Auto-Talk-TTS

Auto-speak every message using edge-tts. Automatically converts all responses to speech asynchronously in the background. Install the package if needed, then...

Security Scan

The skill's stated purpose (auto TTS) matches much of its instructions, but there are several inconsistencies and risky instructions (missing executable, hard-coded user path, global npm install, instructing you to edit SOUL.md to force behavior, and mac-only playback command) that make it questionable to install without further inspection.

Purpose & Capability

The skill claims to auto-speak every message using node-edge-tts, which explains the npm dependency and TTS behavior. However package.json advertises a bin named "auto-speak" and main "auto-speak" but no corresponding auto-speak script file is included in the package manifest—this is an inconsistency. The SKILL.md also references a specific workspace path (/Users/stefano/.openclaw/...) which is user-specific and unrelated to a generic TTS skill.

Instruction Scope

Instructions go beyond simply converting text to speech: they tell you to add a top-level line to SOUL.md to require TTS for every response (modifying an agent-level policy/config), recommend global npm installs, and hard-code use of 'afplay' to play audio. The SOUL.md edit would force global behavior across the agent and is scope-creep; afplay is macOS-only so the skill is not cross-platform as implied. These broadened instructions warrant caution.

Install Mechanism

There is no formal install spec — the runtime instructions tell the user to run 'npm install -g node-edge-tts' or 'npm install' in a local workspace. Recommending global npm installs touches system state and brings supply-chain risk. The package.json suggests the skill provides a local 'auto-speak' executable, but that executable is missing from the files provided, making the package incomplete or inconsistent.

Credentials

The skill does not request environment variables, credentials, or config paths. That matches SKILL.md claims of 'No API key'. However the skill will perform network operations via npm and the node-edge-tts package (not shown), which is a normal requirement for installing dependencies but still carries usual network/supply-chain risk.

Persistence & Privilege

The skill itself does not request 'always: true' or elevated platform privileges, but it explicitly instructs users to edit SOUL.md to force the agent to always use TTS for every message. That instruction would change agent-wide behavior and effectively persist this skill's effect across interactions—this is a meaningful privilege escalation via configuration coercion and should be treated cautiously.

What to consider before installing

Do not install or run this skill yet. Key issues: (1) The package refers to an 'auto-speak' executable but that file is not present—ask the author for the missing script or full source before trusting the package. (2) The SKILL.md recommends running 'npm install -g' (global install) which changes your system; avoid global installs unless you trust the package source. (3) It instructs you to edit SOUL.md to force TTS for every message—this changes agent-wide behavior and should only be done deliberately. (4) It hardcodes use of 'afplay' (macOS-only) and even references a specific user path (/Users/stefano/...), suggesting the package may be a local/unfinished copy. (5) node-edge-tts will be fetched from npm; verify that package and its dependencies are legitimate and inspect the actual auto-speak implementation for unexpected network calls, data exfiltration, or credential use. Suggested next steps: request the missing auto-speak script or a complete release (with source), review that script line-by-line, run installs in an isolated environment or container, avoid editing SOUL.md unless you understand and accept the global behavioral change, and prefer installing only from trusted package authors or vetted release artifacts.

Auto-Talk-TTS Skill

Overview

Automatically speaks every message you generate using Microsoft Edge's neural TTS service. Runs asynchronously in the background so your conversation continues immediately while audio generates.

Quick Start

Every message you send is automatically spoken aloud.

The skill wraps your output with auto-speak which:

1. Installs node-edge-tts if needed
2. Converts your message to speech asynchronously
3. Plays the audio in the background
4. Continues your conversation immediately

Usage

Automatic: Every message is auto-spoken. No action needed from you.

Manual override: If you need to speak something specific:

auto-speak "Your text here"

How It Works

1. Detect output: When you generate a message
2. Wrap with auto-speak: The message gets passed through the auto-speak wrapper
3. Install if needed: First run installs node-edge-tts package
4. Generate audio: Convert text to MP3 in background
5. Play audio: Use afplay to play the audio file
6. Continue: Your conversation flows without waiting for audio

Configuration

Edit config.json to customize:

{
  "voice": "en-US-MichelleNeural",
  "rate": "default",
  "pitch": "default",
  "volume": "default",
  "summaryLength": 100
}

Options:

• voice: Any Edge neural voice (see edge-tts skill for full list)
• rate: Speech speed (-20% to +50%, or default)
• pitch: Voice pitch (-20Hz to +20Hz, or default)
• volume: Audio volume (-100% to +100%, or default)
• summaryLength: How many characters to summarize (default: 100)

Installation

First run will automatically install node-edge-tts:

npm install -g node-edge-tts

Or use the bundled installer:

cd /Users/stefano/.openclaw/workspace/skills/auto-talk-tts
npm install

Files

auto-speak

Wrapper script that:

• Checks if node-edge-tts is installed
• Installs it if needed
• Converts text to speech asynchronously
• Plays audio with afplay
• Continues immediately

config.json

User configuration for voice, rate, pitch, volume settings.

package.json

NPM package with node-edge-tts dependency.

SKILL.md

This file.

Integration with SOUL.md

Add this line to the top of your SOUL.md:

## MUST SPEAK WITH TTS EVERY TIME (ASYNCHRONOUSLY)

**I must use the edge-tts skill to convert my response to speech before sending it to you.** Every single message I send must be spoken aloud using the tts tool. This is non-negotiable - I speak to you, I don't just type.

**Async approach:** I run the TTS command in the background using `&` or `nohup` so the conversation continues immediately while audio generates in the background.

Workflow

Automatic (Recommended)

1. You generate a message
2. auto-speak wraps it: The message gets passed through the wrapper
3. Background TTS: Audio generates in background process
4. Immediate reply: Your conversation continues without waiting
5. Audio plays: User hears your response

Manual (If needed)

# Auto-speak any text
auto-speak "Your message here"

# Custom voice
auto-speak "Your message" --voice en-GB-RyanNeural

# Custom speed
auto-speak "Your message" --rate +20%

Testing

# Test the auto-speak wrapper
auto-speak "This is a test. If you can hear this, it's working!"

# Check if node-edge-tts is installed
npm list -g node-edge-tts

# Install manually if needed
npm install -g node-edge-tts

Troubleshooting

• No audio? Check that node-edge-tts is installed: npm list -g node-edge-tts
• Install needed? First run will auto-install, or run: npm install -g node-edge-tts
• Audio not playing? Check system volume and audio output settings
• Slow? Use async mode - audio generates in background, conversation continues immediately

Notes

• Non-blocking: Conversation flows while audio generates
• No API key: Uses Microsoft Edge's free TTS service
• Neural voices: High-quality, natural-sounding speech
• Multiple voices: See edge-tts skill for full voice list
• Configurable: Customize voice, speed, pitch, volume in config.json
• Automatic installation: First run installs node-edge-tts if missing

See Also

• edge-tts - Core TTS engine
• speak-summary - Alternative auto-speak implementation