Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

New in-house plugin called Verticality Audio 🎧🔊 • Efficient dynamic reverberation based on room size & material • Interfaces with custom MetaSound node that imitates sound passing through floors • Doesn't interfere with how the player perceive the audio source point

Beautiful Light

28,728 subscribers

45,063 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie Gaming

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

🎧 on. New physically-based audio simulation in s&box 🔊 dynamic reverb, occlusion through walls, and sound that bends around corners. Loads more in our weekly update ▶️

🎧 on. New physically-based audio simulation in s&box 🔊 dynamic reverb, occlusion through walls, and sound that bends around corners. Loads more in our weekly update ▶️

s&box

29,347 Aufrufe • vor 1 Monat

🧵 1/5 Have you noticed how the audio in The Division 2 is changing based on your environment? Let's deep dive into a system called 'Bubblespace' with Audio Architect Rob Bantin 🇺🇦🏳️‍⚧️🏳️‍🌈 and Audio Director Simon Koudriavtsev 🎧🎮

🧵 1/5 Have you noticed how the audio in The Division 2 is changing based on your environment? Let's deep dive into a system called 'Bubblespace' with Audio Architect Rob Bantin 🇺🇦🏳️‍⚧️🏳️‍🌈 and Audio Director Simon Koudriavtsev 🎧🎮

Massive Entertainment - A Ubisoft Studio 🎮

32,627 Aufrufe • vor 3 Jahren

In this week’s Stability Seconds, we’re showing you how to generate custom, commercially safe audio for your next video project with Stable Audio 2.5 🎵 Here’s how you can do it: ▶️ Find a short video clip that you want to add sound to. ▶️ Prompt Stable Audio 2.5 for genre, overall mood, and instruments that match your video. In our prompt, we used terms like “cinematic,” “awe-inspiring,” and “dramatic horn section.” ▶️ Generate a 3-minute track, then scrub through to find the best cut. ▶️ Add that audio to your clip to create a polished soundtrack. You can learn more and start using Stable Audio 2.5 here 👉

In this week’s Stability Seconds, we’re showing you how to generate custom, commercially safe audio for your next video project with Stable Audio 2.5 🎵 Here’s how you can do it: ▶️ Find a short video clip that you want to add sound to. ▶️ Prompt Stable Audio 2.5 for genre, overall mood, and instruments that match your video. In our prompt, we used terms like “cinematic,” “awe-inspiring,” and “dramatic horn section.” ▶️ Generate a 3-minute track, then scrub through to find the best cut. ▶️ Add that audio to your clip to create a polished soundtrack. You can learn more and start using Stable Audio 2.5 here 👉

Stability AI

12,229 Aufrufe • vor 10 Monaten

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

Charly Wargnier

565,274 Aufrufe • vor 6 Monaten

Today we're announcing the open-source release of HunyuanVideo-Foley, our new end-to-end Text-Video-to-Audio (TV2A) framework for generating high-fidelity audio.🚀 This tool empowers creators in video production, filmmaking, and game development to generate professional-grade audio that precisely aligns with visual dynamics and semantic context, addressing key challenges in V2A generation.🔊 Key Innovations: 🔹Exceptional Generalization: Trained on a massive 100k-hour multimodal dataset, the model generates contextually-aware soundscapes for a wide range of scenes, from natural landscapes to animated shorts. 🔹Balanced Multimodal Response: Our innovative multimodal diffusion transformer (MMDiT) architecture ensures the model balances video and text cues, generating rich, layered sound effects that capture every detail—from the main subject to subtle background elements. 🔹High-Fidelity Audio: Using a Representation Alignment (REPA) loss function and a powerful Audio VAE, we've improved generation stability and producing professional-grade audio, free of noise and inconsistencies. HunyuanVideo-Foley achieves SOTA on multiple benchmarks, surpassing all open-source models in audio quality, visual-semantic alignment, and temporal alignment. 👉Try it now: 🌐Project Page: 🔗Code: 📄Technical Report: 🤗Hugging Face:

