3 Comments
User's avatar
Bonnie Civalleri's avatar

It would be helpful for my understanding if you would add a transcription of Dr. Speicher explanations.Thank You

Expand full comment
Courageous Truth's avatar

Hi Bonnie. Thank you for the idea. Haven't thought of that. I'll have to give it a go.

Expand full comment
Betsy McDonel Herr, Ph.D.'s avatar

David I posted this on X awhile ago but I don't think you saw it. Just a helpful suggestion that might be more useful than transcripts:

Listening to your linked speech on the givesendgo page, I found that to be more natural, lively, with more personality than the edit on the interview with @DrTrozzi

There is a fascinating video I saw a year ago by a YouTuber I follow who discusses ballet history with lots of dance clips and narration. He experimented with AI text to speech software for cloning his own voice. The process cut down on production time allowing later changes and additions. He used ElevenLabs. You would give the software samples of speech from clips where you have periods of fluency.

https://youtu.be/1uo2t9ZOrlU?si=jKBhOZyXd8PxzbCR

I remember a similar spectacular use of voice cloning technology when someone on X produced Javier Milei giving a speech in English that he had given in Spanish. It was his own voice, cloned for the translation. Incredible. I can see how the software could be great for formal presentations, but also wonder if it can be adapted for use in an interactive live setting so that one could type an answer to a question, in sections, have it spoken in your voice, all faster and more comfortably.

https://youtu.be/1uo2t9ZOrlU?si=jKBhOZyXd8PxzbCR

Technology can be used for good in this case. It could be quite incredible to hear your own voice, smoothed out and normalized.

All the best!

Expand full comment