# CorentinJ/Real-Time-Voice-Cloning
**URL:** https://community.openconversational.ai/t/corentinj-real-time-voice-cloning/7168
**Category:** Archive - Machine Learning
**Created:** [September 4, 2019, 3:37am UTC](https://community.openconversational.ai/t/corentinj-real-time-voice-cloning/7168 "2019-09-04T03:37:06Z")
**Posts on this page:** 5
**Page:** 1
### Author:  [@FruityWelsh](https://community.openconversational.ai/u/FruityWelsh)
#### Post date: [September 4, 2019, 3:37am UTC](https://community.openconversational.ai/t/corentinj-real-time-voice-cloning/7168/1 "2019-09-04T03:37:06Z")
> **[CorentinJ/Real-Time-Voice-Cloning](https://github.com/CorentinJ/Real-Time-Voice-Cloning)**
>
> Clone a voice in 5 seconds to generate arbitrary speech in real-time - CorentinJ/Real-Time-Voice-Cloning
Thoughts?
---
### Author:  [@gez-mycroft](https://community.openconversational.ai/u/gez-mycroft)
#### Post date: [September 4, 2019, 3:54pm UTC](https://community.openconversational.ai/t/corentinj-real-time-voice-cloning/7168/2 "2019-09-04T15:54:26Z")
It’s exciting to see these adapted voices getting better. Particularly for users of alternative communication technologies who either had to pay thousands of dollars to get a custom voice, or have the same 3 voices as everyone else who uses the same device as they do.
Speaker identification would certainly be useful for Mycroft too…
Have you tried it out on your own voice?
---
### Author:  [@FruityWelsh](https://community.openconversational.ai/u/FruityWelsh)
#### Post date: [September 4, 2019, 9:08pm UTC](https://community.openconversational.ai/t/corentinj-real-time-voice-cloning/7168/3 "2019-09-04T21:08:03Z")
It currently requires a cuda enabled GPU, I’m sure there is a work around (ie use the torch-rocm docker image, and run it from in there and do some code massaging), I just have done that yet.
I would be really interested in anyone else’s experiences though!
---
### Author:  [@gez-mycroft](https://community.openconversational.ai/u/gez-mycroft)
#### Post date: [September 5, 2019, 1:03am UTC](https://community.openconversational.ai/t/corentinj-real-time-voice-cloning/7168/4 "2019-09-05T01:03:10Z")
If you want to try it out without dropping a lot of cash on hardware, [Fast.ai](https://course.fast.ai/) has some suggestions and guides on how to get started on different cloud platforms.
---
### Author:  [@baconator](https://community.openconversational.ai/u/baconator)
#### Post date: [September 5, 2019, 4:34am UTC](https://community.openconversational.ai/t/corentinj-real-time-voice-cloning/7168/5 "2019-09-05T04:34:02Z")
How do you save a model and run it as a server? That’s what I want to know.
Quality is so-so based on the samples, though. Wonder if there’s like a minute version that improves things.