Today we're announcing the open-source release of HunyuanVideo-Foley, our new end-to-end Text-Video-to-Audio (TV2A) framework for generating high-fidelity audio.🚀 This tool empowers creators in video production, filmmaking, and game development to generate professional-grade audio that precisely aligns with visual dynamics and semantic context, addressing key challenges in V2A generation.🔊 Key Innovations: 🔹Exceptional Generalization: Trained on a massive 100k-hour multimodal dataset, the model generates contextually-aware soundscapes for a wide range of scenes, from natural landscapes to animated shorts. 🔹Balanced Multimodal Response: Our innovative multimodal diffusion transformer (MMDiT) architecture ensures the model balances video and text cues, generating rich, layered sound effects that capture every detail—from the main subject to subtle background elements. 🔹High-Fidelity Audio: Using a Representation Alignment (REPA) loss function and a powerful Audio VAE, we've improved generation stability and producing professional-grade audio, free of noise and inconsistencies. HunyuanVideo-Foley achieves SOTA on multiple benchmarks, surpassing all open-source models in audio quality, visual-semantic alignment, and temporal alignment. 👉Try it now: 🌐Project Page: 🔗Code: 📄Technical Report: 🤗Hugging Face:

Tencent Hy

122,706 Aufrufe • vor 11 Monaten

My submission to the Cerebras Google Gemma hackathon, Carbide. Carbide is an ontology builder. Based on a research prompt Carbide uses Cerebras Gemma4 agents to build an ontology. The agents connects individual nodes of information based on the relationship that the agents infer. The agents also assign a confidence metric for how accurate they think the relationship is. You can see each node in a relationship table of the information -> relationship -> target -> and the confidence the relationship is true. The inspector shows the node's connected edges and as an expand button to grow the ontology in the direction of that information. You can scroll through each concept and load them in the inspector. You can search the entire graph based on the kind of relationships generated, or key words. A visual shows how each nodes connects to another one and by what relationship, and changes with new nodes or search filters. Sorry for the audio quality. $CBRS $GOOG

My submission to the Cerebras Google Gemma hackathon, Carbide. Carbide is an ontology builder. Based on a research prompt Carbide uses Cerebras Gemma4 agents to build an ontology. The agents connects individual nodes of information based on the relationship that the agents infer. The agents also assign a confidence metric for how accurate they think the relationship is. You can see each node in a relationship table of the information -> relationship -> target -> and the confidence the relationship is true. The inspector shows the node's connected edges and as an expand button to grow the ontology in the direction of that information. You can scroll through each concept and load them in the inspector. You can search the entire graph based on the kind of relationships generated, or key words. A visual shows how each nodes connects to another one and by what relationship, and changes with new nodes or search filters. Sorry for the audio quality. $CBRS $GOOG

QuantHood

16,376 Aufrufe • vor 28 Tagen

Type a sentence, get any sound - from talking cats to singing saxophones. Brilliant release by NVIDIA ✨ NVIDIA just unveiled Fugatto, a groundbreaking 2.5B parameter audio AI model that can generate and transform any combination of music, voices, and sounds using text prompts and audio inputs Fugatto could ultimately allow developers and creators to bring sounds to life simply by inputting text prompts, → The model demonstrates unique capabilities like creating hybrid sounds (trumpet barking), changing accents/emotions in voices, and allowing fine-grained control over sound transitions - trained on millions of audio samples using 32 NVIDIA H100 GPUs 👨‍🔧 Architecture Built as a foundational generative transformer model leveraging NVIDIA's previous work in speech modeling and audio understanding. The training process involved creating a specialized blended dataset containing millions of audio samples → ComposableART's Innovation in Audio Control Introduces a novel technique allowing combination of instructions that were only seen separately during training. Users can blend different audio attributes and control their intensity → Temporal Interpolation Capabilities Enables generation of evolving soundscapes with precise control over transitions. Can create dynamic audio sequences like rainstorms fading into birdsong at dawn → Processes both text and audio inputs flexibly, enabling tasks like removing instruments from songs or modifying specific audio characteristics while preserving others → Shows capabilities beyond its training data, creating entirely new sound combinations through interaction between different trained abilities 🔍 Real-world Applications → Allows rapid prototyping of musical ideas, style experimentation, and real-time sound creation during studio sessions → Enables dynamic audio asset generation matching gameplay situations, reducing pre-recorded audio requirements → Can modify voice characteristics for language learning applications, allowing content delivery in familiar voices NVIDIA AI Developer

