ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified media Safety 4/5

duby

Convert text to speech using Duby.so API. Supports various voices and emotions.

Why use this skill?

Integrate Duby.so text-to-speech into OpenClaw agents. Generate high-quality synthetic audio from text with support for custom voices and easy configuration.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/autogame-17/duby
Or

What This Skill Does

The Duby TTS skill provides a seamless interface to the Duby.so text-to-speech API, allowing OpenClaw agents to convert textual information into high-quality, synthetic audio files. By leveraging advanced speech synthesis, this skill enables agents to "speak" back to users, create narrative content, or produce media assets directly from a terminal or automation pipeline. The skill is designed for modularity, supporting custom voice IDs and emotional inflections, making it a versatile tool for any agent requiring audio output.

Installation

To integrate this skill into your environment, use the OpenClaw package manager. Ensure your environment has the necessary dependencies like curl and jq installed beforehand. Execute the following command in your terminal:

clawhub install openclaw/skills/skills/autogame-17/duby

After installation, you must configure the API_KEY within the tts.sh script located in the skill directory. Without a valid API key, the skill will be unable to authenticate with the Duby.so servers.

Use Cases

  • Automated Alerts: Have your agent read out critical system notifications or build completion statuses using a clear, consistent voice.
  • Content Creation: Quickly generate audio tracks for scripts, blog post summaries, or educational materials.
  • Accessibility: Convert long-form documentation or logs into audio format for improved accessibility and hands-free consumption.
  • Personalization: Use different voice IDs to give your AI agent a unique identity or to match the emotional tone of a specific message.

Example Prompts

  1. "Duby, please convert the following message into an audio file: 'System migration completed successfully.'"
  2. "Use the Xinduo voice to read this text: 'Welcome to the dashboard, please select an option.'"
  3. "Generate an audio file for the script I just pasted using the default Duby settings."

Tips & Limitations

  • Voice Selection: Always verify the Voice ID before running a batch of requests; using invalid IDs will cause the API to fail.
  • Network Dependence: Because this skill relies on the Duby.so external API, it requires an active internet connection to function.
  • Authentication: Ensure your API key is kept secure and never hard-coded in version-controlled scripts that are pushed to public repositories.
  • Latency: Keep in mind that audio generation speed depends on both your network latency and the current load on the Duby.so processing servers.

Metadata

Stars1100
Views1
Updated2026-02-17
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-autogame-17-duby": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags

#tts#audio#voice#duby
Safety Score: 4/5

Flags: network-access, file-write, external-api