Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Microsoft just dropped VibeVoice (open-source) This AI turn text into a 90-min, up to 4-voice podcast. With natural pauses, emotion, even singing. 6 wild examples + code: 1. Spontaneous singing

minchoi's profile picture

Min Choi

323,237 subscribers

94,614 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieBildungKunst
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

This is wild. Hume AI just dropped Octave 2. Ultra realistic text-to-speech AI model in 10+ languages with multi-speaker + voice cloning. 100% AI 8 wild examples + how to try:
0:51

This is wild. Hume AI just dropped Octave 2. Ultra realistic text-to-speech AI model in 10+ languages with multi-speaker + voice cloning. 100% AI 8 wild examples + how to try:

Min Choi

212,441 Aufrufe • vor 11 Monaten

Meta just announced MoCha This AI can create full movie-quality talking & singing characters from just speech & text. 10 wild examples: 1. Talking Characters
0:20

Meta just announced MoCha This AI can create full movie-quality talking & singing characters from just speech & text. 10 wild examples: 1. Talking Characters

Min Choi

420,283 Aufrufe • vor 1 Jahr

🚨BREAKING: A new open-source voice model just dropped and it’s better than ElevenLabs. This open-source voice AI is ultra-expressive, high quality, and fully free with no paywalls, no limits. Here’s how it works (with real examples):👇
0:26

🚨BREAKING: A new open-source voice model just dropped and it’s better than ElevenLabs. This open-source voice AI is ultra-expressive, high quality, and fully free with no paywalls, no limits. Here’s how it works (with real examples):👇

Sehaj Singh

814,129 Aufrufe • vor 1 Jahr

Tencent just dropped HunyuanWorld-1.0 This is world's first open source 3D world generator text / image → roamable VR scene, mesh export, game-engine ready. 10 wild examples + how to try:👇
1:13

Tencent just dropped HunyuanWorld-1.0 This is world's first open source 3D world generator text / image → roamable VR scene, mesh export, game-engine ready. 10 wild examples + how to try:👇

Min Choi

125,110 Aufrufe • vor 1 Jahr

Microsoft just dropped VASA-1. This AI can make single image sing and talk from audio reference expressively. Similar to EMO from Alibaba 10 wild examples: 1. Mona Lisa rapping Paparazzi
0:22

Microsoft just dropped VASA-1. This AI can make single image sing and talk from audio reference expressively. Similar to EMO from Alibaba 10 wild examples: 1. Mona Lisa rapping Paparazzi

Min Choi

7,300,570 Aufrufe • vor 2 Jahren

ByteDance (TikTok) announced Loopy recently. AI that brings any single image to life, making it sing and talk with facial expressions from an audio reference. 🤯 Similar to EMO (Alibaba) and VASA-1 (Microsoft) 10 wild examples: 1. Leonardo DiCaprio singing a Chinese song
0:46

ByteDance (TikTok) announced Loopy recently. AI that brings any single image to life, making it sing and talk with facial expressions from an audio reference. 🤯 Similar to EMO (Alibaba) and VASA-1 (Microsoft) 10 wild examples: 1. Leonardo DiCaprio singing a Chinese song

Min Choi

298,932 Aufrufe • vor 2 Jahren

SwiftUI: You can chain free and open-source STT, TTS, and LLMs to build voice/vision apps with Core AI. Here is a demo I was experimenting with: - Whisper: Speech-to-text - Kokoro-82M: Text-to-speech - Qwen3-VL 2B: Vision I converted Pocket TTS and VibeVoice to Core AI models and tried with Gemma 4. All is working great.
0:36

SwiftUI: You can chain free and open-source STT, TTS, and LLMs to build voice/vision apps with Core AI. Here is a demo I was experimenting with: - Whisper: Speech-to-text - Kokoro-82M: Text-to-speech - Qwen3-VL 2B: Vision I converted Pocket TTS and VibeVoice to Core AI models and tried with Gemma 4. All is working great.

Amos Gyamfi

79,756 Aufrufe • vor 2 Monaten

Just 5 days ago, Hailuo AI dropped Minimax, a new Chinese text-to-video AI. And people are producing creative results 10 wild examples: 1. Will Smith eating spaghetti goes next level
0:28

Just 5 days ago, Hailuo AI dropped Minimax, a new Chinese text-to-video AI. And people are producing creative results 10 wild examples: 1. Will Smith eating spaghetti goes next level

Min Choi

752,179 Aufrufe • vor 2 Jahren

Microsoft just integrated music creation app Suno into its Copilot AI. Music, lyrics, all instruments and singing by AI. A version similar will be in open source soon. 100 billion “new” “songs” soon. I’m sorry. Prompt: “Make a metal song about baseball”.
0:44

Microsoft just integrated music creation app Suno into its Copilot AI. Music, lyrics, all instruments and singing by AI. A version similar will be in open source soon. 100 billion “new” “songs” soon. I’m sorry. Prompt: “Make a metal song about baseball”.

