audify

Convert URLs, files, and raw text into Gemini TTS MP3 narrations.

37|2|Updated Mar 25, 2026

Search Tags:#audio generation #narration #text to speech #MP3 #Gemini TTS

Ready to run

npx skills add https://github.com/jpcaparas/skills --skill audify

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: audify
Source: https://github.com/jpcaparas/skills/tree/main/skills/audify
Command: npx skills add https://github.com/jpcaparas/skills --skill audify

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, ffmpeg, jq, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the process of converting readable resources like URLs, files, and raw text into cleaned Gemini TTS narration with an MP3 output bundle, saving time and effort in audio content creation.

Core Features & Use Cases

Text to Speech: Convert URLs, files, and raw text into Gemini TTS narration.
Output Format: Outputs MP3 narrations in a timestamped folder with additional text and metadata files.
Use Case: You can use this Skill to convert an article or a report into an audio file that can be listened to on any device.

Quick Start

Use the audify skill to convert the article at 'https://example.com/article.md' into an MP3 file.

Frequently Asked Questions about audify

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

FAQPage Schema

How do I convert text from a URL or file into MP3 narration?▼

To convert text into MP3 narration, this Skill reads URLs, files, or raw text and processes them via Gemini TTS. The output is an MP3 audio bundle saved in a timestamped folder with metadata files.

Do I need an API key to generate text-to-speech audio with Gemini TTS?▼

Yes, generating text-to-speech audio with Gemini TTS requires a valid Gemini API key. You must also have Python 3, ffmpeg, and jq installed in your environment to execute the conversion process successfully.

Can I use raw text directly for audio generation or does it only support URLs?▼

You can use raw text directly for audio generation, as the tool supports URLs, files, and raw text inputs. It cleans the readable resources and converts them into Gemini TTS MP3 narrations for playback on any device.

What dependencies are required to set up automated text-to-speech conversion?▼

Automated text-to-speech conversion requires Python 3, ffmpeg, and jq installed on your system. You also need a Gemini API key to authenticate the text-to-speech requests and generate the final MP3 output.

What is included in the MP3 output bundle when converting an article to audio?▼

The MP3 output bundle includes the generated audio narration along with additional text and metadata files. These are organized in a timestamped folder to keep the converted resources structured and easily accessible.