Respeecher tested early real-time voice synthesis models on laryngectomy patients in 2022
Alex Serduk · How we cloned Reid Hoffman’s voice using AI | Masters of Scale · May 23, 2024 · at 13:00
Alex Serdiuk, CEO of Respeecher, discusses medical applications of speech-to-speech AI technology for patients with speech disorders.
0:00 / 0:08exact quote · 8.4s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“Back in twenty-twenty-two, we tried our first rough real-time models on patients with laryngectomy.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Alex Serduk
AI voice startup Respeecher recreated Elvis Presley for America's Got Talent
“We were on America Got Talent in the voice of Elvis Presley.”
Respeecher offers free re-recordings of old projects to update AI voice quality
“When we did the book, we used models we most probably don't use anymore. So when we have to listen to a sound we created a couple of years ago, we really feel bad. We want to remake the voice. And that's the case when we could reach out to a production company…”