Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

MICROSOFT OPEN SOURCED A 7B PARAMETER MODEL THAT TRANSCRIBES 60 MINUTES OF AUDIO IN A SINGLE PASS and it's completely free VIBEVOICE ASR no chunking, no context loss, full speaker diarization baked in not just speech to text..not a basic wrapper who spoke, when they spoke, exactly what they... show more

Rahul

130,466 subscribers

1,373,048 views • 3 months ago •via X (Twitter)

Education Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚨 JUST IN: MICROSOFT just open sourced a VOICE AI THAT TRANSCRIBES 60 MINUTES OF AUDIO in a single pass. 100% FREE. It knows who spoke. It knows when they spoke. It knows exactly what they said. All in one shot. No chunking. No context loss. It's called VibeVoice. Not a transcription tool. Not a basic speech to text wrapper. A frontier voice AI family with ASR, TTS, and real time streaming. All open source. All free. Here's what it actually does 👇 VibeVoice ASR - Speech Recognition: → Processes 60 minutes of continuous audio in a single pass → Never slices audio into chunks so global context is never lost → Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously → Supports customized hotwords for domain specific accuracy → Works in 50+ languages natively → Already adopted by Hugging Face Transformers library → Already being built on by the open source community BY PEOPLE WHO HAD NO IDEA THIS LEVEL OF ACCURACY WAS ALREADY FREE. VibeVoice TTS - Text to Speech: → Generates up to 90 minutes of speech in a single pass → Supports up to 4 distinct speakers in one conversation → Natural turn taking and speaker consistency throughout → Expressive speech that captures emotional nuances → Supports English, Chinese and multiple other languages VibeVoice Realtime - Streaming TTS: → Only 300 millisecond first audible latency → Streams text input in real time → 0.5B parameters so it actually deploys anywhere → Robust long form generation up to 10 minutes → Lightweight enough for production use today The core innovation nobody is talking about: Most voice AI models slice long audio into short chunks. Every time they slice, they lose context. Speaker tracking breaks. Semantic coherence breaks. Accuracy drops. VibeVoice uses continuous speech tokenizers running at an ultra low frame rate of 7.5 Hz. This preserves audio fidelity while dramatically boosting computational efficiency. The entire 60 minutes stays in context. Nothing gets lost. Nobody gets misidentified. The numbers: → VibeVoice ASR 7B - available now on Hugging Face → VibeVoice Realtime 0.5B - try it on Colab right now → 50+ supported languages → 11 distinct English voice styles → 9 multilingual speaker voices → Already integrated into Hugging Face Transformers → Finetuning code now available The wildest part? A voice powered input method called Vibing just built itself on top of VibeVoice ASR. Available on macOS and Windows right now. The open source community is already shipping products on top of this. 100% Open Source. Free to use. Free to fine tune. Free to build on. 🔖 Save this before your competitors find it first. 👇

🚨 JUST IN: MICROSOFT just open sourced a VOICE AI THAT TRANSCRIBES 60 MINUTES OF AUDIO in a single pass. 100% FREE. It knows who spoke. It knows when they spoke. It knows exactly what they said. All in one shot. No chunking. No context loss. It's called VibeVoice. Not a transcription tool. Not a basic speech to text wrapper. A frontier voice AI family with ASR, TTS, and real time streaming. All open source. All free. Here's what it actually does 👇 VibeVoice ASR - Speech Recognition: → Processes 60 minutes of continuous audio in a single pass → Never slices audio into chunks so global context is never lost → Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously → Supports customized hotwords for domain specific accuracy → Works in 50+ languages natively → Already adopted by Hugging Face Transformers library → Already being built on by the open source community BY PEOPLE WHO HAD NO IDEA THIS LEVEL OF ACCURACY WAS ALREADY FREE. VibeVoice TTS - Text to Speech: → Generates up to 90 minutes of speech in a single pass → Supports up to 4 distinct speakers in one conversation → Natural turn taking and speaker consistency throughout → Expressive speech that captures emotional nuances → Supports English, Chinese and multiple other languages VibeVoice Realtime - Streaming TTS: → Only 300 millisecond first audible latency → Streams text input in real time → 0.5B parameters so it actually deploys anywhere → Robust long form generation up to 10 minutes → Lightweight enough for production use today The core innovation nobody is talking about: Most voice AI models slice long audio into short chunks. Every time they slice, they lose context. Speaker tracking breaks. Semantic coherence breaks. Accuracy drops. VibeVoice uses continuous speech tokenizers running at an ultra low frame rate of 7.5 Hz. This preserves audio fidelity while dramatically boosting computational efficiency. The entire 60 minutes stays in context. Nothing gets lost. Nobody gets misidentified. The numbers: → VibeVoice ASR 7B - available now on Hugging Face → VibeVoice Realtime 0.5B - try it on Colab right now → 50+ supported languages → 11 distinct English voice styles → 9 multilingual speaker voices → Already integrated into Hugging Face Transformers → Finetuning code now available The wildest part? A voice powered input method called Vibing just built itself on top of VibeVoice ASR. Available on macOS and Windows right now. The open source community is already shipping products on top of this. 100% Open Source. Free to use. Free to fine tune. Free to build on. 🔖 Save this before your competitors find it first. 👇

