A high-performance text-to-speech skill that converts text into natural-sounding audio using the Inworld.ai API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install inworld-tts
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 inworld-tts 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 Inworld TTS?
The Inworld TTS skill is a powerful utility designed to bridge the gap between text-based AI processing and high-fidelity audio output. As a specialized component of the Openclaw Skills library, it leverages the Inworld.ai API to transform written content into professional MP3 files. This skill is essential for developers building interactive agents, automated narration systems, or accessibility tools that require realistic vocal performances.
By integrating this skill into your workflow, you gain access to a variety of voice profiles and granular control over speech dynamics. Whether you are generating a single line of dialogue or streaming thousands of characters of text, this tool within the Openclaw Skills ecosystem ensures consistent, low-latency performance with minimal local dependencies.
Inworld TTS Use Cases
- Generating vocal responses for AI-driven characters and digital twins.
- Automating the creation of audiobooks or long-form narration from text files.
- Developing voice-enabled alerts and notifications for developer workflows.
- Creating localized audio content by utilizing different voice IDs and speaking rates.
- Batch processing documentation into spoken audio for multitasking and accessibility.
How Inworld TTS Works
- The skill receives a text string and optional configuration parameters like voice selection or speaking speed.
- It verifies the presence of the INWORLD_API_KEY environment variable to authenticate the session.
- The script constructs a payload and sends a POST request to either the standard or streaming Inworld.ai TTS endpoint.
- Upon receiving a response, the skill extracts the base64-encoded audio data using jq.
- The encoded data is piped through a base64 decoder to generate a finalized MP3 file in the specified output directory.
Inworld TTS Setup
To get started with this skill as part of your Openclaw Skills collection, follow these steps:
- Register at the Inworld Platform (https://platform.inworld.ai) and generate an API key with 'Voices: Read' permissions.
- Export your key as an environment variable in your shell configuration file:
export INWORLD_API_KEY="your-base64-key-here"
- Install the skill and ensure the execution permissions are set:
# Copy skill to your directory
cp -r inworld-tts /path/to/your/skills/
# Make script executable
chmod +x /path/to/your/skills/inworld-tts/scripts/tts.sh
# Optional: create a global symlink
ln -sf /path/to/your/skills/inworld-tts/scripts/tts.sh /usr/local/bin/inworld-tts
Inworld TTS Data Schema & Taxonomy
The Inworld TTS skill manages data through a combination of environment variables and command-line arguments. The primary data structure for interactions is detailed below:
| Parameter | Default | Description |
|---|---|---|
| text | N/A | The source string to be converted to speech |
| output_file | N/A | The destination path for the generated MP3 |
| voice | Dennis | The ID of the voice model to be used |
| rate | 1.0 | Speed of speech ranging from 0.5 to 2.0 |
| temp | 1.1 | Expressiveness temperature from 0.1 to 2.0 |
| model | inworld-tts-1.5-max | The specific Inworld TTS model version |
All audio output is encoded in MP3 format, ensuring broad compatibility across Openclaw Skills and media players.
Inworld TTS Advanced Features
- Streaming Support: Utilize the --stream flag to handle text blocks exceeding 4000 characters without timing out.
- Dynamic Rate Scaling: Adjust the --rate parameter to create varied pacing, from slow instructional content to rapid news briefings.
- Expressiveness Control: Use the --temp parameter to fine-tune the emotional 'temperature' of the voice model.
- Headless Integration: Designed to work seamlessly in CLI environments, making it ideal for server-side Openclaw Skills automation.
- Low-Dependency Design: Requires only curl, jq, and base64, making it highly portable across Unix-based systems.
SKILL.md
Loading
Related Openclaw Skills
NotebookLM Research Assistant
A specialized skill for querying Google NotebookLM notebooks to get source-grounded, citation-backed answers with zero hallucinations.
TripGo API
A comprehensive interface for multimodal journey planning, public transport data, and real-time trip management.
SkedGo TripGo API
A comprehensive interface for multimodal routing and public transport management using the SkedGo TripGo platform.
WeChat Sticker Maker
A specialized tool for automatically cropping and formatting grid images into WeChat-compliant sticker packs.
Advogato - Legal Intelligence & Strategy (BR)
A strategic legal intelligence skill specialized in the Brazilian legal system for contract analysis, risk management, and compliance auditing.
ClawdZap
A decentralized messaging layer for AI agents providing encrypted P2P communication and public signaling via the Nostr protocol.
Featured*
