MacMusic  |  PcMusic  |  440 Software  |  440 Forums  |  440TV  |  Zicos
open
Recherche

This open text-to-speech model needs just seconds of audio to clone your voice

dimanche 16 février 2025, 19:58 , par TheRegister
El Reg shows you how to run Zyphra's speech-replicating AI on your own box
Hands on Palo Alto-based AI startup Zyphra unveiled a pair of open text-to-speech (TTS) models this week said to be capable of cloning your voice with as little as five seconds of sample audio. In our testing, we generated realistic results with less than half a minute of recorded speech.…
Lire la suite sur TheRegister
https://go.theregister.com/feed/www.theregister.com/2025/02/16/ai_voice_clone/

Voir aussi

open Muse: Microsoft’s Gen AI Model to Help Game Developers – Not Replace Them eWeek20 Feb
seconds Voici Sniffnet, l’outil open source qui surveille votre réseau TooLinux20 Feb
voice Proton Wallet, le portefeuille crypto chiffré et open source, accessible à tous TooLinux20 Feb
text-to-speech Xbox Pushes Ahead With Muse, a New Generative AI Model. Devs Say ‘Nobody Will Want This’ Wired: Tech.19 Feb
needs Telco to open lab to test cell network interoperability with satellites TheRegister19 Feb
clone Elon Musk prône l’IA open source, alors pourquoi son modèle Grok reste-t-il fermé ? ZDNet.fr19 Feb
just Application open source du mois : Anytype peut désormais publier sur le web TooLinux19 Feb
model xAI launches new Grok-3 AI model with DeepSearch reasoning PC World18 Feb
open xAI Releases Its Latest Flagship Model, Grok 3 Slashdot18 Feb
seconds Alpes Open Source Software​ ce 20 février : tout ce qu’il faut savoir TooLinux18 Feb
voice Deux modèles d’IA open source disponibles dans Duck AI (DuckDuckGo AI) TooLinux18 Feb
text-to-speech Pour Mozilla, le Paris AI Action Summit a placé le curseur de l’IA sur l’open source TooLinux18 Feb
needs Kia EV4 : une berline électrique au style unique pour dompter la Tesla Model 3 01net17 Feb
clone Man legally becomes best friend's grandfather to get revenge over a petty text BoingBoing17 Feb
just Baidu rend Ernie, son prochain modèle d’IA, open source TooLinux17 Feb
model Votre revue de presse GoodTech, IA et Open Source (17 février 2025) TooLinux17 Feb
open Open source maintainers are really feeling the squeeze TheRegister16 Feb
seconds Your boss doesn’t need to know you found this AI with every major model PC World16 Feb
voice The World's Most Printed 3D Model, 3DBenchy, Is Now Public Domain Slashdot15 Feb
text-to-speech PIN AI Launches Mobile App Letting You Make Your Own Personalized, Private AI Model Slashdot15 Feb
News copyright owned by their original publishers | Copyright © 2004 - 2025 Zicos / 440Network
Date Actuelle
jeu. 20 févr. - 20:48 CET