Skip to content
TakoAPI
Back to skills

audio-reply

by matrixy

Speech & Transcription
2.2kDownloads reported by clawskills.sh
3Stars
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Generate audio replies using TTS.

Description

What This Skill Does

Converts Claude responses to spoken audio using the MLX Audio chatterbox-turbo TTS model running locally on macOS. Accepts a public URL to fetch and read aloud, or generates a conversational spoken reply for any topic. Trigger phrases include "read it to me", "talk to me", "voice reply", and "say it".

Runs TTS locally on macOS with no API key or cloud service, keeping audio generation private and offline.

When to Use It

  • Listening to a blog post or article while away from the screen
  • Hands-free answers during cooking or exercise
  • Getting an audio summary of a long documentation page
  • Hearing a conversational explanation of a technical topic
  • Reading out a webpage in the background during a commute

Example Workflow

INPUT

User asks: read it to me https://blog.example.com/new-feature

AGENT
  1. 1

    Validate URL against safety rules, rejecting local or private targets

  2. 2

    Fetch page content with WebFetch and extract main article text

  3. 3

    Summarize content if it exceeds 500 words

  4. 4

    Run mlx_audio.tts.generate with chatterbox-turbo to produce and auto-play audio

  5. 5

    Delete the temporary .wav file after playback

OUTPUT

Audio plays through system speakers; agent confirms "Done reading the article to you."

Requirements

  • uv installed (brew install uv)

Installation

clawhub install matrixy/audio-reply-skill

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

Links