This workflow helps you clone voice of anyone with just a simple voice clip under 10 sec. Upload a voice sample, write what you want to hear in that voice and click queue, Done ! Its that simple to do ! ;) I suggest you use atleast a Large GPU for saving time and quick outputs.
For better output : 👇
Tips to Use ✅
1️⃣ The driving audio ( the voice to be cloned) node works best if the length of the audio clip is kept under 10 sec.
2️⃣ The speed and tone of the input voice highly influence the ouput, so try and test different audio to get the best output.
3️⃣ Tweak the text using, commas, full stop, space or even change the models (i use F5) see the difference in output and choose which output fits to your need. Enjoy and have fun.