### Start WebUI with Default Host and Port

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Launch the WebUI using the provided Python script. The interface will be accessible at http://127.0.0.1:7860 by default.

```bash
python3 main_ui.py
```

--------------------------------

### Run Kokoro TTS with CPU via Docker

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Starts a Docker container for Kokoro TTS using CPU for processing. Ensure Docker is installed and running.

```bash
docker run -p 8880:8880 ghcr.io/remsky/kokoro-fastapi-cpu
```

--------------------------------

### Start WebUI with Custom Host and Port

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Customize the host and port when starting the WebUI. This allows you to specify a different network address or port number for accessibility.

```bash
python3 main_ui.py --host 127.0.0.1 --port 8080
```

--------------------------------

### Install Project Dependencies

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Install the required Python packages listed in the requirements.txt file. Note potential version conflicts with older Python installations.

```bash
pip install -r requirements.txt
```

--------------------------------

### Install ffmpeg on Ubuntu

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Installs the ffmpeg binary on Ubuntu systems to resolve 'FileNotFoundError: [Errno 2] No such file or directory: 'ffmpeg''.

```bash
sudo apt install ffmpeg
```

--------------------------------

### Install ffmpeg on macOS using Homebrew

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Installs the ffmpeg binary on macOS systems using Homebrew to resolve 'FileNotFoundError: [Errno 2] No such file or directory: 'ffmpeg''.

```bash
brew install ffmpeg
```

--------------------------------

### Run Kokoro TTS with GPU via Docker

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Starts a Docker container for Kokoro TTS utilizing GPU acceleration. Requires Docker with GPU support.

```bash
docker run --gpus all -p 8880:8880 ghcr.io/remsky/kokoro-fastapi-gpu
```

--------------------------------

### Install importlib-metadata for older Python versions

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Installs the 'importlib-metadata' package to resolve 'ModuleNotFoundError' on Python versions older than 3.8.

```bash
pip3 install importlib-metadata
```

--------------------------------

### Pull Docker Image

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Download the latest Docker image for the epub_to_audiobook tool from the GitHub Container Registry. Ensure Docker is installed before running this command.

```bash
docker pull ghcr.io/p0n1/epub_to_audiobook:latest
```

--------------------------------

### Run WebUI using Docker Compose

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Deploy the WebUI using Docker Compose for an easier setup. Ensure you edit the 'docker-compose.webui.yml' file to include your API keys.

```bash
# Edit docker-compose.webui.yml with your API keys
docker compose -f docker-compose.webui.yml up
```

--------------------------------

### Preview EPUB Chapter Summary

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Use the --preview option to get a summary of each chapter's character count without converting to speech. This is useful for initial analysis of the EPUB file.

```bash
python3 main.py examples/The_Life_and_Adventures_of_Robinson_Crusoe.epub output_folder --preview
```

--------------------------------

### Run EPUB to Audiobook Conversion with Piper TTS via Docker Compose

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Initiates the EPUB to audiobook conversion process using Piper TTS within a Docker container setup. This requires Docker Desktop, a downloaded Piper model, and configuration of the docker-compose.piper-example.yml file.

```sh
PATH_TO_EPUB_FILE=./Your_epub_file.epub OUTPUT_DIR=$(pwd)/path/to/audiobook_output docker compose -f docker-compose.piper-example.yml up --build
```

--------------------------------

### Set Environment Variables for TTS Providers

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Configure environment variables for Azure TTS or OpenAI TTS before starting the WebUI. Replace placeholders with your actual API keys and region.

```bash
export MS_TTS_KEY=<your_subscription_key>      # For Azure TTS
export MS_TTS_REGION=<your_region>             # For Azure TTS
export OPENAI_API_KEY=<your_openai_api_key>    # For OpenAI TTS
export OPENAI_BASE_URL=<custom_endpoint>       # Optional: For custom OpenAI-compatible endpoints
```

--------------------------------

### Basic EPUB to Audiobook Conversion with Piper TTS

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Converts an EPUB file to an audiobook using Piper TTS with minimal parameters. Ensure Piper TTS is installed and the onnx model file is specified. The 'piper' executable should be in your system's PATH.

```sh
python3 main.py "path/to/book.epub" "path/to/output/folder" --tts piper --model_name <path_to>/en_US-libritts_r-medium.onnx
```

