← 返回 Skills 市场
173
总下载
0
收藏
0
当前安装
8
版本数
在 OpenClaw 中安装
/install kai-minimax-tts
功能描述
Generate voice audio and transcribe speech using MiniMax TTS API. Use when responding with voice or transcribing audio files.
使用说明 (SKILL.md)
Kai MiniMax TTS
Generate voice audio using MiniMax TTS.
Setup
Add to ~/.openclaw/openclaw.json:
{
"skills": {
"entries": {
"kai-minimax-tts": {
"enabled": true,
"env": {
"MINIMAX_API_KEY": "your_key_here"
}
}
}
}
}
Usage
Generate voice (English):
bash {baseDir}/scripts/kai_tts.sh --speak "Hello" en
Generate voice (Spanish):
bash {baseDir}/scripts/kai_tts.sh --speak "Hola" es
Transcribe audio:
bash {baseDir}/scripts/kai_tts.sh --transcribe /path/to/audio.ogg
Output Files
- Voice:
$WORKSPACE/Kai.mp3 - Transcript:
$WORKSPACE/latest_from_blaze.txt
Customization
Set custom workspace:
"env": { "KAI_MINIMAX_WORKSPACE": "/custom/path" }
Set custom voice IDs:
"env": {
"KAI_ENGLISH_VOICE_ID": "voice_id",
"KAI_SPANISH_VOICE_ID": "voice_id"
}
安全使用建议
This skill appears to do exactly what it says: it sends the text you provide to MiniMax's API (https://api-uw.minimax.io) using the MINIMAX_API_KEY and writes an MP3 and a transcript into a workspace directory. Before installing: 1) Ensure the MINIMAX_API_KEY you provide is only for the intended MiniMax service and that you trust that endpoint. 2) Confirm the whisper binary on your system is the implementation you expect (local vs. a wrapper that might upload audio). 3) Be aware output files overwrite fixed names (Kai.mp3 and latest_from_blaze.txt) in the skill workspace; customize KAI_MINIMAX_WORKSPACE if you want a different path. 4) If you need stricter isolation, run the script in a controlled environment since it performs network I/O (to the TTS API) and writes files locally.
功能分析
Type: OpenClaw Skill
Name: kai-minimax-tts
Version: 1.0.7
The skill provides legitimate text-to-speech and transcription functionality using the MiniMax API and the Whisper utility. The script `scripts/kai_tts.sh` correctly implements the described features, and while it lacks robust input sanitization for the shell commands and JSON payloads, these appear to be unintentional coding flaws rather than malicious backdoors.
能力评估
Purpose & Capability
Name/description, required env var (MINIMAX_API_KEY), and required binaries (curl, xxd, whisper) align with a TTS + transcription skill. The script calls a MiniMax API endpoint and uses whisper locally for transcription—these requirements are expected for this functionality.
Instruction Scope
SKILL.md and the included script stick to the stated tasks: generating audio via the MiniMax API and transcribing via a local whisper binary. The script only reads the declared MINIMAX_API_KEY and optional KAI_* env vars, writes outputs into a per-skill workspace, and does not attempt to read unrelated files or credentials.
Install Mechanism
This is an instruction-only skill with an included shell script; there is no install spec that downloads or executes remote code. No high-risk install behavior detected.
Credentials
Only MINIMAX_API_KEY is required (plus optional workspace and voice ID env vars). That single credential is appropriate for calling the external MiniMax API; no unrelated secrets or multiple service credentials are requested.
Persistence & Privilege
The skill does not request always:true and does not change other skills or system-wide settings. It creates and writes files within its workspace only, which is normal for this type of skill.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install kai-minimax-tts - 安装完成后，直接呼叫该 Skill 的名称或使用
/kai-minimax-tts触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.7
- Documentation simplified and condensed in SKILL.md for easier setup and usage.
- Shortened description to focus on core features: generate voice and transcribe speech via MiniMax TTS.
- Clarified usage examples for generating English/Spanish voice and transcribing audio.
- Output file locations and environment variable customization instructions made more concise.
- Removed detailed explanations and lengthy trigger phrase lists from documentation.
v1.0.6
- Simplified and streamlined the SKILL.md setup and usage instructions for clarity.
- Updated environment variable and workspace customization guidance.
- Kept technical details on file outputs, voice IDs, and usage examples.
- Removed redundant or verbose content from earlier documentation.
v1.0.5
- Updated API key setup to use OpenClaw config instead of .env file.
- Improved documentation: clearer setup instructions and safer API management.
- Voice IDs are now configurable via environment variables.
- Removed need to modify skill files for custom voices—set env vars instead.
- Noted support for configurable workspace path via environment variable.
- General cleanup for simplicity and clarity in workflow explanation.
v1.0.4
- Maintenance update with no user-facing changes.
- Documentation, interface, and usage remain the same.
v1.0.3
- metadata structure updated for openclaw; now lists environment variable and required binaries under "requires"
- clarified file path in workflow step for sending Kai's audio (now shows full path for Kai.mp3)
- no functional or interface changes; documentation improvements only
v1.0.2
- Updated the skill manifest in SKILL.md:
- moved `MINIMAX_API_KEY` to a new `env:` section
- removed `MINIMAX_API_KEY` from the `metadata.requires.env` field
- No changes to the functionality or usage—documentation update only.
v1.0.1
- Added requirement for MiniMax API key; users must set MINIMAX_API_KEY in their environment.
- Updated metadata to include env variable requirement for MINIMAX_API_KEY.
- Improved documentation in SKILL.md with clear setup instructions and warning if API key is missing.
- Clarified use of MiniMax TTS and how to use custom voice IDs.
- Minor revisions to wording and organization for ease of use.
v1.0.0
kai-minimax-tts 1.0.0 initial release
- Provides tools to transcribe incoming voice messages using Whisper.
- Generates synthetic voice replies using MiniMax TTS with Kai's authentic voice in English and Spanish.
- Standardizes output files: Kai.mp3 for replies, latest_from_blaze.ogg for received audio, and latest_from_blaze.txt for transcripts.
- Supports trigger phrases like “transcribe this”, “voice message”, “use your voice”, and more.
- Includes clear workflow and command-line instructions for usage.
元数据
常见问题
Kai Minimax Tts 是什么？
Generate voice audio and transcribe speech using MiniMax TTS API. Use when responding with voice or transcribing audio files. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 173 次。
如何安装 Kai Minimax Tts？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install kai-minimax-tts」即可一键安装，无需额外配置。
Kai Minimax Tts 是免费的吗？
是的，Kai Minimax Tts 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Kai Minimax Tts 支持哪些平台？
Kai Minimax Tts 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Kai Minimax Tts？
由 Blaze🔥（@ogdegenblaze）开发并维护，当前版本 v1.0.7。
推荐 Skills