TTS (Text-to-Speech) for Openclaw

A versatile text-to-speech skill that converts agent text responses into professional-grade MP3 audio files.

amstko
v1.0.0
Jan 26, 2026
1
5.3k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install tts

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install 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 TTS (Text-to-Speech)?

The TTS skill empowers AI agents to communicate through audio by converting written text into natural-sounding speech. By integrating with high-performance providers like Hume AI and OpenAI, this skill allows agents to provide voice replies and audio messages seamlessly. It is an essential addition for developers building interactive Openclaw Skills that require a multi-modal approach to user engagement.

This skill focuses on flexibility and quality, offering a preferred high-fidelity voice through Hume AI while maintaining legacy support for OpenAI models. It automates the audio generation pipeline, ensuring that every synthesized message is stored as a portable MP3 file with clear path logging for immediate delivery to the user.

TTS (Text-to-Speech) Use Cases

  • Delivering spoken responses when a user asks to hear something out loud or "of vive voix".
  • Creating audio messages for users who prefer listening over reading.
  • Automating the generation of MP3 assets for multi-modal agent workflows.
  • Providing accessibility options for users with visual impairments within Openclaw Skills environments.

How TTS (Text-to-Speech) Works

  1. The AI agent identifies a request for audio output or a specific voice command.
  2. The skill invokes a Node.js script (either for Hume AI or OpenAI) with the target text and output file name.
  3. The synthesis engine processes the text using a predefined high-quality voice ID.
  4. An MP3 file is generated and saved to the specified directory.
  5. The script prints a MEDIA tag containing the absolute path to the file.
  6. The agent utilizes the message tool to transmit the final audio file to the user.

TTS (Text-to-Speech) Setup

To get started with this skill within your Openclaw Skills ecosystem, configure your environment variables and run the synthesis scripts as follows:

Hume AI Setup (Preferred):

HUME_API_KEY="your_api_key" HUME_SECRET_KEY="your_secret_key" node scripts/generate_hume_speech.js --text "Your text here" --output "output.mp3"

OpenAI Setup (Legacy):

OPENAI_API_KEY="your_api_key" node scripts/generate_speech.js --text "Your text here" --output "output.mp3"

TTS (Text-to-Speech) Data Schema & Taxonomy

Feature Specification
Output Format MP3 Audio
Preferred Voice (Hume) 9e1f9e4f-691a-4bb0-b87c-e306a4c838ef
Preferred Voice (OpenAI) nova
Metadata Output MEDIA: [Absolute Path]
Environment Keys HUME_API_KEY, HUME_SECRET_KEY, OPENAI_API_KEY

TTS (Text-to-Speech) Advanced Features

  • Multi-provider support allowing developers to switch between Hume AI and OpenAI synthesis.
  • Specific voice ID targeting for consistent brand identity in Openclaw Skills.
  • Automated absolute path reporting via the MEDIA prefix for easy tool integration.
  • Lightweight Node.js implementation designed for low-latency audio generation.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*