--------------------------------

### Clone Repository and Navigate

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Clone the project repository and change the directory to the project's root.

```bash
git clone https://github.com/p0n1/epub_to_audiobook.git
cd epub_to_audiobook
```

--------------------------------

### Display Help and Options

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Execute the script with the `-h` flag to view all available command-line options and their descriptions. This is useful for understanding the script's full capabilities and configuration.

```bash
python3 main.py -h
```

--------------------------------

### Use OpenAI-Compatible Service with Custom URL and Voice

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Run an EPUB to audiobook conversion using an OpenAI-compatible service by setting the OPENAI_BASE_URL environment variable. An API key is still required but can be nonsensical.

```shell
docker run -i -t --rm -v ./:/app -e OPENAI_BASE_URL=http://127.0.0.1:8000/v1 -e OPENAI_API_KEY=nope ghcr.io/p0n1/epub_to_audiobook your_book.epub audiobook_output --tts openai --voice_name=skippy --model_name=tts-1-hd
```

--------------------------------

### Create and Activate Virtual Environment

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Create a Python virtual environment and activate it for managing project dependencies.

```bash
python3 -m venv venv
source venv/bin/activate
```

--------------------------------

### Configure Environment and Run Script with Kokoro TTS

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Sets environment variables for OpenAI compatibility and executes the main script with Kokoro TTS. Requires the script to be in the current directory.

```bash
export OPENAI_BASE_URL=http://localhost:8880/v1
export OPENAI_API_KEY="fake"
python main.py path/to/epub output-dir --tts openai --voice_name "af_bella(3)+af_alloy(1)" --model_name "tts-1"
```

--------------------------------

### Full Script Options Help

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

This is the detailed output of the `python3 main.py -h` command, listing all available arguments and their explanations. It covers TTS provider selection, logging levels, preview mode, language settings, newline modes, title parsing strategies, chapter range selection, outputting text files, removing endnotes, and search/replace functionality.

```bash
usage: main.py [-h] [--tts {azure,openai,edge,piper}]
               [--log {DEBUG,INFO,WARNING,ERROR,CRITICAL}] [--preview]
               [--no_prompt] [--language LANGUAGE]
               [--newline_mode {single,double,none}]
               [--title_mode {auto,tag_text,first_few}]
               [--chapter_start CHAPTER_START] [--chapter_end CHAPTER_END]
               [--output_text] [--remove_endnotes]
               [--search_and_replace_file SEARCH_AND_REPLACE_FILE]
               [--worker_count WORKER_COUNT]
               [--voice_name VOICE_NAME] [--output_format OUTPUT_FORMAT]
               [--model_name MODEL_NAME] [--voice_rate VOICE_RATE]
               [--voice_volume VOICE_VOLUME] [--voice_pitch VOICE_PITCH]
               [--proxy PROXY] [--break_duration BREAK_DURATION]
               [--piper_path PIPER_PATH] [--piper_speaker PIPER_SPEAKER]
               [--piper_sentence_silence PIPER_SENTENCE_SILENCE]
               [--piper_length_scale PIPER_LENGTH_SCALE]
               input_file output_folder

Convert text book to audiobook

positional arguments:
  input_file            Path to the EPUB file
  output_folder         Path to the output folder

options:
  -h, --help            show this help message and exit
  --tts {azure,openai,edge,piper}
                        Choose TTS provider (default: azure). azure: Azure
                        Cognitive Services, openai: OpenAI TTS API. When using
                        azure, environment variables MS_TTS_KEY and
                        MS_TTS_REGION must be set. When using openai,
                        environment variable OPENAI_API_KEY must be set.
  --log {DEBUG,INFO,WARNING,ERROR,CRITICAL}
                        Log level (default: INFO), can be DEBUG, INFO,
                        WARNING, ERROR, CRITICAL
  --preview             Enable preview mode. In preview mode, the script will
                        not convert the text to speech. Instead, it will print
                        the chapter index, titles, and character counts.
  --no_prompt           Don't ask the user if they wish to continue after
                        estimating the cloud cost for TTS. Useful for
                        scripting.
  --language LANGUAGE   Language for the text-to-speech service (default: en-
                        US). For Azure TTS (--tts=azure), check
                        https://learn.microsoft.com/en-us/azure/
                        services/speech-service/language-
                        support?tabs=tts#text-to-speech for supported
                        languages. For OpenAI TTS (--tts=openai), their API
                        detects the language automatically. But setting this
                        will also help on splitting the text into chunks with
                        different strategies in this tool, especially for
                        Chinese characters. For Chinese books, use zh-CN, zh-
                        TW, or zh-HK.
  --newline_mode {single,double,none}
                        Choose the mode of detecting new paragraphs: 'single',
                        'double', or 'none'. 'single' means a single newline
                        character, while 'double' means two consecutive
                        newline characters. 'none' means all newline
                        characters will be replace with blank so paragraphs
                        will not be detected. (default: double, works for most
                        ebooks but will detect less paragraphs for some
                        ebooks)
  --title_mode {auto,tag_text,first_few}
                        Choose the parse mode for chapter title, 'tag_text'
                        search 'title','h1','h2','h3' tag for title,
                        'first_few' set first 60 characters as title, 'auto'
                        auto apply the best mode for current chapter.
  --chapter_start CHAPTER_START
                        Chapter start index (default: 1, starting from 1)
  --chapter_end CHAPTER_END
                        Chapter end index (default: -1, meaning to the last
                        chapter)
  --output_text         Enable Output Text. This will export a plain text file
                        for each chapter specified and write the files to the
                        output folder specified.
  --remove_endnotes     This will remove endnote numbers from the end or
                        middle of sentences. This is useful for academic
                        books.
  --search_and_replace_file SEARCH_AND_REPLACE_FILE

