skills.rest
captaindevv
captaindevvCOMMUNITY
Explore all skills by this author →
GitHub

blog-audio

Generate MP3 or WAV audio narration from local Markdown files using Google Gemini TTS.

Updated Apr 12, 2026
Search Tags:#voice#audio#podcast#tts#blog#google-gemini
One-click install
npx skills add https://github.com/captaindevv/blogs --skill blog-audio-captaindevv
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: blog-audio
Source: https://github.com/captaindevv/blogs/tree/main/skills/blog-audio
Command: npx skills add https://github.com/captaindevv/blogs --skill blog-audio-captaindevv

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Quickly produce high-quality audio narrations of blog posts so readers can listen instead of read, enabling accessibility, podcast repurposing, and on-site audio embeds without manual TTS engineering.

Core Features & Use Cases

  • Multi-mode narration: summary (200-300 words), full article read-aloud, or two-speaker dialogue for short podcast-style episodes.
  • Voice catalog & pairing: 30 prebuilt Gemini voices with recommended pairings for host/expert dialogue and content-type suggestions.
  • Operational outputs: MP3 (or WAV fallback), HTML5 embed code, duration & cost estimates, and placement guidance for blog platforms.
  • Robust workflow: local venv management, dry-run cost estimates, FFmpeg fallback, and graceful silent return when API key is missing so writing workflows are never blocked.

Quick Start

Ask the skill to generate audio by saying: /blog audio generate my-article.md --mode summary --voice Charon

Frequently Asked Questions about blog-audio

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

FAQPage Schema
How do I convert a markdown blog post into an audio file?▼

To generate audio from a blog post, run the command targeting your local Markdown file and specify the desired narration mode. You can choose a summary, a full read-aloud, or a two-speaker dialogue output.

Can I create a two-speaker podcast dialogue from a written article?▼

Yes, two-speaker mode generates short podcast-style audio dialogues from your Markdown articles. It uses 30 prebuilt Gemini voices with recommended pairings for host and expert conversations.

Do I need FFmpeg to generate MP3 audio narration?▼

FFmpeg is optional and used as a fallback for MP3 conversion. If FFmpeg is missing, the system gracefully falls back to WAV output instead of blocking the audio generation workflow.

Does blog audio generation work without a Google AI API key?▼

Google Gemini TTS requires a Google AI API key to generate blog audio narration. If the API key is missing, the system executes a graceful silent return so your writing workflow is never blocked.

How do I estimate the cost of text to speech generation for an article?▼

You can estimate text to speech costs by using the dry-run mode before generating audio. This provides duration and cost estimates for your article without consuming the Gemini TTS API.

What is the difference between summary and full read-aloud audio modes?▼

Summary mode condenses the article into a 200-300 word audio narration, while full read-aloud mode converts the entire text. Both produce MP3 files and HTML5 embed code for blog platform placement.

Related Skills

Explore More Content & Communication Skills→
jpcaparasjpcaparas
37

audify

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

Community
Advanced
shenxingyshenxingy
8

blog-audio

Generate MP3 audio narration from blog text using Gemini TTS.

Community
Intermediate
DidierRLopesDidierRLopes
8

convert-beehiiv-newsletter

Convert Beehiiv newsletter posts into blog markdown files with front matter and images.

Community
Advanced
akrindevakrindev
4

gemini-tts

Generates speech from text using Google Gemini TTS models via Python scripts.

Community
Intermediate