sanatan-sdk 0.18.0

Python SDK for creating verse-based content sites with AI translations, multimedia (images, audio), semantic search, and deployment

Sanatan SDK - Python SDK for Spiritual Verse Collections

Complete toolkit for generating rich multimedia content for spiritual text collections (Hanuman Chalisa, Sundar Kaand, etc.)

Features

• 🔄 Complete Workflow: Generate media and embeddings from canonical sources - all in one command
• 📖 Canonical Sources: Local YAML files ensure text accuracy and quality
• 🎨 AI Images: Generate themed images with DALL-E 3
• 🎵 Audio Pronunciation: Full and slow-speed audio with ElevenLabs
• 🔍 Semantic Search: Vector embeddings for intelligent verse discovery
• 📚 Multi-Collection: Organized support for multiple verse collections
• 🎨 Theme System: Customizable visual styles (modern, traditional, kids-friendly, etc.)

Quick Start

# Install
pip install sanatan-sdk

# Set up API keys (in your project directory)
cp .env.example .env
# Edit .env and add your API keys

# List available collections
verse-generate --list-collections

# Complete workflow (default) - fetch text, generate media, update embeddings
verse-generate --collection hanuman-chalisa --verse 15

# Skip text fetching (when verse text already exists)
verse-generate --collection sundar-kaand --verse 5 --no-fetch-text

# Or generate specific components only
verse-generate --collection sundar-kaand --verse 3 --image
verse-generate --collection sankat-mochan-hanumanashtak --verse 5 --audio

By default, the complete workflow includes:

• 🔍 Read canonical Devanagari text from local YAML files
• 🎨 DALL-E 3 generated image (saved to images/{collection}/{theme}/)
• 🎵 Full-speed pronunciation (saved to audio/{collection}/{verse}_full.mp3)
• 🎵 Slow-speed pronunciation (saved to audio/{collection}/{verse}_slow.mp3)
• 🔗 Update vector embeddings for semantic search

Text Source:

• Local YAML file: data/verses/{collection}.yaml or .yml (required)
• You must create this file with canonical verse text (see Local Verses Guide)

Opt-out flags (to skip specific steps):

• --no-fetch-text - Skip fetching text (use when verse text already exists)
• --no-update-embeddings - Skip updating embeddings

Installation

pip install sanatan-sdk

Commands

• verse-generate - Complete orchestrator for verse content (text fetching, multimedia generation, embeddings)
• verse-translate - Translate verses into multiple languages (Hindi, Spanish, French, etc.)
• verse-status - Check status, completion, and validate text against canonical source
• verse-sync - Sync verse text with canonical source (fix mismatches)
• verse-images - Generate images using DALL-E 3
• verse-audio - Generate audio pronunciations using ElevenLabs
• verse-embeddings - Generate vector embeddings for semantic search (multi-collection guide)
• verse-deploy - Deploy Cloudflare Worker for API proxy

Configuration

Copy the example environment file and add your API keys:

cp .env.example .env
# Edit .env and add your API keys

See the Usage Guide for detailed information on project structure, workflows, batch processing, and cost optimization.

Documentation

• Usage Guide - Project setup, workflows, batch processing, and best practices
• Local Verses Guide - Using local YAML files for verse text
• Command Reference - Detailed documentation for all commands
• Development Guide - Setup and contributing to verse-sdk
• Troubleshooting - Common issues and solutions
• Multi-Collection Guide - Working with multiple collections
• Publishing Guide - For maintainers

Example Project

Hanuman GPT - Multi-collection project with Hanuman Chalisa, Sundar Kaand, and Sankat Mochan Hanumanashtak

Requirements

• Python 3.8+
• OpenAI API key (for text/images/embeddings)
• ElevenLabs API key (for audio)

License

MIT License - See LICENSE file for details

Support

• GitHub Issues
• Documentation
• Troubleshooting Guide