← Back to Skills Marketplace
249
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install senseaudio-voice-broadcast
Description
Turn plain text into character-style TTS scripts for narration, companion-style voice messages, emotional comfort audio, and expressive spoken responses. Use...
Usage Guidance
This skill appears to do what it says (rewrite text for persona-driven TTS and call a SenseAudio API) and includes a small local script to perform the call. Before installing: 1) be aware it will send text to an external service (https://api.senseaudio.cn) — do not send sensitive personal, financial, or secret information without confirming privacy terms; 2) the package metadata fails to declare the required SENSEAUDIO_API_KEY environment variable — expect to provide that key yourself and verify you trust the service and the skill owner; 3) there is no homepage or known publisher listed — consider asking the publisher for provenance or using an alternative TTS provider you trust; 4) if you are concerned about autonomous network calls, restrict the skill's permissions or avoid providing the API key so it can only produce offline scripts. If the registry entry were corrected to declare SENSEAUDIO_API_KEY and included verifiable publisher info/homepage, my confidence would increase.
Capability Analysis
Type: OpenClaw Skill
Name: senseaudio-voice-broadcast
Version: 1.0.1
The skill is a legitimate tool for generating persona-driven text-to-speech (TTS) scripts and audio files using the SenseAudio API. The core logic in `scripts/senseaudio_tts.py` uses standard Python libraries to perform API requests and handle audio data (including downloading from URLs provided by the API), while `SKILL.md` provides clear, task-aligned instructions for the AI agent without any signs of prompt injection or malicious intent.
Capability Assessment
Purpose & Capability
The name, description, SKILL.md, reference docs, and included Python script all consistently implement persona-driven TTS and audio generation via the SenseAudio service. However, the registry metadata lists no required environment variables while the skill and docs clearly expect a SENSEAUDIO_API_KEY — a mismatch that reduces transparency.
Instruction Scope
Runtime instructions stay on-topic: rewrite text for speech, produce style notes, and (when requested) call the bundled script to POST to the SenseAudio API and save audio locally. The script only reads the provided text or a text file, the API key, and writes the output audio file; it may also follow an audio_url returned by the service to download audio. It does not instruct reading unrelated system files or other credentials.
Install Mechanism
No install spec (instruction-only) and a small included Python script — nothing is downloaded at install time. This is low-risk compared to remote installers. The script uses standard library urllib and writes files under user-specified output paths.
Credentials
The skill requires an API key to operate (SENSEAUDIO_API_KEY or --api-key) but the registry's required env vars list is empty. Requesting a single service API key is proportionate for a remote TTS integration, but the metadata omission and lack of a homepage/known publisher make it harder to verify the remote service and key handling.
Persistence & Privilege
Skill does not request always:true or any persistent elevated privileges. It does not modify other skills or global agent configuration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install senseaudio-voice-broadcast - After installation, invoke the skill by name or use
/senseaudio-voice-broadcast - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Updated documentation resource links to use relative paths (e.g., `references/voice-broadcast-templates.md`) instead of absolute paths.
- No changes to code or workflow; only documentation/link corrections.
v1.0.0
Initial release of character-voice-broadcast skill:
- Transforms plain text into persona-driven TTS scripts for narration, emotional companionship, greetings, and expressive character responses.
- Guides selection of appropriate speaking roles (narrator, companion, character, comfort voice, etc.) and emotional tones to match user requests.
- Provides clear workflow for rewriting text into natural, spoken language optimized for TTS engines.
- Outputs both final spoken script and TTS style control notes; supports direct SenseAudio TTS invocation when audio output is needed.
- Includes detailed rules on emotional matching, factual retention, language defaults, and persona stability.
- Offers reference templates and SenseAudio integration resources for streamlined speech generation.
Metadata
Frequently Asked Questions
What is SenseAudio?
Turn plain text into character-style TTS scripts for narration, companion-style voice messages, emotional comfort audio, and expressive spoken responses. Use... It is an AI Agent Skill for Claude Code / OpenClaw, with 249 downloads so far.
How do I install SenseAudio?
Run "/install senseaudio-voice-broadcast" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is SenseAudio free?
Yes, SenseAudio is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does SenseAudio support?
SenseAudio is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created SenseAudio?
It is built and maintained by JSinBUPT (@jsinbupt); the current version is v1.0.1.
More Skills