New open source release from Meta FAIR: Audiobox Aesthetics was trained on 562 hours of audio aesthetic data annotated by professional raters across four dimensions to create a model that enables the automatic evaluation of aesthetics for speech, music and sound.
MULTIMODAL AI
-
Audiobox Aesthetics enhances Meta Movie Gen and generative audio models
By
–
Audiobox Aesthetics has already been used to enhance our work on Meta Movie Gen and we’re excited about how this research will be able to support the development of more sophisticated generative audio models. More details in this post
-
Jensen Huang Honored for AI Medical Imaging and Robotics Innovation
By
–
Our contributions to accelerating medical imaging, genomics, computational chemistry and #AI-powered robotics were honored Friday at the Precision Medicine World Conference, where our founder and CEO Jensen Huang received a Luminary award. Learn more on our blog:
-
Eden Chat Now Enables Complete Short Film Creation
By
–
You can now create an entire short film with music, sound effects, and vocals inside an Eden chat. https://t.co/p7bNXXrvHz
— Gene Kogan (@genekogan) 11 février 2025You can now create an entire short film with music, sound effects, and vocals inside an Eden chat.
-
Reasoning Models to Solve Multimodal Data Extraction in 2025
By
–
Prediction: Multimodal data extraction will be solved in 2025, because reasoning models. Reasoning models are going to be the best multimodal data extractors. Data extraction, especially with complex tables (tables in tables!), is hard, and requires getting a piece of data out,
-
Zephra AI launches Zonos audio model
By
–
Zephra AI released Zonos, a new audio gen model along with a voice Playground where you can clone voices and convert text into audio 👀 https://t.co/AhmXy8S3Xd pic.twitter.com/bhhpea9FHn
— 🚨 AI News | TestingCatalog (@testingcatalog) 10 février 2025Zephra AI released Zonos, a new audio gen model along with a voice Playground where you can clone voices and convert text into audio
-
Runway and Luma text-to-video AI video generation
By
–
3. Vidéo AI
— Jouhatsu | AI Influence Operator (@Jouhatsu_ai) 10 février 2025
Rip Sora ! Profitez de la technologie révolutionnaire de génération de vidéos et de la conversion intelligente du texte en vidéo de Runway et Luma. pic.twitter.com/6XyVHOvGcv3. Vidéo AI Rip Sora ! Profitez de la technologie révolutionnaire de génération de vidéos et de la conversion intelligente du texte en vidéo de Runway et Luma.
-
Comparison of Image-Generation AI Tools and Recommendation
By
–
2. Image AI
— Jouhatsu | AI Influence Operator (@Jouhatsu_ai) 10 février 2025
Midjourney, Ideogram, Flux, et Dall-E-3, offrent une variété de styles d'images à apprécier, chacun avec des options réglables pour plus de commodité.
Midjourney est le meilleur à utiliser en plus de la version officielle. pic.twitter.com/DD6fkQdqwW2. Image AI Midjourney, Ideogram, Flux, et Dall-E-3, offrent une variété de styles d'images à apprécier, chacun avec des options réglables pour plus de commodité. Midjourney est le meilleur à utiliser en plus de la version officielle.
-
Demo of an All-in-One Tool Accessing Multiple AI Models
By
–
Ne vous demandez plus si vous devez utiliser ChatGPT ou DeepSeek. J'ai découvert un excellent outil d'IA tout-en-un qui donne accès à ChatGPT, DeepSeek-R1, Gemini, Midjourney, Perplexity, Runway, et bien plus encore. Laissez-moi vous montrer comment l'utiliser
-
Converting AI-Generated Outputs to Audio for On-the-Go Listening
By
–
yep. provided it is worth reading a novel-length output, me too. I even started turning my o1 outputs into audio content via ElevenLabs so I could listen to them on dog walks