Audify

Getting Started

  • Installation
    • Requirements
      • Optional
    • Install from PyPI
    • Install from Source
      • Development dependencies
    • Verify Installation
    • Docker Setup (Optional)
      • Pull an Ollama model
  • Quick Start
    • Option 1: Cloud TTS (Easiest)
      • 1. Install Audify
      • 2. Configure credentials
      • 3. Convert a book
    • Option 2: Kokoro TTS (Local, Free)
      • 1. Clone and start services
      • 2. Pull an Ollama model
      • 3. Convert a book
    • Option 3: Qwen-TTS (Local, Free)
      • Option 3A: Docker Compose Profile (Recommended)
      • Option 3B: Local API Wrapper Script
      • Equivalent commands
    • Next Steps

User Guide

  • Usage
    • Basic TTS Conversion
      • Understanding –language and –translate
    • LLM-Powered Audiobook Generation
      • Using commercial LLM APIs
    • Task System
    • Two-Stage Workflow (Process / Synthesize)
      • Resumability
    • Directory Processing
    • Listing Available Options
    • Output Structure
      • Basic TTS (audify book.epub --task direct)
      • LLM Audiobook (audify book.epub)
  • Task System
    • Built-in Tasks
      • List tasks
      • Use a built-in task
    • Custom Prompt Files
      • Validate a prompt file
    • Writing Effective Prompts
      • Example: Children’s story prompt
      • Example: News briefing prompt
    • Programmatic Task Registration
  • Configuration
    • The .keys File
    • TTS Provider Comparison
    • Google Cloud TTS Configuration
    • Docker Services
    • Supported Languages
    • Pipeline Environment Variables
  • REST API
    • Starting the API
    • Endpoints
    • Examples
      • Synthesize an EPUB to MP3
      • Create an M4B audiobook
      • List available providers
      • List voices for a provider

Reference

  • CLI Reference
    • Synopsis
    • audify [OPTIONS] [PATH]
      • Arguments
      • Conversion options
      • Info / listing options
      • Examples
    • audify list-tasks
    • audify validate-prompt
      • Arguments
  • API Reference
    • CLI entry point (audify.cli)
    • Conversion factory (audify.convert)
    • Audiobook creator (audify.audiobook_creator)
    • Text-to-speech synthesizers (audify.text_to_speech)
    • REST API (audify.api.app)
      • Endpoints
      • health()
      • list_providers()
      • list_voices()
      • synthesize()
      • create_audiobook()
    • Readers
      • Domain interface (audify.domain.reader)
      • EPUB reader (audify.readers.ebook)
      • PDF reader (audify.readers.pdf)
      • Text reader (audify.readers.text)
    • Prompt system
      • Task registry (audify.prompts.tasks)
      • Prompt manager (audify.prompts.manager)
    • Utilities
      • TTS configuration (audify.utils.api_config)
      • Audio processing (audify.utils.audio)
      • M4B builder (audify.utils.m4b_builder)
      • Text utilities (audify.utils.text)
      • Constants (audify.utils.constants)
  • Architecture
    • Overview
    • Pipeline
      • Readers (audify/readers/)
      • Task System (audify/prompts/)
      • AudiobookCreator (audify/audiobook_creator.py)
      • Synthesizers (audify/text_to_speech.py)
      • Audio Processing (audify/utils/)
    • External Services
  • Using Commercial APIs with Audify
    • Supported APIs
    • Setup
      • 1. Create a .keys File
      • 2. Get API Keys
    • Usage
      • DeepSeek Examples
      • Claude Examples
      • OpenAI Examples
      • Google Gemini Examples
    • Complete Example
    • Comparing Ollama vs Commercial APIs
    • Model Recommendations
      • For Best Quality
      • For Best Value
      • For Reasoning Tasks
    • Troubleshooting
      • API Key Not Found
      • Connection Error
      • Invalid Model Name
    • Environment Variables (Alternative to .keys file)
    • Cost Considerations
    • Technical Details

Design & Architecture Decisions

  • QA Pipeline Graph
    • Cycle 1 — text-quality escalation edge
    • Cycle 2 — script-validity reroute edge
    • Cycle 3 — fidelity retry edge
    • Sub-graphs
  • Quality assurance is a cyclic graph, not a central LLM agent
    • Status
    • Considered options
    • Consequences
  • LangGraph as the cyclic-graph substrate
    • Status
    • Considered options
    • Consequences
    • Skeleton scope (deferred behaviours)

Development

  • Contributing
    • Development Setup
    • Development Workflow
      • 1. Create a branch
      • 2. Make changes
      • 3. Run checks
      • 4. Submit a PR
    • Task Commands
    • Code Quality
    • Project Structure
  • Changelog
    • [Unreleased]
      • Added
      • Changed
    • [0.1.0] - 2024-01-01
      • Added

Troubleshooting

  • Troubleshooting: No Audio Files Created
    • Common Symptom
    • Quick Diagnosis
    • Root Causes & Solutions
      • 1. TTS Provider Not Available
      • 2. Docker Networking Issue (Most Common)
      • 3. TTS Service Still Loading Model
      • 4. Port Already in Use
      • 5. CUDA/GPU Not Available
    • Detailed Debugging
      • Step-by-Step Verification
    • Log Files
    • Testing TTS Synthesis Directly
    • Environment Variables
    • Getting Help
    • Quick Reference: Working Setup
      • Host machine with Docker services
      • Inside Docker container
    • Still Having Issues?
Audify
  • Search

© Copyright 2024, Audify Contributors.

Built with Sphinx using a theme provided by Read the Docs.