← Back to Skills Marketplace
212
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install vociemaster
Description
专业级 AI 短视频配音助手，支持多角色音色映射、自动语速调节及 BGM 建议。
Usage Guidance
This skill appears to do what it says: it generates TTS via SenseAudio and uses jq/curl/ffmpeg to build requests and produce/concatenate audio. Before installing, review helper.py (it will run locally and make network calls to https://api.senseaudio.cn), keep your SENSEAUDIO_API_KEY secret and only provide that key (no other credentials are needed), and consider running the skill in an isolated workspace if you have low tolerance for third‑party network activity. Confirm you are comfortable sending your scripts/text to the SenseAudio service and check quota/rate limits. If you need higher assurance, ask for the full helper.py review or run it in a sandbox first.
Capability Analysis
Type: OpenClaw Skill
Name: vociemaster
Version: 1.0.1
The VoiceMaster skill bundle is a legitimate AI dubbing assistant that interfaces with the SenseAudio TTS API. The included Python script (helper.py) handles API requests, hex-to-binary audio conversion, and file concatenation using ffmpeg in a secure manner. The instructions in SKILL.md are well-structured, emphasizing user confirmation for script drafts and proper handling of API keys without any signs of prompt injection or malicious intent.
Capability Assessment
Purpose & Capability
Name/description (短视频配音) match the declared needs: one API key (SENSEAUDIO_API_KEY) and the binaries curl, jq, ffmpeg used for calling the TTS API, constructing JSON, and audio concatenation/processing. No unrelated credentials or surprising binaries are requested.
Instruction Scope
SKILL.md stays on‑topic: it validates the API key, produces editable drafts before generating audio, splits multi‑role scripts into per‑role TTS calls, and instructs concatenation of segments. It does not instruct reading unrelated system files or exfiltrating data to unexpected endpoints; network calls are targeted to the documented SenseAudio API endpoint.
Install Mechanism
No install spec; the skill is instruction‑only (plus a helper.py included). No remote downloads or package installs are requested, so there is low install risk. The included helper.py will be executed locally and is responsible for API calls and file I/O.
Credentials
Only SENSEAUDIO_API_KEY is required, which is proportional for a TTS integration. The SKILL.md explicitly advises not to hardcode the key. No other secrets or unrelated env vars are requested.
Persistence & Privilege
always is false and the skill does not request system‑wide persistence or modification of other skills. disable-model-invocation is false (normal), so the agent could invoke the skill autonomously per platform rules.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install vociemaster - After installation, invoke the skill by name or use
/vociemaster - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
VoiceMaster v1.0.1 Changelog
- Added "draft dialogue" workflow: now supports generating editable short video scripts before TTS when user input is incomplete, only provides a theme, or requests a draft first.
- Introduced multiple short video dialogue templates for various scenarios (story, chat, pitch, knowledge, suspense, monologue), with clear rules and recommended editing steps.
- Changed API key environment variable from TTS_API_KEY to SENSEAUDIO_API_KEY; startup check updated accordingly.
- Updated execution flow: will not synthesize audio until user confirms or edits the draft script.
- Improved input handling: detects non-script/unclear inputs, generates dialogue structure, and guides user confirmation.
- Removed sample and documentation files (README.MD, smoke-test.txt) for a cleaner project structure.
v1.0.0
VoiceMaster 1.0.0
- 首次发布，支持基于 SenseAudio API 的短视频 AI 配音生成，输出直用 MP3 文件。
- 支持多角色音色自动映射、智能语速调节、角色台词识别及片段合成。
- 自动进行文本分段，保障配音请求高效且稳定，大段文本可分段并合并输出。
- 内置多种音色与风格映射，遇账号权限受限时可自动降级并明确提示用户。
- 详细输出配音用参、降级信息、分段与合并状态、错误回执。
- 配音完成后智能推荐背景音乐方向，附镜头节奏与混音建议。
Metadata
Frequently Asked Questions
What is vociemaster?
专业级 AI 短视频配音助手，支持多角色音色映射、自动语速调节及 BGM 建议。 It is an AI Agent Skill for Claude Code / OpenClaw, with 212 downloads so far.
How do I install vociemaster?
Run "/install vociemaster" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is vociemaster free?
Yes, vociemaster is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does vociemaster support?
vociemaster is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created vociemaster?
It is built and maintained by 曹广雨 (@xiaocaijic); the current version is v1.0.1.
More Skills