Kanika

220,924 views • 3 months ago

Microsoft did it again! Speech AI models have a major limitation. They slice long recordings into tiny chunks, lose track of who's speaking, and forget all context halfway through. This is exactly what Microsoft's VibeVoice solves. It's an open-source family of frontier voice AI models for both speech recognition and speech generation. Here's what it can do: > VibeVoice-ASR processes up to 60 minutes of audio in a single pass. No chunking. It outputs structured transcriptions with who spoke, when they spoke, and what they said. > You can feed it custom hotwords like names, technical jargon, or domain-specific terms. The model uses them to significantly improve accuracy on specialized content. > VibeVoice-TTS generates up to 90 minutes of multi-speaker speech with up to 4 distinct speakers. Natural turn-taking, emotional expression, all in one pass. > VibeVoice-Realtime is a 0.5B streaming TTS model with ~300ms first-audio latency. Small enough to deploy practically anywhere. All of this is powered by continuous speech tokenizers running at just 7.5 Hz. This ultra-low frame rate preserves audio quality while making long sequences computationally feasible. I have shared the link to the GitHub repo in the replies!

Microsoft did it again! Speech AI models have a major limitation. They slice long recordings into tiny chunks, lose track of who's speaking, and forget all context halfway through. This is exactly what Microsoft's VibeVoice solves. It's an open-source family of frontier voice AI models for both speech recognition and speech generation. Here's what it can do: > VibeVoice-ASR processes up to 60 minutes of audio in a single pass. No chunking. It outputs structured transcriptions with who spoke, when they spoke, and what they said. > You can feed it custom hotwords like names, technical jargon, or domain-specific terms. The model uses them to significantly improve accuracy on specialized content. > VibeVoice-TTS generates up to 90 minutes of multi-speaker speech with up to 4 distinct speakers. Natural turn-taking, emotional expression, all in one pass. > VibeVoice-Realtime is a 0.5B streaming TTS model with ~300ms first-audio latency. Small enough to deploy practically anywhere. All of this is powered by continuous speech tokenizers running at just 7.5 Hz. This ultra-low frame rate preserves audio quality while making long sequences computationally feasible. I have shared the link to the GitHub repo in the replies!

Akshay 🚀

45,206 views • 4 months ago

Microsoft just killed voice subscriptions. 🤯 They quietly open-sourced VibeVoice, and it’s a total industry disruptor. Transcribe hour-long meetings or generate 90 minutes of natural, multi-speaker speech, all locally on your hardware for free. It handles 50+ languages and complex speaker tracking without the monthly fees. The era of expensive voice apps is officially over. I share updates like these in my free AI community on WhatsApp. Join here

Microsoft just killed voice subscriptions. 🤯 They quietly open-sourced VibeVoice, and it’s a total industry disruptor. Transcribe hour-long meetings or generate 90 minutes of natural, multi-speaker speech, all locally on your hardware for free. It handles 50+ languages and complex speaker tracking without the monthly fees. The era of expensive voice apps is officially over. I share updates like these in my free AI community on WhatsApp. Join here

Vaibhav Sisinty

22,056 views • 3 months ago

MICROSOFT DROPPED A 4B PARAMETER MODEL THAT TURNS ONE IMAGE INTO A 3D ASSET IN 3 SECONDS and it's open source TRELLIS.2 fully textured, physically accurate 3D models with PBR textures out of the box not a rough mesh..not a placeholder roughness, metallic, opacity the kind of detail that makes things look real under any lighting and it handles the weird stuff too..open surfaces, hollow interiors, geometry that breaks every other tool the model doesn't know the word "limitation" apparently demo is live on hugging face right now

