← Back to Skills Marketplace
MiniMax TTS Generator
by
lanhaixuan
· GitHub ↗
· v1.0.0
· MIT-0
115
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install minimax-tts-generator
Description
Text-to-speech (TTS) generation using MiniMax API. Converts text into natural-sounding speech with support for multiple voices, adjustable speed and pitch, a...
Usage Guidance
This skill appears to implement a legitimate MiniMax TTS client and only requires your MiniMax API key. Before installing: (1) Review and confirm you are comfortable providing MINIMAX_API_KEY (the script sends it as a Bearer token to the API). (2) Install ffmpeg if you plan to use multi-segment output (the script calls ffmpeg but ffmpeg is not listed as a required binary). (3) Be aware the code will read ~/.openclaw/openclaw.json and write audio files to ~/.openclaw/workspace/tmp (check those paths and permissions). (4) The script supports an environment override MINIMAX_API_HOST — don't set this to an untrusted host (an attacker-controlled host could capture your API key). (5) If you do not fully trust the skill source, review the included minimax_tts.py before running it (it performs network requests and executes ffmpeg via subprocess). If these points are acceptable or fixed (declare ffmpeg as required, document MINIMAX_API_HOST), the skill is coherent with its stated purpose.
Capability Analysis
Type: OpenClaw Skill
Name: minimax-tts-generator
Version: 1.0.0
The skill is a legitimate text-to-speech generator using the MiniMax API. The Python script `scripts/minimax_tts.py` correctly handles API authentication via environment variables or the standard OpenClaw configuration file and uses `ffmpeg` for audio processing. No evidence of malicious intent, data exfiltration, or prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description match the code: the script sends text to MiniMax endpoints and returns/writes audio. Required binary python3 and MINIMAX_API_KEY are appropriate for a TTS client. The network endpoints in code point to api.minimaxi.com which aligns with the stated MiniMax purpose.
Instruction Scope
SKILL.md instructs running the included Python script and storing the API key in env or openclaw config — this matches the code. The runtime does read the user's openclaw config (~/.openclaw/openclaw.json) and writes audio to ~/.openclaw/workspace/tmp; both are documented in SKILL.md. The script uses subprocess.run to call ffmpeg when concatenating segments; the SKILL.md examples show multi-segment usage but do not declare ffmpeg as a required binary. Also the code allows overriding the API host via MINIMAX_API_HOST (which can redirect network calls) — this override is not declared as a required env var in the registry metadata.
Install Mechanism
This is instruction-only / contained code included in the skill bundle with no network-download install step. No external archives or installers are fetched during install, which lowers supply-chain risk.
Credentials
The only declared required credential is MINIMAX_API_KEY (primaryEnv) which is proportionate for a TTS API client. The code also reads MINIMAX_API_HOST if set (not declared in requires.env) and the openclaw config file; both are reasonable but the undocumented MINIMAX_API_HOST allows redirecting requests to an arbitrary host and should be noted.
Persistence & Privilege
The skill does not request always:true, does not demand extra system privileges, and confines storage to ~/.openclaw/workspace/tmp and its own config entry in ~/.openclaw/openclaw.json. It does not modify other skills' settings or system-wide configs beyond its own entry.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install minimax-tts-generator - After installation, invoke the skill by name or use
/minimax-tts-generator - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: Text-to-speech generation using MiniMax speech-2.8-hd API. Supports multiple Chinese voices, adjustable speed/pitch, MP3/WAV/PCM output formats.
Metadata
Frequently Asked Questions
What is MiniMax TTS Generator?
Text-to-speech (TTS) generation using MiniMax API. Converts text into natural-sounding speech with support for multiple voices, adjustable speed and pitch, a... It is an AI Agent Skill for Claude Code / OpenClaw, with 115 downloads so far.
How do I install MiniMax TTS Generator?
Run "/install minimax-tts-generator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is MiniMax TTS Generator free?
Yes, MiniMax TTS Generator is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does MiniMax TTS Generator support?
MiniMax TTS Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created MiniMax TTS Generator?
It is built and maintained by lanhaixuan (@lanhaixuan); the current version is v1.0.0.
More Skills