← Back to Skills Marketplace
252
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install voice-picker
Description
Recommend the best SenseAudio voice for any scenario or emotion. Use when users ask which voice to use — e.g. "儿童故事播客用什么音色", "电商直播带货适合哪个声音", "我需要撒娇感的女声", "有没...
Usage Guidance
This skill appears to do what it says (map scenarios to SenseAudio voice IDs and optionally generate short TTS previews). However, the registry marks SENSEAUDIO_API_KEY as a required primary credential even though the SKILL.md says the API key is only needed for preview audio. Before installing: (1) only provide SENSEAUDIO_API_KEY if you intend to use the TTS preview feature — otherwise omit it so the agent cannot make network TTS calls; (2) ensure curl, jq, and xxd are installed if you plan to use previews; (3) be aware previews will create preview.json and preview_<VOICE_ID>.mp3 files in the agent's working directory — delete them if they contain sensitive text; (4) confirm the API key you provide is least-privileged and rotate/revoke it if you stop using the skill; (5) verify the SenseAudio homepage and API docs yourself (https://senseaudio.cn) if you need stronger assurance about data handling. The main unresolved issue is the mismatch between "required" credential metadata and the SKILL.md's assertion that the key is optional.
Capability Analysis
Type: OpenClaw Skill
Name: voice-picker
Version: 1.0.0
The skill is a legitimate voice recommendation and preview tool for the SenseAudio service. It uses a static lookup table to suggest voice IDs based on user scenarios and provides a standard shell command (using curl, jq, and xxd) to generate audio previews via the official senseaudio.cn API. No malicious behavior, data exfiltration, or obfuscation was detected.
Capability Assessment
Purpose & Capability
The skill's name/description (voice recommendation) matches the SKILL.md content and the listed voice library. However the registry metadata marks SENSEAUDIO_API_KEY as a required primary credential, while the SKILL.md explicitly states "No API key needed for recommendations; optionally generates a TTS preview sample." Requiring the API key by default is disproportionate to the stated core purpose (recommendations). The required binaries (curl, jq, xxd) are consistent with the optional preview feature.
Instruction Scope
SKILL.md instructions are narrowly scoped: mapping user descriptions to voice IDs, returning 1–3 recommendations, and — only if the user asks for a preview — calling SenseAudio's TTS endpoint. The runtime steps write preview.json and preview_<VOICE_ID>.mp3 files in the working directory. The instructions do not request unrelated files, other environment variables, or external endpoints beyond api.senseaudio.cn. Note: because previews use the API key and produce files on disk, the agent will perform network I/O and local file writes when previews are requested.
Install Mechanism
No install spec and no code files are present; this is an instruction-only skill. That is low-risk from an installation perspective (nothing is downloaded or written by an installer).
Credentials
Only one credential appears: SENSEAUDIO_API_KEY. That credential is appropriate for the optional TTS preview, but the registry's required.env / primaryEnv listing makes it seem mandatory even though the SKILL.md says it is optional. This over-declaration could lead users or agent deployments to supply a sensitive key when it isn't needed for the primary feature (recommendations). No other unrelated credentials are requested.
Persistence & Privilege
The skill is not always-enabled and does not modify other skills or system settings. It can be invoked by the user and (by default) can be invoked autonomously by the agent (normal behavior), but there is no indication it requests elevated or persistent system privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install voice-picker - After installation, invoke the skill by name or use
/voice-picker - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the SenseAudio Voice Picker skill.
- Instantly recommends the most suitable SenseAudio voice for any scenario or emotion, based on user input.
- Provides a clear voice library with plan-level breakdowns (Free, VIP, SVIP).
- Guides matching of user questions or keywords to recommended voice IDs with styles and typical use cases.
- Supports optional TTS preview: generate and offer MP3 samples for any recommended voice (API key required for this feature).
- Filters recommendations to only show voices accessible within the user's stated plan tier.
Metadata
Frequently Asked Questions
What is Voice Picker?
Recommend the best SenseAudio voice for any scenario or emotion. Use when users ask which voice to use — e.g. "儿童故事播客用什么音色", "电商直播带货适合哪个声音", "我需要撒娇感的女声", "有没... It is an AI Agent Skill for Claude Code / OpenClaw, with 252 downloads so far.
How do I install Voice Picker?
Run "/install voice-picker" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Voice Picker free?
Yes, Voice Picker is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Voice Picker support?
Voice Picker is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Voice Picker?
It is built and maintained by scikkk (@scikkk); the current version is v1.0.0.
More Skills