MICROSOFT DROPPED A 4B PARAMETER MODEL THAT TURNS ONE IMAGE INTO A 3D ASSET IN 3 SECONDS and it's open source TRELLIS.2 fully textured, physically accurate 3D models with PBR textures out of the box not a rough mesh..not a placeholder roughness, metallic, opacity the kind of detail that makes things look real under any lighting and it handles the weird stuff too..open surfaces, hollow interiors, geometry that breaks every other tool the model doesn't know the word "limitation" apparently demo is live on hugging face right now

Vaishnavi

354,326 views • 3 months ago

🚨 ElevenLabs just killed every transcription tool on the market. They dropped Scribe v2 Realtime and it's not just another speech-to-text model. This thing processes audio in real-time with zero lag, handles multiple speakers, and actually understands context not just words. Here's how with real examples: Full thread 🧵

🚨 ElevenLabs just killed every transcription tool on the market. They dropped Scribe v2 Realtime and it's not just another speech-to-text model. This thing processes audio in real-time with zero lag, handles multiple speakers, and actually understands context not just words. Here's how with real examples: Full thread 🧵

Hasan Toor

220,564 views • 8 months ago

French President Macron: I do believe in free speech. But what does it mean? Free speech means I will listen to you, you will listen to me, and we are in an equal relationship. A lot of people defending free speech do it based on algorithms without any transparency, with a lot of bias, and with their own political agenda. It's not free speech. And when people clearly help hate speech, racist speech to be spread all over the place, it's not about free speech. It's a jungle. I really believe in free speech based on respect and transparency.

French President Macron: I do believe in free speech. But what does it mean? Free speech means I will listen to you, you will listen to me, and we are in an equal relationship. A lot of people defending free speech do it based on algorithms without any transparency, with a lot of bias, and with their own political agenda. It's not free speech. And when people clearly help hate speech, racist speech to be spread all over the place, it's not about free speech. It's a jungle. I really believe in free speech based on respect and transparency.

Open Source Intel

63,018 views • 5 months ago

French President Macron: I do believe in free speech. But what does it mean? Free speech means I will listen to you, you will listen to me, and we are in an equal relationship. A lot of people defending free speech do it based on algorithms without any transparency, with a lot of bias, and with their own political agenda. It's not free speech. And when people clearly help hate speech, racist speech to be spread all over the place, it's not about free speech. It's a jungle. I really believe in free speech based on respect and transparency.

French President Macron: I do believe in free speech. But what does it mean? Free speech means I will listen to you, you will listen to me, and we are in an equal relationship. A lot of people defending free speech do it based on algorithms without any transparency, with a lot of bias, and with their own political agenda. It's not free speech. And when people clearly help hate speech, racist speech to be spread all over the place, it's not about free speech. It's a jungle. I really believe in free speech based on respect and transparency.

Clash Report

787,804 views • 5 months ago

Hermes Agent is now free to run 24/7. No paid model needed. You can plug in: → Qwen 3.6 Plus → OwlAlpha via OpenRouter Both have 1M token context windows. That means your agent can research, write, find leads, handle tasks, and build workflows without burning through paid API credits. The best part? When one free model hits limits, just switch to the other. Free AI agents are getting scary fast.

Hermes Agent is now free to run 24/7. No paid model needed. You can plug in: → Qwen 3.6 Plus → OwlAlpha via OpenRouter Both have 1M token context windows. That means your agent can research, write, find leads, handle tasks, and build workflows without burning through paid API credits. The best part? When one free model hits limits, just switch to the other. Free AI agents are getting scary fast.

Julian Goldie SEO

21,609 views • 2 months ago

DONALD LUSKIN: EUROPEAN LEADERS ARE TRYING TO TAKE AWAY ELON’S FREE SPEECH IN PLAIN SIGHT “For the President of France to say that Elon Musk is interfering directly in elections because he is speaking his opinion is just ridiculous. It's a terrible distortion of the French language. It's not interference to speak, it is exercising your right to free speech. The leaders of Europe who are attacking Musk for free speech are, by doing so, proving his point. His point is that they are tyrannical leaders who are taking away people's free speech, and they're trying to take away his in plain sight. They're not even ashamed of it. They're just hoping you won't notice the breathtaking hypocrisy. This is what it means to be a totalitarian. You get to decide who has free speech. And what a coincidence! The people who get free speech are the people who agree with you. The people who don't are the people who disagree with you. Now, it's not that they don't love Elon Musk and 𝕏 and all the other social media platforms, they love to tax them. They just don't like to let the free speech happen there.” Source: Fox News, January 7, 2025