Brian Roemmele

243,710 Aufrufe • vor 2 Jahren

wtf.. this is mindblowing.. GoogleDeepMind just dropped Genie 3 you can generate interactive 3D world with text, navigate with keys and.. interact in real time.. AI is crazy 10 examples: 1. navigate to a car and open the door.. omg
0:34

wtf.. this is mindblowing.. GoogleDeepMind just dropped Genie 3 you can generate interactive 3D world with text, navigate with keys and.. interact in real time.. AI is crazy 10 examples: 1. navigate to a car and open the door.. omg

el.cine

1,450,828 Aufrufe • vor 1 Jahr

This is wild. MiniMax-M1 just dropped. This AI agent = Manus + Deep Research + Computer Use + Lovable in one. 1M token memory, open weights🤯 10 wild examples + prompts & demo: 1. Netflix clone with playable trailers
0:28

This is wild. MiniMax-M1 just dropped. This AI agent = Manus + Deep Research + Computer Use + Lovable in one. 1M token memory, open weights🤯 10 wild examples + prompts & demo: 1. Netflix clone with playable trailers

Min Choi

539,094 Aufrufe • vor 1 Jahr

This is wild. OpenAI just dropped Codex Sites. Now anyone can give it a plan, dashboard, launch doc or idea, and turn it into an interactive app with a URL. 5 wild examples:
0:31

This is wild. OpenAI just dropped Codex Sites. Now anyone can give it a plan, dashboard, launch doc or idea, and turn it into an interactive app with a URL. 5 wild examples:

Min Choi

354,460 Aufrufe • vor 3 Monaten

This is wild. Google just dropped Gemini 2.5 And it just topped the AI Arena Leaderboard with the biggest jump ever. Here's what it all means, and 6 wild examples: 1. Interactive health and economic charts
1:11

This is wild. Google just dropped Gemini 2.5 And it just topped the AI Arena Leaderboard with the biggest jump ever. Here's what it all means, and 6 wild examples: 1. Interactive health and economic charts

Min Choi

344,851 Aufrufe • vor 1 Jahr

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!
1:10

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 🚀

45,256 Aufrufe • vor 5 Monaten

turn ANY photo into a singing music video in 1 tap 🎵✨ no editing. no voice training. just pure AI magic. i tested Vibeme.ai and here's why everyone's about to be obsessed 🧵
0:37

turn ANY photo into a singing music video in 1 tap 🎵✨ no editing. no voice training. just pure AI magic. i tested Vibeme.ai and here's why everyone's about to be obsessed 🧵

Kumail Sikandar

37,875 Aufrufe • vor 9 Monaten

Introducing a Text-to-API AI ⚙️ Turn any website into an API with 's /extract. Just describe your API in plain text and get an endpoint you can hit. Another great open-source project by !
0:52

Introducing a Text-to-API AI ⚙️ Turn any website into an API with 's /extract. Just describe your API in plain text and get an endpoint you can hit. Another great open-source project by !

Caleb Peffer (Hiring!)

262,812 Aufrufe • vor 1 Jahr

This is totally wild Google Veo 3 dropped just 90 hours ago, and people literally can’t stop creating with it No one can believe this is 100% AI 10 new trending examples: 1. A car show that never happened all AI-generated.
0:38

This is totally wild Google Veo 3 dropped just 90 hours ago, and people literally can’t stop creating with it No one can believe this is 100% AI 10 new trending examples: 1. A car show that never happened all AI-generated.

ZOYA ✪

4,845,382 Aufrufe • vor 1 Jahr

Microsoft just dropped Muse. This AI can generate minutes of smooth gameplay from just 1 second of footage & controls. And it's open source! The future of gaming is about to change forever.
2:00

Microsoft just dropped Muse. This AI can generate minutes of smooth gameplay from just 1 second of footage & controls. And it's open source! The future of gaming is about to change forever.

Min Choi

102,961 Aufrufe • vor 1 Jahr

🚨 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. 👇
0:44

🚨 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

221,357 Aufrufe • vor 4 Monaten

This is wild. China's Alibaba just dropped Live Avatar. This AI turns any voice into a realtime, talking avatar with infinite length at 20 FPS. 10 wild demos:👇 1. Ilya interview that never happened
1:26

This is wild. China's Alibaba just dropped Live Avatar. This AI turns any voice into a realtime, talking avatar with infinite length at 20 FPS. 10 wild demos:👇 1. Ilya interview that never happened

Min Choi

220,955 Aufrufe • vor 9 Monaten