Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
A Python CLI wrapper for MiniMax's Speech 2.8 T2A REST API. Two subcommands cover TTS generation and voice catalog lookups. Supports voice mixing, pronunciation overrides, audio format control, regional endpoints, and sound effects.
Exposes the full MiniMax Speech 2.8 parameter surface, including voice mixing, pronunciation overrides, and sound effects, that generic TTS clients omit.
When to use it
- Converting a script to narrated audio for a podcast episode
- Listing available cloned or generated voices before building a TTS pipeline
- Generating weather or news announcements in a specific voice tone
- Mixing voice timbres for custom character voices in a game or app
- Batch-converting text to audio with consistent bitrate and sample rate settings
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Generate an MP3 of a weather update using the Sweet_Girl_2 voice
- 1Verifies MINIMAX_API_KEY is set in the environment
- 2Runs the tts subcommand with --text, --voice-id Sweet_Girl_2, --model speech-2.8-hd, and --audio-format mp3
- 3Posts to the MiniMax T2A v2 endpoint and decodes the hex/base64 audio payload
- 4Saves the audio to the specified output file and prints extra_info metadata
minimax-weather.mp3 saved locally, with bitrate, sample rate, and duration printed to stdout
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.