DONALD LUSKIN: EUROPEAN LEADERS ARE TRYING TO TAKE AWAY ELON’S FREE SPEECH IN PLAIN SIGHT “For the President of France to say that Elon Musk is interfering directly in elections because he is speaking his opinion is just ridiculous. It's a terrible distortion of the French language. It's not interference to speak, it is exercising your right to free speech. The leaders of Europe who are attacking Musk for free speech are, by doing so, proving his point. His point is that they are tyrannical leaders who are taking away people's free speech, and they're trying to take away his in plain sight. They're not even ashamed of it. They're just hoping you won't notice the breathtaking hypocrisy. This is what it means to be a totalitarian. You get to decide who has free speech. And what a coincidence! The people who get free speech are the people who agree with you. The people who don't are the people who disagree with you. Now, it's not that they don't love Elon Musk and 𝕏 and all the other social media platforms, they love to tax them. They just don't like to let the free speech happen there.” Source: Fox News, January 7, 2025

Mario Nawfal

54,605 views • 1 year ago

NVIDIA JUST DROPPED A FREE AI MODEL THAT READS PDFS, WATCHES VIDEOS, LISTENS TO AUDIO, AND UNDERSTANDS YOUR SCREEN SIMULTANEOUSLY. Not one at a time. ALL AT ONCE. In a single pass. It is called Nemotron 3 Nano Omni and it runs 9 times faster than every other multimodal model currently available. Think about what that actually means for how you work. Right now you are switching between tools constantly. One tool for transcribing your call recordings. A different tool for analyzing your client PDFs. Another tool for processing your training videos. A separate workflow for understanding what is happening on your screen. Four tools. Four contexts. Four different outputs you have to manually synthesize into one decision. Nemotron 3 Nano Omni does all of it in one model. One pass. One output. The use cases that just got dramatically simpler: Meeting recordings where you need the transcript, the visual context, and the document references all analyzed together. Training videos where the audio, the slides, and the on-screen demonstrations all feed into one coherent summary. Client PDFs where you need the document content cross-referenced against your screen data and your call notes simultaneously. Sales call transcripts analyzed alongside the proposals and the CRM data in one unified pass. This is not a marginal improvement on existing multimodal models. It is a 9x speed increase on a capability that was already changing how people work. Free. From NVIDIA. Available right now. Bookmark this before everyone catches on. Follow CyrilXBT for every AI capability shift the moment it drops.

NVIDIA JUST DROPPED A FREE AI MODEL THAT READS PDFS, WATCHES VIDEOS, LISTENS TO AUDIO, AND UNDERSTANDS YOUR SCREEN SIMULTANEOUSLY. Not one at a time. ALL AT ONCE. In a single pass. It is called Nemotron 3 Nano Omni and it runs 9 times faster than every other multimodal model currently available. Think about what that actually means for how you work. Right now you are switching between tools constantly. One tool for transcribing your call recordings. A different tool for analyzing your client PDFs. Another tool for processing your training videos. A separate workflow for understanding what is happening on your screen. Four tools. Four contexts. Four different outputs you have to manually synthesize into one decision. Nemotron 3 Nano Omni does all of it in one model. One pass. One output. The use cases that just got dramatically simpler: Meeting recordings where you need the transcript, the visual context, and the document references all analyzed together. Training videos where the audio, the slides, and the on-screen demonstrations all feed into one coherent summary. Client PDFs where you need the document content cross-referenced against your screen data and your call notes simultaneously. Sales call transcripts analyzed alongside the proposals and the CRM data in one unified pass. This is not a marginal improvement on existing multimodal models. It is a 9x speed increase on a capability that was already changing how people work. Free. From NVIDIA. Available right now. Bookmark this before everyone catches on. Follow CyrilXBT for every AI capability shift the moment it drops.

CyrilXBT

37,847 views • 2 months ago

Excited about the launch of Amazon Nova Sonic, our new speech-to-speech model that helps make AI voice applications feel remarkably natural. It's designed to understand not just what people say, but how they say it – working with tone, style, and conversation flow including pauses and interruptions. Nova Sonic delivers speech understanding and generation through a single, unified model, making it easier for builders to develop voice applications that maintain important context and nuance for customer service, AI agents, and other use cases across industries. It’s available in Amazon Bedrock now. Look forward to seeing what teams build with Nova Sonic!

