← Back to Skills Marketplace
59
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install senseaudio-floating-audio-assistant
Description
Use when the user wants to open, stop, configure, debug, or package the SenseAudio floating audio assistant in AudioClaw, including system-audio subtitles, b...
Usage Guidance
This package appears coherent and implements what it claims: macOS overlay + SenseAudio integration. Before installing, do the following: (1) Ensure you trust the SenseAudio service (api.senseaudio.cn) because live TTS will send your API key there; the smoke script only contacts SenseAudio when --live-tts is used. (2) Inspect the external workspace tools referenced by TOOL_DIR (workspace/tools/realtime_interpreter) — the start/stop/runner scripts that actually perform capture/overlay are not included in this upload and could perform arbitrary actions. (3) Provide the SENSEAUDIO_API_KEY (or AUDIOCLAW_ASR_API_KEY) via your runtime environment or workspace .env; the scripts will check for but not leak the key. (4) Be aware the skill will run swiftc (compile a native overlay) and execute shell scripts that alter macOS audio routing; run in a safe/testing environment first if you are unsure. Overall, the skill is internally consistent but verify the external toolchain before execution.
Capability Analysis
Type: OpenClaw Skill
Name: senseaudio-floating-audio-assistant
Version: 1.0.0
The skill bundle is a legitimate management interface for a macOS audio assistant integration. It provides wrapper scripts (e.g., start-senseaudio-floating-audio-assistant.sh) to control an external audio processing toolchain, manage macOS audio routing via SwitchAudioSource, and interact with the SenseAudio API (api.senseaudio.cn) for ASR and TTS. The bundle includes robust diagnostic tools like doctor-senseaudio-floating-audio-assistant.sh and senseaudio_api_smoke.py, which specifically check for the presence of required dependencies and ensure that sensitive credentials are not accidentally exposed or printed. No evidence of malicious intent, data exfiltration, or unauthorized persistence was found.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description, required binaries (swiftc, SwitchAudioSource, python3, bash), and required env vars (SENSEAUDIO_API_KEY / AUDIOCLAW_ASR_API_KEY) align with a macOS audio-capture, overlay, ASR/TTS/music workflow. The brew install of switchaudio-osx (providing SwitchAudioSource) is proportionate.
Instruction Scope
SKILL.md and scripts instruct the agent to run local wrapper scripts and a diagnostic Python smoke test. Scripts read workspace/.env for API key presence and may perform an optional live TTS probe that sends the API key to SenseAudio endpoints when --live-tts is used. Most runtime actions are delegated to a separate tools/realtime_interpreter directory (start/stop/runner scripts) which is expected but not included in the package — review those external tool scripts before running to verify behavior.
Install Mechanism
Single brew formula (switchaudio-osx) is specified to provide SwitchAudioSource. This is a standard, low-risk install mechanism on macOS.
Credentials
The skill requires only SenseAudio-related credentials (SENSEAUDIO_API_KEY, AUDIOCLAW_ASR_API_KEY) which are appropriate for ASR/TTS/music features. The SKILL.md and scripts explicitly avoid printing keys and the smoke script only performs network calls to SenseAudio endpoints when requested.
Persistence & Privilege
always is false and the skill does not request permanent system-wide presence or modify other skills. It runs local scripts and expects to be invoked by the agent; this is normal for an integration skill.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install senseaudio-floating-audio-assistant - After installation, invoke the skill by name or use
/senseaudio-floating-audio-assistant - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of SenseAudio Floating Audio Assistant for AudioClaw.
- Enables macOS floating audio assistant for live subtitles, ASR/translation, TTS of copied text, music generation, and multi-output audio routing.
- Provides scripts to start/stop the assistant, check system dependencies, manage recent projects, and perform health checks.
- Integrates with SenseAudio API for accurate ASR, translation, and TTS; supports configuration of source/target languages and TTS voice.
- Requires macOS, BlackHole 2ch, Multi-Output Device (configured via Audio MIDI Setup), SwitchAudioSource, python3, bash, and swiftc.
- Includes troubleshooting guides, diagnostic scripts, and templates for project organization and music generation.
- Designed for seamless use with AudioClaw and external agent integration, without exposing sensitive credentials in logs or output.
Metadata
Frequently Asked Questions
What is senseaudio-floating-audio-assistant?
Use when the user wants to open, stop, configure, debug, or package the SenseAudio floating audio assistant in AudioClaw, including system-audio subtitles, b... It is an AI Agent Skill for Claude Code / OpenClaw, with 59 downloads so far.
How do I install senseaudio-floating-audio-assistant?
Run "/install senseaudio-floating-audio-assistant" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is senseaudio-floating-audio-assistant free?
Yes, senseaudio-floating-audio-assistant is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does senseaudio-floating-audio-assistant support?
senseaudio-floating-audio-assistant is cross-platform and runs anywhere OpenClaw / Claude Code is available (macos).
Who created senseaudio-floating-audio-assistant?
It is built and maintained by KkZz1225 (@kkzz1225); the current version is v1.0.0.
More Skills