Setup & Installation
openclaw skills install @gugic/inworld-tts
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install inworld-tts
What This Skill Does
Generates speech audio from text using the Inworld.ai TTS API. Outputs MP3 files with configurable voice, speaking rate, and temperature. Supports a streaming mode for text exceeding 4000 characters.
Inworld TTS 1.5-max supports streaming for long-form text, which most simple TTS wrappers skip.
When to use it
- Converting article text to audio for listening on the go
- Adding spoken responses to a chatbot or assistant
- Generating narration for video or slideshow content
- Producing audio previews of written notifications
- Testing different voice styles for a production app
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: convert this blog post to an MP3 with a faster speaking rate
AGENT
- 1Reads the blog post text from the source file
- 2Calls tts.sh with the text, output filename, and --rate 1.4
- 3Sends the request to the Inworld standard synthesis endpoint
- 4Writes the decoded audio to the specified MP3 file
OUTPUT
An MP3 file containing the narrated blog post at 1.4x speed
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
INWORLD_API_KEY environment variable (Base64 key from platform.inworld.ai with 'Voices: Read' permission)