Excited about the launch of Amazon Nova Sonic, our new speech-to-speech model that helps make AI voice applications feel remarkably natural. It's designed to understand not just what people say, but how they say it – working with tone, style, and conversation flow including pauses and interruptions. Nova Sonic delivers speech understanding and generation through a single, unified model, making it easier for builders to develop voice applications that maintain important context and nuance for customer service, AI agents, and other use cases across industries. It’s available in Amazon Bedrock now. Look forward to seeing what teams build with Nova Sonic!

Andy Jassy

155,772 views • 1 year ago

OpenAI's S2S preview is polished but it still thinks in steps. Speech → text → model → text → speech. That's not how humans converse. Introducing Hydra. A native speech-to-speech model that doesn't wait for turn-taking, doesn't flatten emotion into text, and doesn't break when you interrupt it mid-sentence. Hydra reasons asynchronously, speaks and listens simultaneously, and preserves emotion because it never leaves the audio domain. It's still in beta, but the shift is obvious. If you want early access, the link is in the comments. Here's a preview of what that looks like -

OpenAI's S2S preview is polished but it still thinks in steps. Speech → text → model → text → speech. That's not how humans converse. Introducing Hydra. A native speech-to-speech model that doesn't wait for turn-taking, doesn't flatten emotion into text, and doesn't break when you interrupt it mid-sentence. Hydra reasons asynchronously, speaks and listens simultaneously, and preserves emotion because it never leaves the audio domain. It's still in beta, but the shift is obvious. If you want early access, the link is in the comments. Here's a preview of what that looks like -

Sudarshan Kamath

328,927 views • 4 months ago

💥Bill Maher SCHOOLS Canadian Comedian Tom Green on why Canada *DOESN'T* have free speech like America🇺🇸 GREEN: "We have freedom of speech … There are hate speech laws in Canada — so there are things you can't say ... Who would want to say that sh*t anyways?" MAHER: "That's not what free speech means … You don’t know what free speech is." "The Supreme Court ruled in our country that the Nazis could march in Skokie, Illinois — which they were marching in because it is a community of a lot of Holocaust survivors ... That is what free speech is about."

💥Bill Maher SCHOOLS Canadian Comedian Tom Green on why Canada DOESN'T have free speech like America🇺🇸 GREEN: "We have freedom of speech … There are hate speech laws in Canada — so there are things you can't say ... Who would want to say that sh*t anyways?" MAHER: "That's not what free speech means … You don’t know what free speech is." "The Supreme Court ruled in our country that the Nazis could march in Skokie, Illinois — which they were marching in because it is a community of a lot of Holocaust survivors ... That is what free speech is about."

Jason Cohen 🇺🇸

1,442,608 views • 10 months ago

NVIDIA just removed the biggest friction point in Voice AI 🤯 They've open-sourced PersonaPlex-7B, a full-duplex conversational model that can listen and speak at the same time. Instead of waiting for you to finish talking, it uses a dual-stream architecture to process and respond in real-time. 100% Open-Source and Free.

NVIDIA just removed the biggest friction point in Voice AI 🤯 They've open-sourced PersonaPlex-7B, a full-duplex conversational model that can listen and speak at the same time. Instead of waiting for you to finish talking, it uses a dual-stream architecture to process and respond in real-time. 100% Open-Source and Free.

