A professional integration that converts text into natural speech using MiniMax TTS and delivers it as voice messages or files to Lark via lark-cli.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install voice-minimax
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install voice-minimax using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is voice-minimax?
The voice-minimax skill is a specialized automation tool designed for the Openclaw Skills ecosystem. It bridges the gap between advanced AI speech synthesis and enterprise communication by leveraging the MiniMax speech-2.8-hd model. This skill enables developers to transform any text input into a high-quality audio stream, transcode it into platform-compatible formats, and transmit it directly to users as native voice notes.
By utilizing Openclaw Skills, this workflow handles the complexities of API communication, audio transcoding via FFmpeg, and bot-level messaging through the Lark interface. It is particularly effective for teams looking to add a human touch to their automated notifications or build voice-enabled AI assistants within their internal workspace.
voice-minimax Use Cases
- Automating personalized voice introductions for onboarding workflows.
- Converting long-form text reports into digestible audio broadcasts for mobile team members.
- Delivering critical system alerts as audible voice messages to ensure immediate attention.
- Building interactive AI personas that communicate through native voice bubbles in Lark.
How voice-minimax Works
- The skill captures text input and sends a request to the MiniMax Text-to-Audio (v2) API using the speech-2.8-hd model.
- The API returns audio data which is saved locally as an MP3 file.
- If a standard voice bubble is requested, the system uses FFmpeg to transcode the MP3 into a specific OPUS format (16kHz, mono, 64kbps) to ensure compatibility with mobile playback.
- The lark-cli is invoked with bot identity to upload and send the audio file to the target user's chat.
voice-minimax Setup
To get started with this skill in your Openclaw Skills environment, ensure you have the necessary dependencies and credentials ready:
# 1. Install required system tools
sudo apt-get install ffmpeg
npm install -g lark-cli
# 2. Set your environment variables
export MINIMAX_API_KEY='your_minimax_key_here'
export LARK_USER_ID='your_lark_open_id'
You must also ensure that your lark-cli is configured with bot permissions to send messages successfully.
voice-minimax Data Schema & Taxonomy
The skill manages temporary audio assets and uses a structured metadata approach for the synthesis process:
| Attribute | Description | Data Type |
|---|---|---|
| model | The MiniMax speech model (speech-2.8-hd) | String |
| voice_id | Identifier for the selected voice (e.g., male-qn-qingse) | String |
| /tmp/voice.mp3 | Intermediate high-quality audio file | File (MP3) |
| /tmp/voice.opus | Platform-optimized voice message | File (OPUS) |
| msg_type | Delivery format (audio for voice notes, file for MP3) | Enum |
voice-minimax Advanced Features
- Precision Transcoding: Custom FFmpeg parameters (vbr off, bitexact) to prevent zero-duration errors on mobile devices.
- Multi-Format Support: Toggle between interactive OPUS voice bubbles and high-fidelity, forwardable MP3 files.
- Bot Identity Integration: Uses the --as bot flag to ensure seamless message delivery within the Openclaw Skills framework.
- Customizable Voice Settings: Fine-tune audio output with adjustable speed, sample rates, and bitrate parameters.
SKILL.md
Loading
Related Openclaw Skills
Complex Task Orchestrator
A robust framework for decomposing, executing, and recovering complex, multi-step AI agent tasks without losing context or data.
Skill Sync
A powerful utility to audit, deduplicate, and synchronize AI agent skills across multiple environments into a single canonical source of truth.
Doubao Copywriter Skill
An automated AI writing assistant that leverages the Doubao platform to generate high-quality copy for social media, blogs, and video scripts.
MakeContents
An autonomous AI agent skill for fetching, screening, and publishing news content across multiple platforms via local API integration.
Memory Dream
Memory Dream is a structured memory classification and periodic consolidation system designed to keep Openclaw Skills agents efficient and context-aware.
Claude Code Integration for OpenClaw
A professional-grade programming integration that bridges the Claude Code CLI with OpenClaw for autonomous software engineering tasks.
Featured*
