listen

Read the latest conversation response aloud using edge-tts and afplay.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/paulovictor237/PeveAgent --skill listen-paulovictor237
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: listen
Source: https://github.com/paulovictor237/PeveAgent/tree/main/.agents/skills/listen
Command: npx skills add https://github.com/paulovictor237/PeveAgent --skill listen-paulovictor237

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires edge-tts, afplay, and includes scripts (resource) components.

What problem does it solve?

The skill eliminates the need to manually copy and read text, allowing users to hear the latest response or any file content spoken aloud instantly.

Core Features & Use Cases

  • Text-to-speech of last response: Converts the most recent assistant reply into natural‑sounding audio using edge‑tts.
  • File reading: Reads a specified text file and speaks its contents, handling emojis and special characters.
  • Cross‑language support: Chooses appropriate neural voice for Portuguese and English.
  • Use case example: When a user asks to “listen to the answer” or wants a document read aloud while working on code.

Quick Start

Ask the assistant to listen to the last reply or provide a file path to have its contents spoken.

Frequently Asked Questions about listen

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert text-to-speech from a file on macOS?

To convert text-to-speech from a file on macOS, you can use a tool that reads the file's contents and generates natural-sounding MP3 audio. This Skill processes specified text files, handles special characters, and plays the spoken audio instantly using edge-tts and afplay.

Can I use edge-tts to read an assistant's reply aloud?

Yes, you can use edge-tts to read an assistant's reply aloud. This Skill captures the most recent conversation response and instantly converts it into natural-sounding neural text-to-speech audio, eliminating the need to manually copy and read the text.

Does neural text-to-speech support Portuguese and English voice playback?

Neural text-to-speech supports both Portuguese and English voice playback. The Skill automatically selects an appropriate neural voice based on the language of the latest response or the specified text file being read aloud.

What dependencies do I need to play generated MP3 audio on macOS?

To play generated MP3 audio on macOS, you need edge-tts for generating the neural text-to-speech audio and afplay as the audio player. These dependencies are required to synthesize and play the spoken text output.

How do I listen to a document while coding without switching windows?

To listen to a document while coding without switching windows, you can request audio playback of a specified file path or the latest assistant reply. The Skill instantly speaks the text contents aloud, enabling a hands-free reading experience.

Are there limitations when using afplay for text-to-speech on macOS?

A limitation when using afplay for text-to-speech on macOS is that it requires the edge-tts dependency to first generate the MP3 audio file. Additionally, afplay is a macOS-specific utility, meaning this workflow is restricted to Apple platforms.