```

--------------------------------

### Convert EPUB to Audiobook

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Run the main script to convert an EPUB file to an audiobook. Specify the input EPUB file, the output folder, and optionally a TTS provider using the `--tts` flag.

```bash
python3 main.py <input_file> <output_folder> [options]
```

--------------------------------

### Run Audiobook Generation with Kokoro TTS via Docker Compose

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Executes the audiobook generation process using Docker Compose with Kokoro TTS. Replace placeholder values with your specific file paths and desired voice name.

```bash
PATH_TO_EPUB_FILE=./Your_epub_file.epub OUTPUT_DIR=$(pwd)/path/to/audiobook_output VOICE_NAME=Your_desired_voice docker compose -f docker-compose.kokoro-example.yml up --build
```

--------------------------------

### Run Docker Container with OpenAI TTS

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Execute the epub_to_audiobook tool within a Docker container using OpenAI TTS. Mounts the current directory and sets the OpenAI API key environment variable.

```bash
docker run -i -t --rm -v ./:/app -e OPENAI_API_KEY=$OPENAI_API_KEY ghcr.io/p0n1/epub_to_audiobook your_book.epub audiobook_output --tts openai
```

--------------------------------

### OpenAI TTS with Preview and Text Output

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Enable preview mode and text output for OpenAI TTS, which displays chapter information and exports the text instead of audio.

```sh
python3 main.py "path/to/book.epub" "path/to/output/folder" --tts openai --preview --output_text
```

--------------------------------

### Run Docker Container with Azure TTS

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Execute the epub_to_audiobook tool within a Docker container using Azure Text-to-Speech. Mounts the current directory and sets necessary environment variables for TTS.

```bash
docker run -i -t --rm -v ./:/app -e MS_TTS_KEY=$MS_TTS_KEY -e MS_TTS_REGION=$MS_TTS_REGION ghcr.io/p0n1/epub_to_audiobook your_book.epub audiobook_output --tts azure
```

--------------------------------

### Generate Audiobook from EPUB

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Execute the main script with the EPUB file path and an output directory. This command generates MP3 files for each chapter using default TTS settings.

```bash
python3 main.py examples/The_Life_and_Adventures_of_Robinson_Crusoe.epub output_folder
```

--------------------------------

### Convert EPUB with Search and Replace

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Convert an EPUB file to an audiobook using a specified search and replace configuration file. This allows for text normalization and pronunciation adjustments.

```bash
python3 main.py examples/The_Life_and_Adventures_of_Robinson_Crusoe.epub output_folder --search_and_replace_file search.conf
```