Simplifying AI

278,796 views • 6 months ago

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 views • 6 months ago

You can now generate real-time speech that sounds conversational. Microsoft just open-sourced VibeVoice, a real-time text-to-speech system with ~300 ms first audio latency and streaming input. It handles long conversations without falling apart. 𝗧𝗵𝗶𝘀 𝗺𝗼𝗱𝗲𝗹 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝘀 𝗹𝗼𝗻𝗴, 𝗺𝘂𝗹𝘁𝗶-𝘀𝗽𝗲𝗮𝗸𝗲𝗿 𝘀𝗽𝗲𝗲𝗰𝗵. It produces up to 90 minutes of audio. It supports up to four distinct speakers. Turn-taking stays consistent over long sessions. 𝗜𝘁 𝘄𝗼𝗿𝗸𝘀 𝗯𝘆 𝗿𝗲𝗱𝘂𝗰𝗶𝗻𝗴 𝘁𝗶𝗺𝗲 𝗿𝗲𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻. Audio compresses into semantic and acoustic tokens. They run at 7.5 Hz instead of frame-level audio. A language model predicts structure. A diffusion head restores acoustic detail. 𝗜𝘁 𝗮𝗹𝗹𝗼𝘄𝘀 𝗹𝗼𝘄-𝗹𝗮𝘁𝗲𝗻𝗰𝘆 𝘀𝘁𝗿𝗲𝗮𝗺𝗶𝗻𝗴 𝗮𝘂𝗱𝗶𝗼. The real-time variant streams text incrementally. First speech arrives in ~300 ms. A WebSocket demo shows live generation. The code is MIT-licensed and research-only. The repo already passed 20k GitHub stars.

You can now generate real-time speech that sounds conversational. Microsoft just open-sourced VibeVoice, a real-time text-to-speech system with ~300 ms first audio latency and streaming input. It handles long conversations without falling apart. 𝗧𝗵𝗶𝘀 𝗺𝗼𝗱𝗲𝗹 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝘀 𝗹𝗼𝗻𝗴, 𝗺𝘂𝗹𝘁𝗶-𝘀𝗽𝗲𝗮𝗸𝗲𝗿 𝘀𝗽𝗲𝗲𝗰𝗵. It produces up to 90 minutes of audio. It supports up to four distinct speakers. Turn-taking stays consistent over long sessions. 𝗜𝘁 𝘄𝗼𝗿𝗸𝘀 𝗯𝘆 𝗿𝗲𝗱𝘂𝗰𝗶𝗻𝗴 𝘁𝗶𝗺𝗲 𝗿𝗲𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻. Audio compresses into semantic and acoustic tokens. They run at 7.5 Hz instead of frame-level audio. A language model predicts structure. A diffusion head restores acoustic detail. 𝗜𝘁 𝗮𝗹𝗹𝗼𝘄𝘀 𝗹𝗼𝘄-𝗹𝗮𝘁𝗲𝗻𝗰𝘆 𝘀𝘁𝗿𝗲𝗮𝗺𝗶𝗻𝗴 𝗮𝘂𝗱𝗶𝗼. The real-time variant streams text incrementally. First speech arrives in ~300 ms. A WebSocket demo shows live generation. The code is MIT-licensed and research-only. The repo already passed 20k GitHub stars.

Lior Alexander

61,122 views • 6 months ago

🇺🇸 SPEAKER JOHNSON: INCITE VIOLENCE IS NOT FREE SPEECH "America is built on the idea of free speech. You have the right to protest. We've defended that right in the courts. But what they're doing right now is different. I mean, they are trying to incite violence. You don't mock a president who has already had two failed assassination attempts on his life." Source: Acyn, Speaker Mike Johnson

🇺🇸 SPEAKER JOHNSON: INCITE VIOLENCE IS NOT FREE SPEECH "America is built on the idea of free speech. You have the right to protest. We've defended that right in the courts. But what they're doing right now is different. I mean, they are trying to incite violence. You don't mock a president who has already had two failed assassination attempts on his life." Source: Acyn, Speaker Mike Johnson

Mario Nawfal

62,840 views • 9 months ago

Anthropic pays its ML engineers $500K+/year to deploy what Percy Liang just taught for free in Lecture 3 of CS221. 80 minutes. one whiteboard. everything between "a neuron" and the model running in your IDE right now. three things click after this one: / why two Claude prompts that "mean the same thing" land in different regions of weight space / why fine-tuning sometimes makes a model dumber, not smarter / what RLHF actually changes when Anthropic aligns Claude same $90K Stanford sequence. lecture 3 of ~20. free. the gap between "using Claude" and "understanding it" is exactly one lecture wide.

Anthropic pays its ML engineers $500K+/year to deploy what Percy Liang just taught for free in Lecture 3 of CS221. 80 minutes. one whiteboard. everything between "a neuron" and the model running in your IDE right now. three things click after this one: / why two Claude prompts that "mean the same thing" land in different regions of weight space / why fine-tuning sometimes makes a model dumber, not smarter / what RLHF actually changes when Anthropic aligns Claude same $90K Stanford sequence. lecture 3 of ~20. free. the gap between "using Claude" and "understanding it" is exactly one lecture wide.

dunik

24,381 views • 2 months ago