Hi , Sharon,
Despite being in holiday mood, you are quite fast with your reply ! Thanks
I still need your confirmation that , when uploaded onto Persona.ai, those hundreds of hours of audio files will get converted into Memory Blocks ( from which , ANSWERS are generated ). We need this to entice those politicians !
Regard,
hemen
Subject: RE: FW: UPLOADING MY AUDIO FILE
Hey Hemen,
Would such separate / single ( unconsolidated ) uploads manage to create my “ Voice Clone “ , which can “ speak out “ in my voice, ANSWERS when questions are posed to my personal.ai ? Or , to create a “ Voice Clone “ require us to merge all 123 files into ONE file, before uploading ?
Right now - it only needs about 30 minutes of speech for the voice clone to happen. It actually doesn't matter that it's separate, the 30 minutes are usually split into single utterances (one sentence / utterance).
Holidays is a little tricky as I am waiting on a few people to coordinate on working on your voice clone but I hope to have good news by NY. The one that we created for me is very promising and I can't wait to hear yours as well.
Cheers,
Sharon
On Mon, Dec 19, 2022 at 6:24 PM, Hemen Parekh <hcp@recruitguru.com> wrote:
Hello , Sharon,
Thanks for this feedback . We will await your instructions
As you are aware, we sent to you 123 audio files ( for 123 English Poems ), each about 2 – 3 minutes long
I presume, each would require separate upload ( if your software is configured to convert each into a separate Memory Block by Speech-to-Text conversion )
Would such separate / single ( unconsolidated ) uploads manage to create my “ Voice Clone “ , which can “ speak out “ in my voice, ANSWERS when questions are posed to my personal.ai ? Or , to create a “ Voice Clone “ require us to merge all 123 files into ONE file, before uploading ?
Whereas for Politicians / Celebrities, voice cloning is an important reason to become members of Personal.ai, they may not have much “ written digital content “ ( to help generate thousands of Memory Blocks.)
They may have their “ Recorded Speeches “ running into hundreds of hours. If these speeches ( audio files ), can be uploaded and converted to text / memory blocks, then we could get thousands of them to join Personal.ai !
Sometime back, Suman had hinted at this
Regards,
hemen
Subject: Re: FW: UPLOADING MY AUDIO FILE
Hey Hemen -
We are actually working on a audio upload version where you can do it yourself. Should be in production sometime EOW here and I can send you a note/instruction on how your team can do the upload.
Cheers,
Sharon
On Mon, Dec 19, 2022 at 4:42 AM, Hemen Parekh <hcp@recruitguru.com> wrote:
Sharon,
I believe we have already sent to you my AUDIO files in Mp4 format . Pl confirm
What next ?
Regards,
hemen
Subject: Fwd: UPLOADING MY AUDIO FILE
Hi Mr.Parekh,
Copying Sharon here, our CTO, she recently discovered a method to create your voice clone! She can also tell you what Audio formats are and are not possible. Currently Mp4 seems is possible via Google Drive. If you have the audio recordings in that format within our Drive folder for you, if your team copy & pastes the share link for each file into your stack, the transcription will be generated- Sharon to confirm.
Best,
Sahiti
---------- Forwarded message ---------
Sahiti,
I vaguely remember that sometime back you had confirmed the possibility of uploading on personal.ai, audio recordings ( as long as in English and in my own voice )
I believe this feature was also mentioned in one of your support team’s circular
I would like to experiment by uploading audio file of my English poem recitals to see how many memory blocks it generates
Can you please guide the process to be followed ?
Regards,
Hemen
No comments:
Post a Comment