Welcome!
Table of Contents (TOC)
The table of contents is defined in the toc.yml
file, which can be divided into two parts:
- The essential and/or optional details needed to generate each video.
- The basic course structure.
As an example:
[Essential and/or optional details]
name: Hello world
version: v1
email: help@lupo.ai, dev@lupo.ai
speaker: Jenny
speed: 1.1
pitch: 1.2
style: default
slides: false
resolution: 720
[Basic course structure]
chapters:
- name: Chapter One
sections:
- name: Test
href: hello_world.md
generate: true
- name: Chapter Two
sections:
- name: Test_2
href: hello_world_2.md
generate: false
Essential and/or optional details
As essential and/or optional details needed to generate each video, we have:
Field Name | Required | Description | Example |
name |
Yes | The name of the course | name: Course Creator Demo |
version |
No Sets default: v1 |
A code in case you need to differentiate or update the same course | version: v1 |
email |
No Sets default: GitHub email |
A comma-separated list of email addresses to send the generated videos | email: email_1@example.com, email_2@example.com, ... |
speaker |
No Sets default: Aria |
The name of the speaker who will provide the voiceover for the generated videos. | speaker: Abbi You can find the list of available speakers and their styles here: Speakers | Emotions |
speed |
No Sets default: 1 |
The speed of the video. Accepts a float value from 0.5 to 2 with 1 being the normal speed | speed: 1.5 would make the video 1.5 times faster than normal. |
pitch |
No Sets default: 1 |
The pitch of the video. Accepts a float value from 0.5 to 1.5 with 1 being the normal pitch | pitch: 1.2 would increase the pitch of the audio by 20%. |
style |
No Sets default: default |
Speaking style to express different emotions of the speaker and is applied to all generated videos | style: excited You can find the list of available speakers and their styles here: Speakers | Emotions |
slides |
No Sets default: False |
A boolean value indicating if includes a PowerPoint presentation, PDF document, and HTML document for each video | slides: True |
transcript |
No Sets default: False |
A boolean value indicating if includes a transcript for each video | transcript: True |
resolution |
No | A value that indicates the resolution of the produced video, with two values currently supported: 720 and 1080 | resolution: 720 |
Basic course structure
[Essential and/or optional details previously selected]
chapters:
- name: [Chapter 1 Name]
sections:
- name: [Section Name]
href: [Path/to/file.md]
generate: [true|false] # Optional Section prompt
speaker: Aria # Optional section prompt override, defaults: chapter or course prompts
speed: 1.2 # Optional section prompt override, defaults: chapter or course prompts
pitch: 1.3 # Optional section prompt override, defaults: chapter or course prompts
style: friendly # Optional section prompt override, defaults: chapter or course prompts
- name: [Chapter 2 Name]
sections:
- name: [Section 1 Name]
href: [Path/to/file.md]
- name: [Section 2 Name]
href: [Path/to/file.md]
generate: [true|false] # Optional Chapter Indication
combine: [true|false] # Optional Chapter Indication
You should consider proper indentation in the YAML file is of utmost importance. It is not just about maintaining a neat and organized appearance.
chapters:
: This is the main container for all the chapters or episodes of the video series. Each chapter is listed as a sub-item under this section.name: [Chapter name]
: Within the chapters section, you define the name of each chapter or episode. This name should give a clear idea of the content covered in that particular video.sections:
: For each chapter, you can create multiple sections, each representing a specific segment or topic within the video.name: [Section name]
: Under each chapter, you define the name of the section. This name helps viewers understand the specific focus of that particular segment.href: [Path/to/file.md]
: This field contains the file path to the Markdown file associated with the section. The Markdown file likely contains the script or content for the corresponding section of the video.
And optional indications:
generate: [true|false]
: Specifies whether the section or chapter should be included in the generated output. If not specified, defaults to true.speaker, speed, pitch, style
: Optional parameters allowing customization of speech synthesis settings. These parameters can override default configurations. If not provided at the section level, defaults are inherited from higher levels (chapter or course configurations).combine: [true|false]
: Flag indicating whether sections or chapters should be combined if desired. If set to true, sections or chapters can be merged as needed.