openai-latam-audiobook

Translate Russian text to LATAM Spanish and generate audiobook videos with TTS narration.

Updated Dec 6, 2025
One-click install
npx skills add https://github.com/smoreg/biLangGen --skill openai-latam-audiobook
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openai-latam-audiobook
Source: https://github.com/smoreg/biLangGen/tree/main/.claude/skills/openai-latam-audiobook
Command: npx skills add https://github.com/smoreg/biLangGen --skill openai-latam-audiobook

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creating high-quality bilingual audiobooks involves complex, multi-step processes: accurate translation, natural text-to-speech (TTS), background image selection, and video generation. This Skill streamlines the entire pipeline, transforming raw text into a polished video audiobook with minimal effort.

Core Features & Use Cases

  • AI-Powered Translation: Utilizes OpenAI GPT-4o-mini for high-quality Russian to Latin American Spanish translation.
  • Premium Text-to-Speech: Leverages Google Cloud TTS for natural-sounding, high-fidelity audio in both source and target languages.
  • Automated Video Generation: Creates engaging videos with karaoke-style subtitles, rare word cards, and customizable or AI-generated background images.
  • Dynamic Parallelism: Automatically adjusts processing workers based on file size, optimizing performance for both short stories and long novels.
  • Use Case: Convert a Russian novel into a fully produced bilingual video audiobook in Latin American Spanish, complete with AI-generated translation, professional voice-over, and a thematic background, all with a single, optimized command.

Quick Start

Create a Russian to Latin American Spanish audiobook video from the text in 'my_book.txt', using OpenAI for translation and Google Cloud for TTS.

Frequently Asked Questions about openai-latam-audiobook

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

FAQPage Schema
How do I translate Russian text to Spanish and generate an audiobook video?

This Skill translates Russian text to Latin American Spanish using GPT-4o-mini, then generates a complete audiobook video with Google Cloud text-to-speech narration, karaoke-style subtitles, and a background image—all in a single automated pipeline.

Can I create bilingual audiobooks without manual translation and voice recording?

Yes. The Skill automates the entire process: AI translation, professional TTS in both languages, and video assembly with subtitles and background imagery, eliminating manual translation and recording steps.

What languages and text-to-speech options does this support?

The Skill translates Russian to Latin American Spanish and uses Google Cloud TTS for natural-sounding narration in both source and target languages, with configurable voice parameters.

How does it handle large files and optimize processing speed?

The Skill automatically adjusts parallelism based on file size, scaling worker processes to optimize runtime for both short stories and long novels without manual tuning.

What input formats and image options are available?

Input is plain text files. Background images can be sourced locally, pulled from the web, or generated by AI, and are customizable within the video assembly step.

Do I need API keys or cloud credentials to use this?

Yes. You need OpenAI API access for GPT-4o-mini translation and Google Cloud credentials for TTS services; both are configured before running the pipeline.