Edge-TTS Skill

Overview

Generate high-quality text-to-speech audio using Microsoft Edge's neural TTS service via the node-edge-tts npm package. Supports multiple languages, voices, adjustable speed/pitch, and subtitle generation.

Quick Start

When you detect TTS intent from triggers or user request:

1. 1. Call the tts tool (Clawdbot built-in) to convert text to speech
2. The tool returns a MEDIA: path
3. Clawdbot routes the audio to the current channel

CODEBLOCK0

Trigger Detection

Recognize "tts" keyword as TTS requests. The skill automatically filters out TTS-related keywords from text before conversion to avoid converting the trigger words themselves to audio.

Advanced Customization

Using the Node.js Scripts

For more control, use the bundled scripts directly:

TTS Converter

CODEBLOCK1

Options:

• - --voice, -v: Voice name (default: en-US-AriaNeural)
• INLINECODE1: Language code (e.g., en-US, es-ES)
• INLINECODE2: Output format (default: audio-24khz-48kbitrate-mono-mp3)
• INLINECODE3: Pitch adjustment (e.g., +10%, -20%, default)
• INLINECODE4: Rate adjustment (e.g., +10%, -20%, default)
• INLINECODE5: Volume adjustment (e.g., +0%, -10%, default)
• INLINECODE6: Save subtitles as JSON file
• INLINECODE7: Output file path (default: tts_output.mp3)
• INLINECODE8: Proxy URL (e.g., http://localhost:7890)
• INLINECODE9: Request timeout in milliseconds (default: 10000)
• INLINECODE10: List available voices

Configuration Manager

CODEBLOCK2

Voice Selection

Common voices (use --list-voices for full list):

English:

• - en-US-MichelleNeural (female, natural, default)
• INLINECODE13 (female, natural)
• INLINECODE14 (male, natural)
• INLINECODE15 (female, British)
• INLINECODE16 (male, British)

Other Languages:

• - es-ES-ElviraNeural (Spanish, Spain)
• INLINECODE18 (French)
• INLINECODE19 (German)
• INLINECODE20 (Japanese)
• INLINECODE21 (Chinese)
• INLINECODE22 (Arabic)

Rate Guidelines

Rate values use percentage format:

• - "default": Normal speed
• INLINECODE24 to "-10%": Slow, clear (tutorials, stories, accessibility)
• INLINECODE26 to "+20%": Slightly fast (summaries)
• INLINECODE28 to "+50%": Fast (news, efficiency)

Output Formats

Choose audio quality based on use case:

• - audio-24khz-48kbitrate-mono-mp3: Standard quality (voice notes, messages)
• INLINECODE31: High quality (presentations, content)
• INLINECODE32: Highest quality (professional audio, music)

Resources

scripts/tts-converter.js

Main TTS conversion script using node-edge-tts. Generates audio files with customizable voice, rate, volume, pitch, and format. Supports subtitle generation and voice listing.

scripts/config-manager.js

Manages persistent user preferences for TTS settings (voice, language, format, pitch, rate, volume). Stores config in ~/.tts-config.json.

scripts/package.json

NPM package configuration with node-edge-tts dependency.

references/nodeedgetts_guide.md

Complete documentation for node-edge-tts npm package including:

• - Full voice list by language
• Prosody options (rate, pitch, volume)
• Usage examples (CLI and Module)
• Subtitle generation
• Output formats
• Best practices and limitations

Voice Testing

Test different voices and preview audio quality at: https://tts.travisvn.com/

Refer to this when you need specific voice details or advanced features.

Installation

To use the bundled scripts:

CODEBLOCK3

This installs:

• - node-edge-tts - TTS library
• INLINECODE35 - CLI argument parsing

Workflow

1. 1. Detect intent: Check for "tts" trigger or keyword in user message
2. Choose method: Use built-in tts tool for simple requests, or scripts/tts-converter.js for customization
3. Generate audio: Convert the target text (message, search results, summary)
4. Return to user: The tts tool returns a MEDIA: path; Clawdbot handles delivery

Testing

Basic Test

Run the test script to verify TTS functionality:

cd /home/user/clawd/skills/public/edge-tts/scripts
npm test

This generates a test audio file and verifies the TTS service is working.

Voice Testing

Test different voices and preview audio quality at: https://tts.travisvn.com/

Integration Test

Use the built-in tts tool for quick testing: CODEBLOCK5

Configuration Test

Verify configuration persistence: CODEBLOCK6

Troubleshooting

• - Test connectivity: Run npm test to check if TTS service is accessible
• Check voice availability: Use node tts-converter.js --list-voices to see available voices
• Verify proxy settings: If using proxy, test with INLINECODE41
• Check audio output: The test should generate test-output.mp3 in the scripts directory

Notes

• - node-edge-tts uses Microsoft Edge's online TTS service (updated, working authentication)
• No API key needed (free service)
• Output is MP3 format by default
• Requires internet connection
• Supports subtitle generation (JSON format with word-level timing)
• Temporary File Handling: By default, audio files are saved to the system's temporary directory (/tmp/edge-tts-temp/ on Unix, C:\Users\<user>\AppData\Local\Temp\edge-tts-temp\ on Windows) with unique filenames (e.g., tts_1234567890_abc123.mp3). Files are not automatically deleted - the calling application (Clawdbot) should handle cleanup after use. You can specify a custom output path with the --output option if permanent storage is needed.
• TTS keyword filtering: The skill automatically filters out TTS-related keywords (tts, TTS, text-to-speech) from text before conversion to avoid converting the trigger words themselves to audio
• For repeated preferences, use config-manager.js to set defaults
• Default voice: en-US-MichelleNeural (female, natural)
• Neural voices (ending in Neural) provide higher quality than Standard voices