Type a sentence, get any sound - from talking cats to singing saxophones. Brilliant release by NVIDIA ✨ NVIDIA just unveiled Fugatto, a groundbreaking 2.5B parameter audio AI model that can generate and transform any combination of music, voices, and sounds using text prompts and audio inputs Fugatto could ultimately allow developers and creators to bring sounds to life simply by inputting text prompts, → The model demonstrates unique capabilities like creating hybrid sounds (trumpet barking), changing accents/emotions in voices, and allowing fine-grained control over sound transitions - trained on millions of audio samples using 32 NVIDIA H100 GPUs 👨‍🔧 Architecture Built as a foundational generative transformer model leveraging NVIDIA's previous work in speech modeling and audio understanding. The training process involved creating a specialized blended dataset containing millions of audio samples → ComposableART's Innovation in Audio Control Introduces a novel technique allowing combination of instructions that were only seen separately during training. Users can blend different audio attributes and control their intensity → Temporal Interpolation Capabilities Enables generation of evolving soundscapes with precise control over transitions. Can create dynamic audio sequences like rainstorms fading into birdsong at dawn → Processes both text and audio inputs flexibly, enabling tasks like removing instruments from songs or modifying specific audio characteristics while preserving others → Shows capabilities beyond its training data, creating entirely new sound combinations through interaction between different trained abilities 🔍 Real-world Applications → Allows rapid prototyping of musical ideas, style experimentation, and real-time sound creation during studio sessions → Enables dynamic audio asset generation matching gameplay situations, reducing pre-recorded audio requirements → Can modify voice characteristics for language learning applications, allowing content delivery in familiar voices NVIDIA AI Developer

Rohan Paul

96,354 Aufrufe • vor 1 Jahr

#BREAKING: Hayes: “Last week we had a NYTimes report of a White House freak out over the #Epstein files that took the lace last Summer. VP JD Vance, Chief of Staff Susie Wiles and everybody in between, was in a series of Situation Room meetings…trying to figure out how to handle the crisis over their boss being in the Epstein files. Well, today, we got new reporting from Axios that they are freaking out about that freak out report and just how that information was leaked: ‘Top White House officials believe NYTimes reporters Maggie Haberman and Jonathan Swan obtained audio recordings of Situation Room meetings for their forthcoming book Regime Change on which the Epstein report is based.’” 😳

#BREAKING: Hayes: “Last week we had a NYTimes report of a White House freak out over the #Epstein files that took the lace last Summer. VP JD Vance, Chief of Staff Susie Wiles and everybody in between, was in a series of Situation Room meetings…trying to figure out how to handle the crisis over their boss being in the Epstein files. Well, today, we got new reporting from Axios that they are freaking out about that freak out report and just how that information was leaked: ‘Top White House officials believe NYTimes reporters Maggie Haberman and Jonathan Swan obtained audio recordings of Situation Room meetings for their forthcoming book Regime Change on which the Epstein report is based.’” 😳

Emoluments Clause

36,412 Aufrufe • vor 1 Monat

I recreated Meta’s new AI Glasses on my Quest, and the complete source code is available! 👓 Hey everyone! I’ve received a lot of feedback and messages about my latest project, where I used the Quest to recreate the features shown during Meta’s keynote. To answer your questions I decided to create a cool video to explain how I built it but also, share the full source code on Patreon 👇 Watch the making-of: Download the source code: This project includes: ✨ A UI navigable with microgestures 🤏 A pinch & twist hand-tracking input system 🎧 An audio player with volume control via pinch & twist 📸 A camera that zooms with pinch & twist 🖼️ A carousel to browse captured pictures 🧠 And a contextual AI that reacts to what you’re looking at Hope you guys will like it and that it will help you on your own project!! 😊

