AI based video conversion across languages

What do you think of this AI translated demo of Lex Friedman and Mark Z speaking in Hindi

The Twitter user @therealprady built a beta using GPT-4 + prompt engineering for translation

What I do like about it is the preservation of the Original Speakers’ voice and tonality – something that most translations miss

What I do miss, as someone who understands the language, is that it doesn’t in the least represent how a native speaker would converse

More colloquial versions might be what the future would look like (I hope)

Pavan Reddy – Reminded me of the work your startup is doing in this space. DM me if you have a beta that is ready to be tried out by end customers 🙂

[11labs for voice training + text-to-speech in other languages while preserving the OG speakers voice

wav2lip-2 API to lipsync the video to the translated audio in HD [sota model + API in beta by @synchronicitylabs]

 

Video link here 

****************************

Ranjani Mani

#reviewswithranjani #GenerativeAIandI

#Technology | #Books | #BeingBetter

Leave a Comment

Your email address will not be published. Required fields are marked *