← Back to Skills Marketplace
298
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install persona-voice
Description
在 chatgpt / claw 与飞书 / lark 机器人场景中，根据随机或指定人格生成明显带有人格风格的短回复，并通过 senseaudio tts 合成语音，再以飞书原生语音条发送。支持文字输入和音频输入；音频输入时先调用 senseaudio asr。适用于飞书人格陪伴、随机人格语音回复、角色化语音机器...
Usage Guidance
This skill appears to do what it says (generate personaized replies, send TTS audio to Feishu using SenseAudio). Before installing: 1) be aware the package actually requires FEISHU_APP_ID, FEISHU_APP_SECRET and SENSEAUDIO_API_KEY (the registry metadata incorrectly lists none) and will attempt to load .env.local/.env in the skill folder — do not store secrets in the repository. 2) Understand audio (user voice) will be uploaded to SenseAudio and audio files uploaded to Feishu — review SenseAudio and Feishu privacy/policy and ensure you trust those services. 3) Ensure ffmpeg is available in the runtime or set FFMPEG_PATH; the code runs ffmpeg via subprocess. 4) If you require transparency to end users, note the SKILL enforces hiding internal rules (it instructs the model not to reveal it's using random personas). 5) Run the skill in a limited/test environment first (with test credentials) and review logs/requests to confirm behavior. If you need, ask the maintainer to correct the registry metadata to list the required env vars and binaries.
Capability Analysis
Type: OpenClaw Skill
Name: persona-voice
Version: 1.1.0
The skill bundle provides a legitimate integration for generating persona-based voice replies on Feishu/Lark using SenseAudio's ASR and TTS services. It handles sensitive credentials (Feishu and SenseAudio API keys) but uses them exclusively to communicate with the official endpoints (open.feishu.cn and api.senseaudio.cn). The use of subprocess to call ffmpeg for audio conversion in feishu_api.py is implemented safely using argument lists, and the agent instructions in SKILL.md are focused on maintaining persona consistency and do not contain malicious prompt injection or unauthorized data access.
Capability Assessment
Purpose & Capability
The skill name/description (persona voice for Feishu/Lark using SenseAudio TTS/ASR) matches the code and instructions. However the registry metadata claims no required env vars or binaries while the SKILL.md and code clearly require FEISHU_APP_ID, FEISHU_APP_SECRET, SENSEAUDIO_API_KEY and recommend python3/ffmpeg/requests. This metadata mismatch is an incoherence and could mislead users about what secrets and tools are needed.
Instruction Scope
SKILL.md and the scripts limit actions to: generating persona prompts, calling SenseAudio ASR/TTS endpoints, converting audio with ffmpeg, uploading to Feishu via its API, and reading/writing local skill state (.env, data/, outputs/). The instructions do not attempt to read arbitrary system files or unrelated credentials. One behavioral note: the guidance explicitly instructs the model not to disclose internal rules or that a persona was randomly chosen — this is a functional design choice (deceptive behaviour toward end users) but not a technical incoherence.
Install Mechanism
There is no install spec (instruction-only / script bundle). Code dependencies are minimal (requests in requirements.txt) and no external downloads or installers are performed. This is low install risk.
Credentials
The code requires FEISHU_APP_ID, FEISHU_APP_SECRET and SENSEAUDIO_API_KEY (and optionally FFMPEG_PATH or having ffmpeg on PATH). Those credentials are proportionate to the stated Feishu + SenseAudio integration. The concern is the registry metadata declaring none required — an important mismatch. Also the code will auto-load .env.local and .env from the skill root, so secrets placed there could be read; users should avoid committing secrets into repo files.
Persistence & Privilege
The skill does not request 'always: true' and does not modify other skills or system-wide agent settings. It writes only to its own data/ and outputs/ directories. It can make outbound network calls to SenseAudio and Feishu, which is expected for its purpose.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install persona-voice - After installation, invoke the skill by name or use
/persona-voice - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
persona-voice v1.0.0
- Reworked skill for integration with Feishu/Lark bots: generates persona-based voice replies and delivers as native Feishu voice messages.
- Switched ASR and TTS exclusively to SenseAudio; removed AudioZen LLM dependency.
- Simplified configuration: only Feishu and SenseAudio API keys required as environment variables.
- New command-line workflow via scripts/main.py, supporting persona prompt generation, audio transcription, and direct Feishu audio sending.
- Only 3 public/free personas and voice options retained for this version.
- Removed previous install-time key setup and unrelated scripts.
v1.0.1
- Switched to a standalone Python script workflow; removed external skill registry dependency.
- Added scripts for LLM (AudioZen), ASR, TTS (SenseAudio), key setup, and persona voice orchestration.
- Introduced `.env`-based install-time API key management via setup script.
- Documentation and CLI usage now fully in Chinese with updated quickstart.
- Removed legacy skill.json; all configuration handled by scripts and local files.
- Persona and voice management improved; all configurable via JSON and CLI switches.
v1.0.0
Initial release of persona-voice!
- Generate short, persona-driven voice replies (≤20 seconds) from text or audio input.
- Randomly select or manually specify persona and voice style.
- Integrates OpenAI-compatible LLM for text and SenseAudio for ASR/TTS.
- Simple CLI to input text/audio and output personalized speech.
- Supports custom voice IDs and includes a starter pool of 13 unique personas.
- Extensive documentation provided in SKILL.md for setup and usage.
Metadata
Frequently Asked Questions
What is persona-voice?
在 chatgpt / claw 与飞书 / lark 机器人场景中，根据随机或指定人格生成明显带有人格风格的短回复，并通过 senseaudio tts 合成语音，再以飞书原生语音条发送。支持文字输入和音频输入；音频输入时先调用 senseaudio asr。适用于飞书人格陪伴、随机人格语音回复、角色化语音机器... It is an AI Agent Skill for Claude Code / OpenClaw, with 298 downloads so far.
How do I install persona-voice?
Run "/install persona-voice" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is persona-voice free?
Yes, persona-voice is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does persona-voice support?
persona-voice is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created persona-voice?
It is built and maintained by HeiMaoM (@hei-maom); the current version is v1.1.0.
More Skills