I recreated Meta’s new AI Glasses on my Quest, and the complete source code is available! 👓 Hey everyone! I’ve received a lot of feedback and messages about my latest project, where I used the Quest to recreate the features shown during Meta’s keynote. To answer your questions I decided to create a cool video to explain how I built it but also, share the full source code on Patreon 👇 Watch the making-of: Download the source code: This project includes: ✨ A UI navigable with microgestures 🤏 A pinch & twist hand-tracking input system 🎧 An audio player with volume control via pinch & twist 📸 A camera that zooms with pinch & twist 🖼️ A carousel to browse captured pictures 🧠 And a contextual AI that reacts to what you’re looking at Hope you guys will like it and that it will help you on your own project!! 😊

Quentin Valembois

15,977 Aufrufe • vor 9 Monaten

Discover American art through a fresh lens. ✨ As The Met American Wing celebrates its 100th anniversary, newly reimagined galleries across three floors highlight connections within the Wing’s expansive, hemispheric collection—spanning from the mid-17th to mid-20th century, with contemporary expressions included. By pairing foundational holdings with recent acquisitions, key loans, and select pieces from across the Museum, these galleries invite new dialogues that enrich our understanding of American art, history, and culture. This reinstallation reflects expansive scholarship and incorporates diverse curatorial and community perspectives, broadening the evolving understanding what American art means today. 🎧 Listen to historians, artists, poets, and community leaders from diverse backgrounds offer perspectives on various works in our new audio guides.

Discover American art through a fresh lens. ✨ As The Met American Wing celebrates its 100th anniversary, newly reimagined galleries across three floors highlight connections within the Wing’s expansive, hemispheric collection—spanning from the mid-17th to mid-20th century, with contemporary expressions included. By pairing foundational holdings with recent acquisitions, key loans, and select pieces from across the Museum, these galleries invite new dialogues that enrich our understanding of American art, history, and culture. This reinstallation reflects expansive scholarship and incorporates diverse curatorial and community perspectives, broadening the evolving understanding what American art means today. 🎧 Listen to historians, artists, poets, and community leaders from diverse backgrounds offer perspectives on various works in our new audio guides.

The Metropolitan Museum of Art

15,111 Aufrufe • vor 1 Jahr

Today we’re celebrating 10 years of the Meta FAIR lab in Paris by sharing a collection of new models, datasets and some exciting milestones in the impacts of open source — all laddering up to our ongoing work to achieve Advanced Machine Intelligence (AMI). 1️⃣ Meta PARTNR is a framework for human-robot collaboration that builds on our existing work in this space with a new dataset and a large planning model enabling robots to accomplish complex tasks alongside humans. 2️⃣ Meta Audiobox Aesthetics enables the automatic evaluation of audio aesthetics, providing a comprehensive assessment of audio quality across speech, music and sound. 3️⃣ Open Source Machine Translation Benchmark is a carefully crafted collection with the aim of building an unprecedented multilingual machine translation benchmark for the community. 4️⃣ Two new breakthrough studies using AI to further our understanding of language in the brain.

Today we’re celebrating 10 years of the Meta FAIR lab in Paris by sharing a collection of new models, datasets and some exciting milestones in the impacts of open source — all laddering up to our ongoing work to achieve Advanced Machine Intelligence (AMI). 1️⃣ Meta PARTNR is a framework for human-robot collaboration that builds on our existing work in this space with a new dataset and a large planning model enabling robots to accomplish complex tasks alongside humans. 2️⃣ Meta Audiobox Aesthetics enables the automatic evaluation of audio aesthetics, providing a comprehensive assessment of audio quality across speech, music and sound. 3️⃣ Open Source Machine Translation Benchmark is a carefully crafted collection with the aim of building an unprecedented multilingual machine translation benchmark for the community. 4️⃣ Two new breakthrough studies using AI to further our understanding of language in the brain.

