https://github.com/codevideo/pontificator
Generate studio quality dictated audio files from books, articles, and blog posts.
https://github.com/codevideo/pontificator
Last synced: about 1 year ago
JSON representation
Generate studio quality dictated audio files from books, articles, and blog posts.
- Host: GitHub
- URL: https://github.com/codevideo/pontificator
- Owner: codevideo
- Created: 2024-02-18T12:17:08.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2025-01-15T11:34:16.000Z (over 1 year ago)
- Last Synced: 2025-03-25T12:18:49.711Z (about 1 year ago)
- Language: TypeScript
- Size: 68.4 KB
- Stars: 2
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# @fullstackcraftllc/pontificator
Generate studio quality dictated audio files from books, articles, and blog posts.
See an example of a dictated blog post [on one of Chris's blog posts](https://chrisfrew.in/blog/blazor-on-netlify-with-environment-variables/).
## Install in a Node.js Project
```shell
npm install @fullstackcraftllc/pontificator
```
## CLI Usage
```shell
npx @fullstackcraftllc/pontificator
```
## Prerequisites
If you are fine with using the built in text-to-speech software, you can skip this section. If you want to use a payed text-to-speech software, you will need to set up an account and get an API key. We currently support the following vendors:
- Eleven Labs. You'll need to set an `ELEVEN_LABS_API_KEY` - if defined in `.env`, the Eleven Labs text-to-speech API will be used, optionally additionally with `ELEVEN_LABS_VOICE_ID`.
- More coming soon!
## Installation
Install dependencies:
```shell
npm install
```
## Example
Paste any markdown into the `example/blog-post.mdx` file. (Or leave as-is for the example.)
Then, run `pontificator` with the following command:
```python
npm run start example/blog-post.mdx
```
This will clean up the markdown, chunk it for API calls, and combine the audio chunks to a single .mp3 file reflecting the entire text content of the blog post.
If all goes well, you should get an `audio.mp3` file produced in the `example` directory.
### Validation and Verification
Consider validating the produced text with CodeVideo's other tool, [`speech-shield`](https://github.com/codevideo/speech-shield)