https://github.com/C-Loftus/QuickPiperAudiobook

With one command, create a natural-sounding audiobook from a variety of input formats (epub, mobi, txt, PDF, HTML and more!)
https://github.com/C-Loftus/QuickPiperAudiobook

audiobooks piper productivity tts

Last synced: 4 days ago
JSON representation

With one command, create a natural-sounding audiobook from a variety of input formats (epub, mobi, txt, PDF, HTML and more!)

• Host: GitHub
• URL: https://github.com/C-Loftus/QuickPiperAudiobook
• Owner: C-Loftus
• License: agpl-3.0
• Created: 2024-07-27T01:06:28.000Z (7 months ago)
• Default Branch: master
• Last Pushed: 2025-02-01T03:05:38.000Z (10 days ago)
• Last Synced: 2025-02-07T06:38:53.801Z (4 days ago)
• Topics: audiobooks, piper, productivity, tts
• Language: Go
• Homepage:
• Size: 8.12 MB
• Stars: 615
• Watchers: 6
• Forks: 33
• Open Issues: 4
• Metadata Files:
  • Readme: readme.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

• my-awesome-github-stars - C-Loftus/QuickPiperAudiobook - With one command, create a natural-sounding audiobook from a variety of input formats (epub, mobi, txt, PDF, HTML and more!) (Go)

README

        
# QuickPiperAudiobook

Create a natural audiobook for any text content with one command. 

 - Converts [PDFs, epub, txt, mobi, djvu, HTML, docx, and more](https://manual.calibre-ebook.com/generated/en/ebook-convert.html)

 - All conversion is done offline and is entirely private

 - Uses [piper models](https://rhasspy.github.io/piper-samples/); supports many languages

Listen to sample output [ here ](./examples/)

## Installing

1. Grab a prebuilt [release](https://github.com/C-Loftus/QuickPiperAudiobook/releases/)

    * (Or build from source using `go mod tidy && go build`)

2. Download `ebook-convert` and make sure it is in your PATH. (This is often bundled with [calibre](https://calibre-ebook.com/))

> [!NOTE]  

> You don't need to have piper installed. This program manages piper and the associated models

## Usage 

* Pass in either a local file or a remote URL to generate an audiobook: 

   * i.e. `./QuickPiperAudiobook test.txt`

* For a full list of options use the `--help` flag

   * i.e. `./QuickPiperAudiobook --help`

### Non-English / UTF-8

* Grab a model for the language of choice (.onnx and .json) from the [piper models](https://rhasspy.github.io/piper-samples/)

  * i.e. `pl_PL-gosia-medium.onnx` and corresponding `pl_PL-gosia-medium.onnx.json` (rename if needed)

* Put them in `~/.config/QuickPiperAudiobook/`

* Use the `--speak-utf-8` and `--model=`  flags to specify you want utf characters to be spoken with a specific model

  * i.e. `./QuickPiperAudiobook --speak-utf-8 --model=pl_PL-gosia-medium.onnx MaszynaTuringa_Wikipedia.pdf`

> [!NOTE]  

> Consider specifying this model as the default in the configuration file if you plan to use it frequenlty

### Configuring

* A configuration file at `~/.config/QuickPiperAudiobook/config.yml` will be automatically created. 

* You can specify a default model and output path so you do not need to specify these args each time.

* You can use any arbitrary model by putting the associated `.onnx` and `.onnx.json` file for it in `~/.config/QuickPiperAudiobook/`

```yml

# An example for `~/.config/QuickPiperAudiobook/config.yml`

# the default output directory to use if the user does not specify --output in the cli args

output: ~/Audiobooks

# the default model to use if the user does not specify --model in the cli args

model: "en_US-hfc_female-medium.onnx"

```

## Notes

Piper does not support progress output. Long audiobooks may take a long time to generate since all computation is being done locally. 

This repo has only been tested on Linux.