Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We finally have open-source, long-form, expressive TTS models. VibeVoice-1.5B from Microsoft: ✅ MIT licensed ✅ Up to 90 minutes long ✅ Highly expressive & emotional!

realmrfakename's profile picture

mrfakename

2,852 subscribers

168,591 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Microsoft just dropped VibeVoice-Realtime-0.5B Open-source realtime TTS AI model that starts talking in ~300 ms Streaming, long-form and insanely fast.
4:30

Microsoft just dropped VibeVoice-Realtime-0.5B Open-source realtime TTS AI model that starts talking in ~300 ms Streaming, long-form and insanely fast.

Min Choi

80,970 Aufrufe • vor 9 Monaten

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

Marvis-TTS-v0.2 is here 🚀 A local first TTS model capable of realtime performance even on older iPhones that Lucas Newman and I built. What’s new: ✨ Blazing fast — 100M (tiny) & 250M parameter models 🌍 Multilingual — English, French, German 🎭 Enhanced voice cloning — More natural & expressive ⚡ Long-form generation — Up to 90 seconds (4x improvement) Get started today: > pip install -U mlx-audio
2:38

Marvis-TTS-v0.2 is here 🚀 A local first TTS model capable of realtime performance even on older iPhones that Lucas Newman and I built. What’s new: ✨ Blazing fast — 100M (tiny) & 250M parameter models 🌍 Multilingual — English, French, German 🎭 Enhanced voice cloning — More natural & expressive ⚡ Long-form generation — Up to 90 seconds (4x improvement) Get started today: > pip install -U mlx-audio

Prince Canuma

118,522 Aufrufe • vor 10 Monaten

🌟New Rules Game ✅Tag the runner & shut down the return pass (new game demands slowing transitions at source to get set up) ✅Scan Long First (With 3v3 we now have long options) Players are conditioned to scan short. Help them learn scan long early 👩‍💻
0:59

🌟New Rules Game ✅Tag the runner & shut down the return pass (new game demands slowing transitions at source to get set up) ✅Scan Long First (With 3v3 we now have long options) Players are conditioned to scan short. Help them learn scan long early 👩‍💻

iGaelicCoach

11,513 Aufrufe • vor 1 Jahr

today we are releasing Le Lamp. an open source expressive robot. expressive interaction design is the missing layer in robotics. the future isn’t just functional robots - it’s robots that feel natural to use and are designed from the ground up for expressive human-robot interaction. we will continue iterating Le Lamp to make it more expressive and useful in the upcoming weeks. github: discord: order the Le Lamp kit:
2:04

today we are releasing Le Lamp. an open source expressive robot. expressive interaction design is the missing layer in robotics. the future isn’t just functional robots - it’s robots that feel natural to use and are designed from the ground up for expressive human-robot interaction. we will continue iterating Le Lamp to make it more expressive and useful in the upcoming weeks. github: discord: order the Le Lamp kit:

Shahvir Sarkary

57,565 Aufrufe • vor 1 Jahr

MiniMax-Music3 is now open source. 🎶 Generate complete songs up to five minutes long, with expressive vocals, evolving arrangements, and coherent structure from intro to outro. 🤖 🧠 Around 11.1B parameters: an 8B Global LLM for long-range structure, a 0.6B Local LLM for acoustic detail, plus a 2.4B Flow Matching model and 123M decoder. 🎤 Control lyrics, song sections, genre, mood, vocals, instrumentation, and arrangement development. 🎧 Generates 32 kHz, 16-bit stereo WAV audio with stable long-form quality. Listen to the demos👇
1:00

MiniMax-Music3 is now open source. 🎶 Generate complete songs up to five minutes long, with expressive vocals, evolving arrangements, and coherent structure from intro to outro. 🤖 🧠 Around 11.1B parameters: an 8B Global LLM for long-range structure, a 0.6B Local LLM for acoustic detail, plus a 2.4B Flow Matching model and 123M decoder. 🎤 Control lyrics, song sections, genre, mood, vocals, instrumentation, and arrangement development. 🎧 Generates 32 kHz, 16-bit stereo WAV audio with stable long-form quality. Listen to the demos👇

ModelScope

18,047 Aufrufe • vor 1 Monat

🚨 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

221,715 Aufrufe • vor 5 Monaten

We already have everything inside us to master our mind and body, we just were never taught how. Andrew Huberman says tools like morning sunlight, long exhales, ice baths, and 15-minute Pennebaker journaling can radically change how we feel. Expressive writing about emotional distress for 15 minutes on 3–4 consecutive days (the Pennebaker protocol) has been shown in dozens of studies to reduce anxiety, improve immune function, and lower trauma symptoms long-term.
2:39

We already have everything inside us to master our mind and body, we just were never taught how. Andrew Huberman says tools like morning sunlight, long exhales, ice baths, and 15-minute Pennebaker journaling can radically change how we feel. Expressive writing about emotional distress for 15 minutes on 3–4 consecutive days (the Pennebaker protocol) has been shown in dozens of studies to reduce anxiety, improve immune function, and lower trauma symptoms long-term.

