Convert markdown blog content into audio narrations using Google Gemini TTS models.
npx skills add https://github.com/smarmen86/claude-code-kit --skill blog-audio-smarmen86
Please help me install this Agent Skill. Skill: blog-audio Source: https://github.com/smarmen86/claude-code-kit/tree/main/skills/blog-audio Command: npx skills add https://github.com/smarmen86/claude-code-kit --skill blog-audio-smarmen86
This skill solves the lack of accessibility and engagement in text-heavy content by automatically converting written blog posts into high-quality, natural-sounding audio narrations.
Use the blog audio skill to generate a podcast-style dialogue narration for the file named article.md.
High-intent search queries and answers about installing and using this skill.
You can convert markdown blog posts into audio narrations using Google Gemini TTS models to generate high-fidelity spoken audio from your written content. This process supports generating spoken summaries, full article read-alouds, and multi-speaker dialogues.
Yes, you can generate a two-speaker podcast-style dialogue from written articles. The system supports multi-speaker dialogue generation alongside single-speaker narration, allowing you to create engaging conversational audio formats from your markdown files.
Yes, FFmpeg is required for audio processing and format conversion alongside the Google GenAI SDK. These dependencies are necessary to handle and convert the generated TTS audio into its final output format.
The best way to customize text-to-speech narration is by selecting from 30 distinct voice profiles. This allows you to match your brand tone, ranging from professional experts to casual hosts for your generated audio output.
Yes, Google Gemini TTS models support multi-speaker dialogue generation. You can create engaging podcast-style dialogues with two speakers or use standard single-speaker narration for summaries and full articles.
joyehuangConvert text to WAV narration at 1.2x speed via Google Gemini TTS API.
shenxingyGenerate MP3 audio narration from blog text using Gemini TTS.
Dante-danPublish markdown articles to dhpie.com via an authenticated API workflow.
kaivyyTranscribe audio files with OpenAI Whisper and synthesize speech from text.
