Text to Voice -- Convert Articles to Audio

Convert rewritten investigative articles into MP3 audio using Google Cloud TTS.

1|Updated Feb 23, 2026
One-click install
npx skills add https://github.com/ValorInvestigator/claude-plugin-toolkit --skill text-to-voice-convert-articles-to-audio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Text to Voice -- Convert Articles to Audio
Source: https://github.com/ValorInvestigator/claude-plugin-toolkit/tree/main/skills/text-to-voice
Command: npx skills add https://github.com/ValorInvestigator/claude-plugin-toolkit --skill text-to-voice-convert-articles-to-audio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pydub, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Converts dense investigative and journalistic articles into ready-to-play MP3 narration so Levi can share reporting with audio-first review while saving time on manual TTS editing.

Core Features & Use Cases

  • Rewrite-for-ear guidance enforces contractions, spelled-out numbers, and silence markers so the article flows naturally when spoken.
  • Chunked TTS rendering calls Google Cloud's Chirp 3 HD voice per paragraph, stitches sections with silence, and exports a single MP3 with duration and size reporting.
  • Use Case prepares finished pieces from the Bingaman archive by rewriting, saving _TTS.txt copies, then running the renderer to deliver the final audio file and stats.

Quick Start

Rewrite the article per the rules, save the `_TTS.txt` version, and run render_audio.py with the rewritten file and desired mp3 path to create the narration.

Frequently Asked Questions about Text to Voice -- Convert Articles to Audio

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

FAQPage Schema
How do I convert a long article into an MP3 using Google Cloud TTS?

Convert articles to MP3 by rewriting the text for natural speech, saving it as a `_TTS.txt` file, and running the render_audio python tool to stitch paragraph chunks with silence gaps.

What does rewriting for ear mean when preparing text-to-speech narration?

Rewriting for ear means adjusting text to flow naturally when spoken, enforcing contractions, spelling out numbers, and inserting silence markers before generating the TTS audio.

Do I need gcloud credentials to generate text-to-speech MP3 files?

Generating TTS MP3 files requires OAuth refresh tokens from the local gcloud credentials database to authenticate Google Cloud Chirp 3 HD voice rendering requests.

Can I use pydub to stitch TTS audio segments with silence gaps?

Pydub handles stitching individual Google Cloud TTS MP3 segments together, inserting silence gaps between sections to create a single cohesive audio file.

How does chunked TTS rendering handle lengthy investigative reports?

Chunked TTS rendering processes lengthy reports by calling Google Cloud TTS per paragraph, then stitching sections with silence to export a single MP3 with duration and size reporting.

What is the best way to automate audio production from dense journalistic articles?

Automate audio production by applying rewrite-for-ear rules to the article, saving the output, and running the renderer to deliver the final MP3 audio file and stats.