Camus

31,903 Aufrufe • vor 3 Monaten

NVIDIA Cosmos Reason 2 is here. 🥳 An open, highly accurate reasoning vision language model for physical AI, featuring: ✅ Improved spatio-temporal understanding and timestamp precision ✅ Flexible deployment with 2B and 8B model sizes ✅ Long-context reasoning with up to 256K tokens ✅ Expanded visual perception across complex environments We also have new Cosmos releases: Predict 2.5, Transfer 2.5, and the NVIDIA GR00T N1.6 robot foundation model. 📗Read our technical blog: 🤗 Download Cosmos Reason 2 on Hugging Face:
0:57

NVIDIA Cosmos Reason 2 is here. 🥳 An open, highly accurate reasoning vision language model for physical AI, featuring: ✅ Improved spatio-temporal understanding and timestamp precision ✅ Flexible deployment with 2B and 8B model sizes ✅ Long-context reasoning with up to 256K tokens ✅ Expanded visual perception across complex environments We also have new Cosmos releases: Predict 2.5, Transfer 2.5, and the NVIDIA GR00T N1.6 robot foundation model. 📗Read our technical blog: 🤗 Download Cosmos Reason 2 on Hugging Face:

NVIDIA AI Developer

45,677 Aufrufe • vor 8 Monaten

Otra alternativa a CapCut que no te pone watermark y te roba la privacidad [OpenReel Video] ✅ 100% en el navegador (sin instalar nada) ✅ 100% local (tus videos NUNCA salen de tu PC) ✅ Sin watermarks, sin límites, sin nube ✅ Open Source (MIT) y gratis para siempre Con timeline profesional multi-pista, IA para subtítulos automáticos (90+ idiomas + karaoke style), grading estilo DaVinci, animaciones 3D, chroma key, TTS, multi-track audio y export en ProRes/4K. REPOOO👇
0:28

Otra alternativa a CapCut que no te pone watermark y te roba la privacidad [OpenReel Video] ✅ 100% en el navegador (sin instalar nada) ✅ 100% local (tus videos NUNCA salen de tu PC) ✅ Sin watermarks, sin límites, sin nube ✅ Open Source (MIT) y gratis para siempre Con timeline profesional multi-pista, IA para subtítulos automáticos (90+ idiomas + karaoke style), grading estilo DaVinci, animaciones 3D, chroma key, TTS, multi-track audio y export en ProRes/4K. REPOOO👇

Erick

120,726 Aufrufe • vor 4 Monaten

💥Simple guide on Berachain Foundation 🐻⛓ Testnet V2 💰$142M funding 💯FREE ⚠️Don't skip this, because it's L1 ✅So they want token to Go mainnet 🤔Decent chances of 🪂to testnet users 👇Steps 📝All links can be accessed from dapps list in main website 🔗 1️⃣Faucet ✅Select faucet ✅Enter wallet & get test tokens ⌚U can claim every 8hrs 2️⃣Faucet 2 🔗 ✅Connect wallet & claim ⌚U can claim every day 3️⃣DEX ✅Select BEX on website ✅Connect wallet ✅Add Testnet in metamask ✅Swap Bera to Honey ✅Go to pool ✅Add liquidity to BERA/HONEY pool 4️⃣BGT Station ✅Stake LP tokens to farm $BGT 5️⃣Honey ✅Get some SGTUSDC from DEX ✅Select Honey dapp on list ✅Mint $HONEY with SGTUSDC 6️⃣Bend ✅Get some WBTC from BEX ✅Supply $WBTC ✅Borrow $HONEY 7️⃣Berps ✅Open Berps link ✅Open long or short position 8️⃣Delegation ✅Go to BGT Station ✅Claim $BGT ✅Delegate $BGT to any 9️⃣Beratrails ✅Select beratrails on dapp list ✅Paste ur wallet address & track ur number of txns on V2 ✅We interacted with all official dapps 💥Regularly do testnet transaction 💙Like 🔁RT
3:46

