โ Back to Skills Marketplace
Video Dubbing
by
Newaiguy
ยท GitHub โ
ยท v1.2.0
ยท MIT-0
157
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install voxcpm-chinese-dubbing
Description
๐ฏ **ๅฏไธไฝฟ็จVoxCPM็ไธญๆ้
้ณๆ่ฝ** - ๅค่ฏญ่ง้ขไธ้ฎไธญๆ้
้ณ๏ผๆฏๆ็กฌๅญๅนๆฃๆตใๆญ็น็ปญไผ ใๆบ่ฝBGMใ่งฆๅๅบๆฏ๏ผ(1) ็จๆท้่ฆ็ปๅค่ฏญ่ง้ข้
้ณ (2) ่ง้ข็ฟป่ฏ้ๆฑ (3) ๅค่ฏญ่จๅ
ๅฎนๆฌๅฐๅ
Usage Guidance
Before installing or running: 1) Treat TRANSLATE_API_KEY as sensitive โ confirm you trust the default external endpoint (https://api.siliconflow.cn) or change it to a provider you control. 2) Inspect and edit scripts/upload_bilibili.py: it reads credentials from a hardcoded Windows path and uses absolute ffmpeg paths โ remove or modify this script if you do not want it to access local secrets or upload automatically. 3) If you don't need Bilibili upload functionality, delete upload_bilibili.py from the package. 4) Run the tool in an isolated environment (container or VM) and supply configuration via config.json or environment variables rather than relying on defaults. 5) Verify VoxCPM model installation location (VOXCPM_DIR) and do not place secrets in predictable paths. If any behavior is unclear, ask the skill author to explain why local credential paths are used and to provide a safe configuration option.
Capability Analysis
Type: OpenClaw Skill
Name: voxcpm-chinese-dubbing
Version: 1.2.0
The skill bundle provides a legitimate and functional workflow for automated video dubbing using Whisper for transcription, SiliconFlow APIs for translation/vision, and VoxCPM for text-to-speech. The scripts (dubbing.py, add_bgm.py, and upload_bilibili.py) use standard libraries and subprocess calls to ffmpeg for media processing. While upload_bilibili.py contains hardcoded local file paths (e.g., 'D:/openclaw_workspace/credentials/bilibili.json'), these appear to be non-portable development artifacts rather than malicious indicators. No evidence of data exfiltration, unauthorized remote control, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
The main scripts (dubbing, add_bgm) and SKILL.md align with a video-dubbing/TTS workflow and require a translation API key and a VoxCPM model directory; however the registry metadata claims no required env vars while SKILL.md and the scripts expect TRANSLATE_API_KEY and VOXCPM_DIR. That mismatch between declared registry requirements and the runtime configuration is inconsistent and should be clarified.
Instruction Scope
SKILL.md and scripts perform typical tasks for the stated purpose (whisper transcription, translation API calls, TTS, ffmpeg processing). However scripts/dubbing.py and upload_bilibili.py access system files and make network calls: upload_bilibili.py loads credentials from a hardcoded absolute path (D:/openclaw_workspace/credentials/bilibili.json) and invokes a hardcoded ffmpeg path (E:/ImageMagick.../ffmpeg.exe). Those file reads and absolute-path accesses are outside the core dubbing purpose and represent scope creep (access to local credential stores).
Install Mechanism
There is no automated install spec (instruction-only). The README/SKILL.md instructs installing Python packages and cloning VoxCPM โ reasonable and proportionate for a local TTS/transcription tool. Nothing in the install instructions downloads arbitrary executables from unknown servers.
Credentials
The runtime expects TRANSLATE_API_KEY and VOXCPM_DIR (declared in SKILL.md and used in scripts) which are reasonable. But upload_bilibili.py reads Bilibili credentials from a hardcoded system path not declared as required, and also references absolute local tools; these imply the package expects access to unrelated secrets on the host. The skill also defaults API endpoints to api.siliconflow.cn โ users should verify trustworthiness of that external service before supplying keys.
Persistence & Privilege
The skill does not request always:true and has no install hooks that would force persistent system presence. It is instruction-only plus included scripts; autonomous invocation is allowed by default (normal), but there is no evidence of the skill attempting to modify other skills or system-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install voxcpm-chinese-dubbing - After installation, invoke the skill by name or use
/voxcpm-chinese-dubbing - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.0
voxcpm-chinese-dubbing 1.2.0 Changelog
- Version bump to 1.2.0 without any file changes or documentation updates.
- No new features, fixes, or modifications detected in this release.
v1.1.0
**config/manifest/unified config support, vision API integration**
- Added manifest.json and unified `SKILL.md` to include standard field definitions (credentials, endpoints, environment variable mapping).
- Introduced Vision API integration for hard subtitle detection, now configurable in both environment variables and config files.
- Expanded config.example.json to support vision parameters.
- All configuration items can now be overridden by environment variables; added clear documentation for default values and override priority.
- Updated documentation structure for clarity on external calls, API endpoints, and required credentials.
v0.1.0
Initial release of "voxcpm-chinese-dubbing" โ the only Chinese dubbing skill using VoxCPM.
- One-click Chinese dubbing for foreign language videos, with support for hard subtitle detection, breakpoint resume, and intelligent BGM.
- Integrates OpenAI Whisper for transcription, Tencent Hunyuan MT for translation, and VoxCPM TTS for voice synthesis.
- Provides a streamlined workflow covering transcription, translation, TTS grouping, subtitle generation, and GPU-accelerated video merging.
- Includes scripts for main dubbing, BGM addition, and Bilibili uploading; flexible configuration and environment variable support.
- Outputs both dubbed video and Chinese subtitle files; optimizes audio matching for high fidelity.
- Comprehensive documentation for installation, configuration, advanced usage, and troubleshooting.
Metadata
Frequently Asked Questions
What is Video Dubbing?
๐ฏ **ๅฏไธไฝฟ็จVoxCPM็ไธญๆ้ ้ณๆ่ฝ** - ๅค่ฏญ่ง้ขไธ้ฎไธญๆ้ ้ณ๏ผๆฏๆ็กฌๅญๅนๆฃๆตใๆญ็น็ปญไผ ใๆบ่ฝBGMใ่งฆๅๅบๆฏ๏ผ(1) ็จๆท้่ฆ็ปๅค่ฏญ่ง้ข้ ้ณ (2) ่ง้ข็ฟป่ฏ้ๆฑ (3) ๅค่ฏญ่จๅ ๅฎนๆฌๅฐๅ. It is an AI Agent Skill for Claude Code / OpenClaw, with 157 downloads so far.
How do I install Video Dubbing?
Run "/install voxcpm-chinese-dubbing" in the OpenClaw or Claude Code chat to install it in one step โ no extra setup required.
Is Video Dubbing free?
Yes, Video Dubbing is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Video Dubbing support?
Video Dubbing is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Video Dubbing?
It is built and maintained by Newaiguy (@newaiguy); the current version is v1.2.0.
More Skills