low`/`medium`/`high`/`xhigh` |
| `--response-format` | string | Output format: `text` (default) / `json` (JSON object) / `json_schema` (same as `json`, fallback is json_object; f

references/vod_aigc_image.md

# vod_aigc_image — Detailed Parameters and Examples
> This file is generated by splitting references, corresponding script: `scripts/vod_aigc_image.py`

### ⚠️ Common Parameter Errors

| Incorrect Usage | Correct Usage | Description |
|---------|---------|------|
| `--model hunyuan-3.0` | `--model Hunyuan --model-version 3.0` | Model name and version number are separate |
| `--model vidu-q2` or `--model vidu` | `--model Vidu --model-version q2` | **Model name must be capitalized (`Vidu`), version number uses a separate `--model-version q2`** |
| `--aspect-ratio 16:9` | `--output-aspect-ratio 16:9` | Image generation output parameters use the `output-` prefix |
| `--resolution 2K` | `--output-resolution 2K` | Image generation resolution parameters use the `output-` prefix |
| `--class-id 10` | `--output-class-id 10` | **Image generation output class ID must use `--output-class-id`, not `--class-id`** |
| `--file-ids id1,id2` | `--file-infos '[{"Type":"File","FileId":"id1"}]'` | Multiple reference images use `--file-infos` JSON array |
| `--person-generation Disallowed` | `--output-person-generation Disallowed` | Disabling person generation uses the `output-` prefix |
| `--num-images 4` or `-n 4` | `--output-image-count 4` | **Multi-image output (OG 1-8, Kling 1-9)**; uses the `output-` prefix |
| `--format png` | `--output-format png` | **Specify output format (OG)**: `jpeg`/`png`; uses the `output-` prefix |
| `--mask-url ...` or `--mask-file-id ...` | `--file-infos '[{"Type":"File","FileId":"src"},{"Type":"File","FileId":"mask","ReferenceType":"mask"}]'` | **OG mask editing**: first image is the source to edit, second is the mask (`ReferenceType="mask"`) |

## Parameter Description

### General Parameters

| Parameter | Type | Description |
|------|------|------|
| `--sub-app-id` | int | Sub-application ID (can also be set via environment variable `TENCENTCLOUD_VOD_SUB_APP_ID`) |
| `--region` | string | Tencent Cloud region (default: `ap-guangzhou`) |
| `--json` | flag | JSON format output |
| `--dry-run` | flag | Only prints request parameter preview without sending the request |

### create Parameters (Create Image Generation Task)

#### Model Parameters (Required)

| Parameter | Type | Required | Description |
|------|------|------|------|
| `--model` | string | ✅ | Model name (Hunyuan/Qwen/Vidu/Kling/MJ/GG) |
| `--model-version` | string | - | Model version (uses default version if not specified) |

#### Prompt Parameters

| Parameter | Type | Required | Description |
|------|------|------|------|
| `--prompt` | string | ✅* | Prompt for generating the image (required when no reference image is provided) |
| `--negative-prompt` | string | - | Prompt to prevent the model from generating certain content (negative prompt) |
| `--enhance-prompt` | string | - | Whether to automatically optimize the prompt (Enabled/Disabled) |

#### Reference Image Parameters

| Parameter | Type | Required | Description |
|------|------|------|------|
| `--file-id`

Github ReposUpdated 1d 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.