AI at Meta

85,774 Aufrufe • vor 1 Jahr

I’m utterly blown away by this new audio in the Epstein Files. It shows the secret conversation you fear every high-level gov’t official might have with an outside fixer to hook them up the moment they “leave government to enter the private sector.” Here, Jeffrey Epstein teaches Ehud Barak — while he is still Minister of Defense in Israel but on his way out — how to make millions of dollars in the private sector by first compiling a list of people who owe him favors from his 40 years in government service. Epstein then told Ehud Barak to pursue Peter Thiel, whose name at that point Ehud Barak did not even know how to spell, and to try to connect with a company called Palantir, which existence Ehud Barak had never heard of, and whose name Jeffrey Epstein didn’t know how to spell. Credit Ryan Grim whose clip I first saw to look for this. I used Grok to backtrace the source link from the audio. Ryan assesses this meeting took place in February 2013, which seems to line up with the audio saying Ehud Barak is about 71 at the time of the recording, as Ehud Barak is 83 today.

I’m utterly blown away by this new audio in the Epstein Files. It shows the secret conversation you fear every high-level gov’t official might have with an outside fixer to hook them up the moment they “leave government to enter the private sector.” Here, Jeffrey Epstein teaches Ehud Barak — while he is still Minister of Defense in Israel but on his way out — how to make millions of dollars in the private sector by first compiling a list of people who owe him favors from his 40 years in government service. Epstein then told Ehud Barak to pursue Peter Thiel, whose name at that point Ehud Barak did not even know how to spell, and to try to connect with a company called Palantir, which existence Ehud Barak had never heard of, and whose name Jeffrey Epstein didn’t know how to spell. Credit Ryan Grim whose clip I first saw to look for this. I used Grok to backtrace the source link from the audio. Ryan assesses this meeting took place in February 2013, which seems to line up with the audio saying Ehud Barak is about 71 at the time of the recording, as Ehud Barak is 83 today.

Mike Benz

6,549,119 Aufrufe • vor 5 Monaten

🇺🇸 TOM GREEN: ROGAN WAS FIRST TO NAIL THE STREAMING BUSINESS MODEL "In the early 2000s, I realized you could stream live on the internet. I’d been experimenting with tech since the '90s—my website launched in 1994, with audio clips posted even back then. When the technology caught up, I built a multi-camera TV studio in my LA living room and started streaming. I didn’t figure out the business model—Joe Rogan nailed that—but I figured out how to plug it all in. Rogan was way ahead when it came to making it work." Source: Graham Bensinger Tom Green

🇺🇸 TOM GREEN: ROGAN WAS FIRST TO NAIL THE STREAMING BUSINESS MODEL "In the early 2000s, I realized you could stream live on the internet. I’d been experimenting with tech since the '90s—my website launched in 1994, with audio clips posted even back then. When the technology caught up, I built a multi-camera TV studio in my LA living room and started streaming. I didn’t figure out the business model—Joe Rogan nailed that—but I figured out how to plug it all in. Rogan was way ahead when it came to making it work." Source: Graham Bensinger Tom Green

Mario Nawfal

231,073 Aufrufe • vor 1 Jahr

Reachy Mini just got a new Brain! We released a fully open-source backend for talking to Reachy Mini. In the last 48 hours, 3,000+ robots have already hit the version deployed on Hugging Face's infra. Until today, if you wanted a real-time voice agent in your robot, you were looking at $20+ a day. Realtime APIs are expensive because every second the connection is up, you are being charged! But with our approach, you can run the audio models locally and use your OpenAI or Claude subscription for the LLM, at no extra costs. The audio pipeline is very efficient; in the video, it's running on the cheapest Mac mini, 16GB of RAM (the one that sold out a couple of months back when people were buying them up for openclaws setups). Tutorials coming in the next few weeks: how to run your robot fully locally, or with your favorite agent. Stay tuned!

