Skip to content
TakoAPI
Back to skills

lh-edge-tts

by liuhedev

Git & GitHub
206Downloads reported by clawskills.sh
1Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Text-to-speech conversion using Python edge-tts for generating audio from text.

Description

What This Skill Does

Converts text to speech using Microsoft Edge's neural TTS service via Python edge-tts. Supports multiple languages and voices, with controls for speed, pitch, volume, and subtitle file generation in SRT or VTT format.

Uses Microsoft Edge's neural voices at no cost, with no API key required, while still supporting a wide range of languages and fine-grained audio controls.

When to Use It

  • Listen to a long article while commuting
  • Generate narration for a tutorial in a specific accent
  • Convert cooking instructions to audio hands-free
  • Create accessible audio versions of written content
  • Produce subtitled audio files for video projects

Example Workflow

INPUT

User asks: tts 'Welcome to the tutorial' with a British male voice at slightly faster speed

AGENT
  1. 1

    Detect 'tts' trigger in user message

  2. 2

    Strip TTS-related keywords from the target text

  3. 3

    Call tts_converter.py with --voice en-GB-RyanNeural and --rate +10%

  4. 4

    Receive the generated MP3 file path

  5. 5

    Return the MEDIA: path to Clawdbot for delivery

OUTPUT

Audio file played in the current channel using en-GB-RyanNeural voice at +10% speed

Installation

clawhub install liuhedev/lh-edge-tts

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links