💥Simple guide on Berachain Foundation 🐻⛓ Testnet V2 💰$142M funding 💯FREE ⚠️Don't skip this, because it's L1 ✅So they want token to Go mainnet 🤔Decent chances of 🪂to testnet users 👇Steps 📝All links can be accessed from dapps list in main website 🔗 1️⃣Faucet ✅Select faucet ✅Enter wallet & get test tokens ⌚U can claim every 8hrs 2️⃣Faucet 2 🔗 ✅Connect wallet & claim ⌚U can claim every day 3️⃣DEX ✅Select BEX on website ✅Connect wallet ✅Add Testnet in metamask ✅Swap Bera to Honey ✅Go to pool ✅Add liquidity to BERA/HONEY pool 4️⃣BGT Station ✅Stake LP tokens to farm $BGT 5️⃣Honey ✅Get some SGTUSDC from DEX ✅Select Honey dapp on list ✅Mint $HONEY with SGTUSDC 6️⃣Bend ✅Get some WBTC from BEX ✅Supply $WBTC ✅Borrow $HONEY 7️⃣Berps ✅Open Berps link ✅Open long or short position 8️⃣Delegation ✅Go to BGT Station ✅Claim $BGT ✅Delegate $BGT to any 9️⃣Beratrails ✅Select beratrails on dapp list ✅Paste ur wallet address & track ur number of txns on V2 ✅We interacted with all official dapps 💥Regularly do testnet transaction 💙Like 🔁RT

CryptoTelugu

249,665 Aufrufe • vor 2 Jahren

🔒 Exciting news! The long-awaited 𝐬𝐭𝐚𝐤𝐢𝐧𝐠 𝐩𝐥𝐚𝐭𝐟𝐨𝐫𝐦 is finally on its way! ✅ Built and coded from scratch, check! ✅ Internal testnet, check! 🔍 Audit, currently in progress! 🚀 Soon to be released for selected testers! The next Galxe campaign? On its way!
2:34

🔒 Exciting news! The long-awaited 𝐬𝐭𝐚𝐤𝐢𝐧𝐠 𝐩𝐥𝐚𝐭𝐟𝐨𝐫𝐦 is finally on its way! ✅ Built and coded from scratch, check! ✅ Internal testnet, check! 🔍 Audit, currently in progress! 🚀 Soon to be released for selected testers! The next Galxe campaign? On its way!

Tyche Protocol

88,454 Aufrufe • vor 3 Jahren

DONnell ✅ We are pleased to announce the signing of forward Donnell McNeilly on a season-long loan, with an option to buy, from Nottingham Forest 🤝 🔗
0:34

DONnell ✅ We are pleased to announce the signing of forward Donnell McNeilly on a season-long loan, with an option to buy, from Nottingham Forest 🤝 🔗

AFC Wimbledon

82,630 Aufrufe • vor 23 Tagen

🤝 Alphabet and NVIDIA are expanding their decade-long partnership to advance agentic AI, robotics, drug discovery, and more. This involves deep co-engineering with integrated platforms, open-source frameworks, and managed services. ✅ Google Cloud is one of the first to bring the NVIDIA Blackwell platform to the cloud. ✅ Google Distributed Cloud using NVIDIA Confidential Computing on #NVIDIABlackwell for enterprises to run Google Gemini on-premises. ✅ Integration of the NVIDIA AI platform across Vertex AI, Cluster Director and Google Kubernetes Engine. ✅ Bringing the NVIDIA Nemotron family of open models to Vertex AI Model Garden. Watch the full video to learn more ➡️
0:30

🤝 Alphabet and NVIDIA are expanding their decade-long partnership to advance agentic AI, robotics, drug discovery, and more. This involves deep co-engineering with integrated platforms, open-source frameworks, and managed services. ✅ Google Cloud is one of the first to bring the NVIDIA Blackwell platform to the cloud. ✅ Google Distributed Cloud using NVIDIA Confidential Computing on #NVIDIABlackwell for enterprises to run Google Gemini on-premises. ✅ Integration of the NVIDIA AI platform across Vertex AI, Cluster Director and Google Kubernetes Engine. ✅ Bringing the NVIDIA Nemotron family of open models to Vertex AI Model Garden. Watch the full video to learn more ➡️