Reachy Mini just got a new Brain! We released a fully open-source backend for talking to Reachy Mini. In the last 48 hours, 3,000+ robots have already hit the version deployed on Hugging Face's infra. Until today, if you wanted a real-time voice agent in your robot, you were looking at $20+ a day. Realtime APIs are expensive because every second the connection is up, you are being charged! But with our approach, you can run the audio models locally and use your OpenAI or Claude subscription for the LLM, at no extra costs. The audio pipeline is very efficient; in the video, it's running on the cheapest Mac mini, 16GB of RAM (the one that sold out a couple of months back when people were buying them up for openclaws setups). Tutorials coming in the next few weeks: how to run your robot fully locally, or with your favorite agent. Stay tuned!

Andi Marafioti

56,036 Aufrufe • vor 2 Monaten

Call of Duty Modern Warfare 4 has revealed its DMZ mode in a new first look deep dive. -DMZ is a dedicated extraction style experience set in Hajin, a large Exclusion Zone on the Korean peninsula shaped by events from the Modern Warfare 4 campaign. -It mixes narrative driven story missions with player driven dynamic operations in a living open world. -Players prepare at a Forward Operating Base hub that lets them test loadouts and upgrades. -Looting feels logical with items found in realistic locations, plus crafting through a 3D printer using gathered materials. -Dynamic weather systems affect visibility and gameplay in real time. -AI threats start basic and escalate to high tier commanders based on player actionsthat lets you disengage or go loud.

Call of Duty Modern Warfare 4 has revealed its DMZ mode in a new first look deep dive. -DMZ is a dedicated extraction style experience set in Hajin, a large Exclusion Zone on the Korean peninsula shaped by events from the Modern Warfare 4 campaign. -It mixes narrative driven story missions with player driven dynamic operations in a living open world. -Players prepare at a Forward Operating Base hub that lets them test loadouts and upgrades. -Looting feels logical with items found in realistic locations, plus crafting through a 3D printer using gathered materials. -Dynamic weather systems affect visibility and gameplay in real time. -AI threats start basic and escalate to high tier commanders based on player actionsthat lets you disengage or go loud.

Pirat_Nation 🔴

28,755 Aufrufe • vor 1 Monat

LFG !! Our work with the Pelosi Tracker is making it's way to the House Floor ! "In fact, there's funds out there that follow and trade along with members of congress to see what they're trading" $400,000,000. That's how much money every day Americans are using to copy the stock trades of their elected officials Yes, Pelosi literally has $400M copying her right now on Autopilot If that doesn't raise some eyebrows idk what would He's right, does sound ridiculous because it is ridiculous So let's get that ban through 🫡

LFG !! Our work with the Pelosi Tracker is making it's way to the House Floor ! "In fact, there's funds out there that follow and trade along with members of congress to see what they're trading" $400,000,000. That's how much money every day Americans are using to copy the stock trades of their elected officials Yes, Pelosi literally has $400M copying her right now on Autopilot If that doesn't raise some eyebrows idk what would He's right, does sound ridiculous because it is ridiculous So let's get that ban through 🫡

Nancy Pelosi Stock Tracker ♟

250,727 Aufrufe • vor 1 Jahr

I’ve been exploring Gemini 2.0’s new native audio output capability, which is available for early testers. I’m a developer at Google Creative Lab, and wanted to share one of my favorite experiments so far called ✨ VoiceCursor (🔊 sound on for video) Unlike traditional TTS, native audio lets you prompt the model with expressive styles, ie “Say this like a disgruntled pirate…” So I made ✨VoiceCursor… it lets you rapidly try different prompts. Just type, highlight your phrase, then hear it spoken in different ways! My code is open-sourced here: Here’s a thread 🧵

I’ve been exploring Gemini 2.0’s new native audio output capability, which is available for early testers. I’m a developer at Google Creative Lab, and wanted to share one of my favorite experiments so far called ✨ VoiceCursor (🔊 sound on for video) Unlike traditional TTS, native audio lets you prompt the model with expressive styles, ie “Say this like a disgruntled pirate…” So I made ✨VoiceCursor… it lets you rapidly try different prompts. Just type, highlight your phrase, then hear it spoken in different ways! My code is open-sourced here: Here’s a thread 🧵

Trudy Painter

67,668 Aufrufe • vor 1 Jahr

I absolutely love that you can play retro flat games from several consoles and handhelds native on the Quest 3 without any type of side loading required with this new application Retro Game Dev VR. You have to source your own backups of the games but I love it. And the room looks fantastic on Quest 3 too. You can play at a desk on a small CRT monitor on your large CRT TV or on a handheld while laying in bed. Oh and spatial audio too.

