The client needed a custom web application that enabled them to perform Text to Speech (TTS), Singing Voice Conversion (SVC), and Text to Audio (TTA). The client also had good computational power available.
Knowing that sufficient computing power was available, I suggested to the client that we leverage free AI models, tailor them to their specific needs, and deploy them directly on their local infrastructure. This approach would grant them greater independence.
P.S. It worked brilliantly.
Thanks to Hanks Trill for permission to publish open source code.
Arthur took the work very seriously. I hardly had to lift a finger, he did everything himself. If you don't know much about IT, like me, you should definitely reach out to Arthur.