本文へスキップ
TakoAPI
スキル一覧に戻る

audio-reply

matrixy 作

Speech & Transcription
2.2kダウンロード数はclawskills.shが公開している値です
3スター
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Generate audio replies using TTS.

説明

このスキルでできること

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.

使いどころ

  • 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

ワークフロー例

入力

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

エージェント
  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

出力

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

要件

  • uv installed (brew install uv)

インストール

clawhub install matrixy/audio-reply-skill

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク