Is your feature request related to a problem? Please describe.
Currently you can do one off text to speech using the studio and instructions, however you can't use voice design models to create, save and design a voice. The only option is to clone a voice in the operate->voice menu. This would propose generations and then if the voice cannot be saved directly from the generation, that it takes the output audio from the instructions sent to the voice design model and clones the output to produces a final voice
Describe the solution you'd like
Using the same instructions field, have support for designing a voice and saving the voice design as a personality for re-use later on
Describe alternatives you've considered
Storing performing this info manually. Create a voice in voice design, download it. Go to Voice Library and create a new personality with the downloaded voice as a reference
Additional context
Continuing on from Issue-11609
Is your feature request related to a problem? Please describe.
Currently you can do one off text to speech using the studio and instructions, however you can't use voice design models to create, save and design a voice. The only option is to clone a voice in the
operate->voicemenu. This would propose generations and then if the voice cannot be saved directly from the generation, that it takes the output audio from theinstructionssent to the voice design model and clones the output to produces a final voiceDescribe the solution you'd like
Using the same
instructionsfield, have support for designing a voice and saving the voice design as a personality for re-use later onDescribe alternatives you've considered
Storing performing this info manually. Create a voice in voice design, download it. Go to Voice Library and create a new personality with the downloaded voice as a reference
Additional context
Continuing on from Issue-11609