pull down to refresh

Azure AI Speech needs seconds of audio to clone voiceswww.theregister.com/2025/07/31/microsoft_updates_azure_ai_speech/
175 sats \ 2 comments \ @0xbitcoiner 31 Jul AI
No way this will be abused
Microsoft has upgraded Azure AI Speech so that users can rapidly generate a voice replica with just a few seconds of sampled speech.
The personal voice feature for AI Speech became generally available on May 21, 2024. It was impressive but required some training to get the best out of it. According to Microsoft, the feature has been upgraded to a new zero-shot text-to-speech model named "DragonV2.1Neural" with "more natural-sounding and expressive voices." It will also generate audio in any of the more than 100 supported languages.
...read more at theregister.com
write
preview
related posts
33 sats \ 1 reply \ @optimism 1 Aug
I'm still undecided on whether deepfaking myself would be good or bad. As someone that is slightly better in textual addresses than spoken ones, it could be a tool. But it feels inauthentic.
reply
0 sats \ 0 replies \ @perscrutador 10h freebie
Make their job difficult. Why would you want to hand them something they want so badly on a silver platter? Authenticity is your mind, and no AI can steal that, but its physical representation through your face and voice is what makes your authenticity present and recognizable. Like a visual shortcut.