Setup & Installation
openclaw skills install @marcus20232023/togetherai-tts
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install togetherai-tts
Version History
v1.0.1Feb 21, 2026 - Version note by skill developer:
- Updated package metadata in package.json. - No user-facing changes.
What This Skill Does
Converts text to speech using the TogetherAI API with the MiniMax speech-2.6-turbo model. Outputs audio files in configurable formats with selectable voices.
Uses TogetherAI's hosted inference so no local model setup or GPU is required.
When to use it
- Generate voiceovers for video content
- Create audio versions of written articles
- Automate spoken notifications or alerts
- Prototype voice interfaces without a recording studio
- Batch convert documentation to audio files
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: convert 'Welcome to our platform' to an MP3 file
AGENT
- 1Load TOGETHERAI_API_KEY and model settings from .env
- 2Send text payload to TogetherAI TTS endpoint with selected voice and format
- 3Receive audio binary response from the API
- 4Write response to output.mp3
OUTPUT
output.mp3 file containing the spoken phrase
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
TOGETHERAI_API_KEY environment variableTogetherAI account (togetherai.ai)