Request a feature: Integrate Distinct Character Voices (from VoxNovel) #891
ATAD4NRY4N
started this conversation in
General
Replies: 1 comment
-
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Is your feature request related to a problem? Please describe.
Currently, ebook2audiobook generates audiobooks using a single voice for the entire narration, including character dialogues. While this is functional, it can sometimes lead to a less immersive listening experience, as it can be challenging to differentiate between speakers, especially in books with many characters or extensive dialogue.
Describe the solution you'd like
I propose porting the character-specific voice features from the VoxNovel project (https://github.com/DrewThomasson/VoxNovel) into ebook2audiobook. This would allow for:
Unique Voices for Each Character: Each character in the audiobook would have a distinct, recognizable voice.
Accent Capabilities: The ability to assign specific accents to characters, further enhancing their personality and the listener's immersion.
Improved Listener Engagement: Listeners would be able to easily identify who is speaking, leading to a much more engaging and enjoyable audiobook experience.
Describe alternatives you've considered
Currently, there aren't many readily available tools that offer this level of character voice distinction for audiobook generation from ebooks. Manually editing audio after generation to apply different voices would be incredibly time-consuming and impractical for most users.
Additional context
The VoxNovel repository already demonstrates the core functionality of identifying characters and assigning unique voices. Integrating this intelligence into ebook2audiobook would leverage existing work and significantly elevate the quality and appeal of the generated audiobooks. The VoxNovel project uses booknlp for character attribution and coqui tts for voice generation, which could potentially be integrated or adapted.
This feature would truly bring the characters to life and make the audiobooks generated by ebook2audiobook stand out.
Beta Was this translation helpful? Give feedback.
All reactions