I absolutely love that you can play retro flat games from several consoles and handhelds native on the Quest 3 without any type of side loading required with this new application Retro Game Dev VR. You have to source your own backups of the games but I love it. And the room looks fantastic on Quest 3 too. You can play at a desk on a small CRT monitor on your large CRT TV or on a handheld while laying in bed. Oh and spatial audio too.

BMFVR

13,302 Aufrufe • vor 1 Monat

Mira Murati says the next AI interface is not a chatbot. It is a model that can listen, see, interrupt, and respond in real time. "The models that we work with today, they're very turn-based." "You talk, they talk, then they go off and think." "While they're thinking, it's almost like they're deaf and blind. They cannot perceive anything else about what's going on." Her new frame: interaction models. "They're not turn-based. They're more like time-based interaction." "They're continuously taking in audio, text, video, and continuously providing output." "We cut this up in chunks of 20 milliseconds... this enables you to catch things like interruptions and simultaneous speech." That is the product shift: from AI as a prompt box to AI as a high-bandwidth collaborator.

Mira Murati says the next AI interface is not a chatbot. It is a model that can listen, see, interrupt, and respond in real time. "The models that we work with today, they're very turn-based." "You talk, they talk, then they go off and think." "While they're thinking, it's almost like they're deaf and blind. They cannot perceive anything else about what's going on." Her new frame: interaction models. "They're not turn-based. They're more like time-based interaction." "They're continuously taking in audio, text, video, and continuously providing output." "We cut this up in chunks of 20 milliseconds... this enables you to catch things like interruptions and simultaneous speech." That is the product shift: from AI as a prompt box to AI as a high-bandwidth collaborator.

Karl Mehta

191,299 Aufrufe • vor 27 Tagen

NEW: Former House Speaker Newt Gingrich claims a 'reliable source' told him that someone in Washington made a call to Georgia District Attorney Fani Willis, instructing her to indict Donald Trump on Monday, not Tuesday. "We have to cover up all of the mistakes we just made with Weiss," the source passed on while explaining what was allegedly said. "That I am told, this is hearsay, but I'm told by a reliable source that Friday evening, somebody from Washington called the district attorney in Atlanta and said, you have to indict on Monday.” “‘We have to cover up all of the mistakes we just made with Weiss.’ And she said, apparently: ‘My jurors aren't coming back till Tuesday.’” “And they said: ‘You didn't hear me, you have to indict on Monday.’ And she said: ‘Well, we're not gonna get here before noon.’” “They said: ‘It doesn't matter.’ She said: ‘This means it's gonna be eight or nine or 10 o'clock at night.’” “They said: ‘It doesn't matter. We need the news media shifting.’” I’m skeptical but wouldn’t be surprised at this point.

NEW: Former House Speaker Newt Gingrich claims a 'reliable source' told him that someone in Washington made a call to Georgia District Attorney Fani Willis, instructing her to indict Donald Trump on Monday, not Tuesday. "We have to cover up all of the mistakes we just made with Weiss," the source passed on while explaining what was allegedly said. "That I am told, this is hearsay, but I'm told by a reliable source that Friday evening, somebody from Washington called the district attorney in Atlanta and said, you have to indict on Monday.” “‘We have to cover up all of the mistakes we just made with Weiss.’ And she said, apparently: ‘My jurors aren't coming back till Tuesday.’” “And they said: ‘You didn't hear me, you have to indict on Monday.’ And she said: ‘Well, we're not gonna get here before noon.’” “They said: ‘It doesn't matter.’ She said: ‘This means it's gonna be eight or nine or 10 o'clock at night.’” “They said: ‘It doesn't matter. We need the news media shifting.’” I’m skeptical but wouldn’t be surprised at this point.

Collin Rugg

2,935,884 Aufrufe • vor 2 Jahren