-
Notifications
You must be signed in to change notification settings - Fork 71
Open
Description
Title: Add Kokoro TTS as a Voiceover Backend
Description
Kokoro TTS is a lightweight, high-quality text-to-speech model that performs well even on edge devices. Its voice clarity is significantly better than several of the current open-source options available in the project, while still being extremely resource-efficient.
Why Kokoro
- Offers multiple natural-sounding voices
- Small model size suitable for low-resource environments
- Strong audio quality despite being compact
Benefits
Adding Kokoro would make voiceovers more accessible for users who don’t have paid API keys or stronger hardware to run large models. This expands the usability of the voiceover module and supports more open-source workflows.
Additional Comments
I’d be happy to work on this feature if the maintainers decide to assign it to me.
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels