Voice Design Audio Funktionen

Hello Intel AI Playground Team,

First of all, thank you for the 3.1.0-alpha release. The progress on the Studio version is impressive.

I am currently working with a Dual Intel Arc A770 (16GB) setup. As I am in the process of producing an audiobook/audio drama based on my own book, I have noticed a significant gap in the current ecosystem: there is a lack of accessible tools for Voice Design and Voice Cloning that natively support Intel Arc hardware without falling back to the CPU.

My Suggestion:
Please consider integrating a dedicated Voice Design/Cloning tool (or a specialized OpenVINO-accelerated node/module) into AI Playground Studio. Having a solution that can leverage the power of at least one (or ideally both) Arc GPUs for high-quality, local voice synthesis would be a game-changer for creators in the Intel ecosystem.

This feature would be incredibly beneficial for long-form projects like audiobooks where consistent, high-fidelity voice output is required.

Thank you for your hard work and for considering this request!

Best regards,

Stephan Riepshoff