Q: Future plans for more natural voices and integration of open-source solutions?
Hello Simon,
I noticed that the voices provided in the current AppSumo deal version of gspeech sound somewhat less organic compared to current industry standards.
Are there plans to integrate improved, more natural-sounding voices in the future, especially as voice technology continues to advance?
Additionally, are you considering leveraging high-quality open-source solutions, such as Zonos (https://www.youtube.com/watch?v=kHJVovkrJ2o), which already offer very realistic and natural voices?
https://github.com/Zyphra/Zonos
Thanks for clarifying your roadmap and future developments!
Best regards,
Simon_Poghosyan
Mar 21, 2025A: Hello,
Thank you for your feedback! I agree, voice technology is advancing rapidly. Our current models are trained on a vast amount of data and perform well for most use cases, but there’s always room for improvement as the industry evolves.
Thanks for sharing the video and GitHub link to Zonos. We’re currently working on GSpeech Studio, which will include a broader range of voices beyond what we offer now. Some of these will be suitable for the lifetime deal, and I’m committed to making them available to the AppSumo community as part of the package.
I appreciate your input and am excited to keep you updated on our roadmap as we continue to enhance GSpeech!
Thanks! :)