--------------------------------

### Search and Replace Configuration

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Define search and replace rules in a configuration file to modify text within the EPUB before conversion. Each line should contain a regex search and its replacement, separated by '=='.

```text
# this is the general structure
<search>==<replace>
# this is a comment
# fix cardinal direction abbreviations
N.E.==north east
# be careful with your regexes, as this would also match Sally N. Smith
N.==north
# pronounce Barbadoes like the locals
Barbadoes==Barbayduss
```

--------------------------------

### Set Environment Variables for TTS APIs

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Configure necessary environment variables for Azure Text-to-Speech or OpenAI Text-to-Speech API credentials.

```bash
export MS_TTS_KEY=<your_subscription_key> # for Azure
export MS_TTS_REGION=<your_region> # for Azure
export OPENAI_API_KEY=<your_openai_api_key> # for OpenAI
```

--------------------------------

### Basic OpenAI TTS Conversion

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Perform a basic EPUB to audiobook conversion using OpenAI TTS with default settings.

```sh
python3 main.py "path/to/book.epub" "path/to/output/folder" --tts openai
```

--------------------------------

### Basic Azure TTS Conversion

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Perform a basic EPUB to audiobook conversion using Azure TTS with default settings.

```sh
python3 main.py "path/to/book.epub" "path/to/output/folder" --tts azure
```

--------------------------------

### Specify Custom Piper TTS Executable Path

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Converts an EPUB to an audiobook while specifying a custom path to the Piper TTS executable using the `--piper_path` parameter.

```sh
python3 main.py "path/to/book.epub" "path/to/output/folder" --tts piper --model_name <path_to>/en_US-libritts_r-medium.onnx --piper_path <path_to>/piper
```

--------------------------------

### Specify Azure Voice and Language

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Use --voice_name and --language options to select a specific voice and language for Azure TTS. Consult Azure documentation for available options.

```bash
python3 main.py <input_file> <output_folder> --voice_name en-GB-LibbyNeural --language en-GB
```

--------------------------------

### Azure TTS with Custom Language, Voice, and Logging

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Convert an EPUB to an audiobook using Azure TTS with a specified Chinese voice and language, and set the log level to DEBUG for detailed output.

```sh
python3 main.py "path/to/book.epub" "path/to/output/folder" --tts azure --language zh-CN --voice_name "zh-CN-YunyeNeural" --log DEBUG
```

--------------------------------

### Basic Edge TTS Conversion

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Perform a basic EPUB to audiobook conversion using Edge TTS with default settings.

```sh
python3 main.py "path/to/book.epub" "path/to/output/folder" --tts edge
```

--------------------------------

### OpenAI TTS with HD Model and Specific Voice

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Convert an EPUB to an audiobook using OpenAI TTS with the high-definition model and a specified voice.

```sh
python3 main.py "path/to/book.epub" "path/to/output/folder" --tts openai --model_name "tts-1-hd" --voice_name "fable"
```

--------------------------------

### Specify Output Format for Piper TTS Audio

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Converts an EPUB to an audiobook using Piper TTS and specifies the output audio format (e.g., 'opus', 'mp3') using the `--output_format` parameter. Piper TTS defaults to 'wav' or raw format.

```sh
python3 main.py "path/to/book.epub" "path/to/output/folder" --tts piper --model_name <path_to>/en_US-libritts_r-medium.onnx --piper_speaker 256 --piper_length_scale 1.5 --piper_sentence_silence 0.5 --output_format opus
```

--------------------------------

### Edge TTS with Custom Language, Voice, and Logging

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Convert an EPUB to an audiobook using Edge TTS with a specified Chinese voice and language, and set the log level to DEBUG for detailed output.

```sh
python3 main.py "path/to/book.epub" "path/to/output/folder" --tts edge --language zh-CN --voice_name "zh-CN-YunxiNeural" --log DEBUG
```

--------------------------------

### Select Piper TTS Voice with Voice Name

Source: https://github.com/p0n1/epub_to_audiobook/blob/main/README.md

Converts an EPUB to an audiobook and selects a specific voice from a Piper TTS model that supports multiple voices using the `--piper_speaker` parameter.

```sh
python3 main.py "path/to/book.epub" "path/to/output/folder" --tts piper --model_name <path_to>/en_US-libritts_r-medium.onnx --piper_speaker 256
```