NVIDIA AI Infrastructure

268,567 Aufrufe • vor 8 Monaten

💥Simple guide on Berachain Foundation 🐻⛓ Testnet V2 😁Few were asking for detailed guide on my previous post 💰$142M funding 💯FREE ⚠️Don't skip this, because it's L1 ✅So they want token to Go mainnet 🤔Decent chances of 🪂to testnet users 👇Steps 📝All links can be accessed from dapps list in main website 🔗 1️⃣Faucet ✅Select faucet ✅Enter wallet & get test tokens ⌚U can claim every 8hrs 2️⃣Faucet 2 🔗 ✅Connect wallet & claim ⌚U can claim every day 3️⃣DEX ✅Select BEX on website ✅Connect wallet ✅Add Testnet in metamask ✅Swap Bera to Honey ✅Go to pool ✅Add liquidity to BERA/HONEY pool 4️⃣BGT Station ✅Stake LP tokens to farm $BGT 5️⃣Honey ✅Get some SGTUSDC from DEX ✅Select Honey dapp on list ✅Mint $HONEY with SGTUSDC 6️⃣Bend ✅Get some WBTC from BEX ✅Supply $WBTC ✅Borrow $HONEY 7️⃣Berps ✅Open Berps link ✅Open long or short position 8️⃣Delegation ✅Go to BGT Station ✅Claim $BGT ✅Delegate $BGT to any 9️⃣Beratrails ✅Select beratrails on dapp list ✅Paste ur wallet address & track ur number of txns on V2 ✅We interacted with all official dapps 💥Claim faucet twice a day & Regularly add liquidity & stake LP to earn $BGT 💙Like 🔁RT
3:46

💥Simple guide on Berachain Foundation 🐻⛓ Testnet V2 😁Few were asking for detailed guide on my previous post 💰$142M funding 💯FREE ⚠️Don't skip this, because it's L1 ✅So they want token to Go mainnet 🤔Decent chances of 🪂to testnet users 👇Steps 📝All links can be accessed from dapps list in main website 🔗 1️⃣Faucet ✅Select faucet ✅Enter wallet & get test tokens ⌚U can claim every 8hrs 2️⃣Faucet 2 🔗 ✅Connect wallet & claim ⌚U can claim every day 3️⃣DEX ✅Select BEX on website ✅Connect wallet ✅Add Testnet in metamask ✅Swap Bera to Honey ✅Go to pool ✅Add liquidity to BERA/HONEY pool 4️⃣BGT Station ✅Stake LP tokens to farm $BGT 5️⃣Honey ✅Get some SGTUSDC from DEX ✅Select Honey dapp on list ✅Mint $HONEY with SGTUSDC 6️⃣Bend ✅Get some WBTC from BEX ✅Supply $WBTC ✅Borrow $HONEY 7️⃣Berps ✅Open Berps link ✅Open long or short position 8️⃣Delegation ✅Go to BGT Station ✅Claim $BGT ✅Delegate $BGT to any 9️⃣Beratrails ✅Select beratrails on dapp list ✅Paste ur wallet address & track ur number of txns on V2 ✅We interacted with all official dapps 💥Claim faucet twice a day & Regularly add liquidity & stake LP to earn $BGT 💙Like 🔁RT

CryptoTelugu

81,665 Aufrufe • vor 2 Jahren

Today we released our March Quarterly Activities Report, delivering a strong operational quarter and a record production of 232,400 tonnes 🔋 Here are some of the other highlights from the quarter: ✅Average realised pricing up 61% to US$1,867 ✅Revenue up 52% to $567M ✅Unit operating costs down 11% ✅Cash balance of $1.5B at 31 March 2026 Importantly, all three of our core value drivers moved in our favour – volumes up, costs down, pricing stronger 📈 Read more 👉 $PLS #Lithium #QuarterlyResults
2:47

Today we released our March Quarterly Activities Report, delivering a strong operational quarter and a record production of 232,400 tonnes 🔋 Here are some of the other highlights from the quarter: ✅Average realised pricing up 61% to US$1,867 ✅Revenue up 52% to $567M ✅Unit operating costs down 11% ✅Cash balance of $1.5B at 31 March 2026 Importantly, all three of our core value drivers moved in our favour – volumes up, costs down, pricing stronger 📈 Read more 👉 $PLS #Lithium #QuarterlyResults

PLS

12,269 Aufrufe • vor 5 Monaten