i actually found out in F5 TTS if the voice you're cloning sounds clear and less distorted it can match almost exactly like the audio of that voice and its personality.
I believe this is possible if you can write the code, but if not you can try using ChatGPT to write the code for you, you will need to provide ChatGPT with all the open source and GitHub codes and documents and tell it to build you this APi endpoint also try using the smartest ChatGPT model the O1-preview model it’s very possible this can be done.
I believe it’s possible to use AMD GPU’s for this workflow as I have checked now and they didn’t specify that’s the project is NVIDIA only so that means you can use AMD as well. Let me know if it works
i actually found out in F5 TTS if the voice you're cloning sounds clear and less distorted it can match almost exactly like the audio of that voice and its personality.
Yes that’s true thanks for sharing!
click the link below to stay update with latest tutorial about Ai 👇🏻 :
www.youtube.com/@AiMotionStudio?sub_confirmation=1
Is there a way to run E2-F5 TTS in python? ie: can I run it in a server and then send the string to an API endpoint and get the response back?
I believe this is possible if you can write the code, but if not you can try using ChatGPT to write the code for you, you will need to provide ChatGPT with all the open source and GitHub codes and documents and tell it to build you this APi endpoint also try using the smartest ChatGPT model the O1-preview model it’s very possible this can be done.
the quality is not very good, no one has yet been able to achieve the quality of elevenlabs
Yes I agree, I believe they will release another open source with a better quality in the future.
what AI did you use for your own youtube video? 😃
Wink wink Elevenlabs🤣🤣
just English and Chinese ... Elevenlabs 100x more
Yeah exactly Elevelabs is way more better!
Yes, I need German :(
but not free as you want to create a thousand clone voice
Mac m1 I can ?
Yes due to not using a lot of resources, M1 mac is good enough to run any AI without the need for torch pip installation.
Any alternative for AMD ?
I believe it’s possible to use AMD GPU’s for this workflow as I have checked now and they didn’t specify that’s the project is NVIDIA only so that means you can use AMD as well. Let me know if it works
4060 ti 8 gb can do it?
Yes you can even use 2060 since the model does not use much VRAm you are fine!
I used rtx 1060 6gb vram and it worked. 44 second audio was created in 132 seconds