Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

BOOM! Microsoft just released an upgraded VibeVoice Large ~10B Text to Speech model - MIT licensed ๐Ÿ”ฅ > Generate multi-speaker podcasts in minutes โšก > Works blazingly fast on ZeroGPU with H200 (FREE) Try it out today!

reach_vb's profile picture

Vaibhav (VB) Srivastav

43,385 subscribers

89,549 Aufrufe โ€ข vor 10 Monaten โ€ขvia X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossiโ€ข Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfรผgbar

Kommentare vom Original-Post werden hier angezeigt

ร„hnliche Videos

Introducing Supertonic WebGPU: blazingly fast text-to-speech running 100% locally in your browser. โšก๏ธ Generate free audiobooks in seconds, no installation required. In this example, I created a 5-hour audiobook of The Great Gatsby in less than 3 minutes! ๐Ÿคฏ Try it yourself! ๐Ÿ‘‡
1:28

Introducing Supertonic WebGPU: blazingly fast text-to-speech running 100% locally in your browser. โšก๏ธ Generate free audiobooks in seconds, no installation required. In this example, I created a 5-hour audiobook of The Great Gatsby in less than 3 minutes! ๐Ÿคฏ Try it yourself! ๐Ÿ‘‡

Xenova

23,474 Aufrufe โ€ข vor 7 Monaten

Microsoft just killed voice subscriptions. ๐Ÿคฏ They quietly open-sourced VibeVoice, and itโ€™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
1:10

Microsoft just killed voice subscriptions. ๐Ÿคฏ They quietly open-sourced VibeVoice, and itโ€™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 Aufrufe โ€ข vor 2 Monaten

BOOM! Latest Qwen 30B A3B 2507 running blazingly fast on Mac powered by MLX ๐Ÿ’ฅ mlx_lm.chat --model "lmstudio-community/Qwen3-30B-A3B-Instruct-2507-MLX-4bit" That's it, try it out today!
1:38

BOOM! Latest Qwen 30B A3B 2507 running blazingly fast on Mac powered by MLX ๐Ÿ’ฅ mlx_lm.chat --model "lmstudio-community/Qwen3-30B-A3B-Instruct-2507-MLX-4bit" That's it, try it out today!

Vaibhav (VB) Srivastav

35,873 Aufrufe โ€ข vor 11 Monaten

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 โ€ข vor 9 Monaten

We finally have open-source, long-form, expressive TTS models. VibeVoice-1.5B from Microsoft: โœ… MIT licensed โœ… Up to 90 minutes long โœ… Highly expressive & emotional!
1:08

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

mrfakename

168,359 Aufrufe โ€ข vor 10 Monaten

๐Ÿง‘โ€๐Ÿณ Microsoft cooked with VibeVoice-Large (MIT license) We are now super close to 100% open source NotebookLM ๐Ÿ’ซ (demo on Hugging Face)
0:20

๐Ÿง‘โ€๐Ÿณ Microsoft cooked with VibeVoice-Large (MIT license) We are now super close to 100% open source NotebookLM ๐Ÿ’ซ (demo on Hugging Face)

Victor M

28,568 Aufrufe โ€ข vor 10 Monaten

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 said..all in one shot and it handles the hard stuff too..50+ languages, custom hotwords, long form audio that breaks every other tool the model doesn't know what "context window" means apparently Available on macOS and Windows right now. Free to use. Free to fine tune. Free to build on.
5:45

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 said..all in one shot and it handles the hard stuff too..50+ languages, custom hotwords, long form audio that breaks every other tool the model doesn't know what "context window" means apparently Available on macOS and Windows right now. Free to use. Free to fine tune. Free to build on.

Rahul

1,371,872 Aufrufe โ€ข vor 2 Monaten

Microsoft just released Agent Mode in Excel. It created a financial model in minutes:
1:53

Microsoft just released Agent Mode in Excel. It created a financial model in minutes:

Alex Banks

43,106 Aufrufe โ€ข vor 9 Monaten

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! ๐Ÿ”ฅ > Zero-shot TTS with Voice Cloning: Input text and a 10-30 second speaker sample to generate high-quality text-to-speech output > Audio Prefix Inputs: Enhance speaker matching by adding an audio prefix to the text, enabling behaviors like whispering that are hard to achieve with voice cloning alone > Multilingual Support: Supports English, Japanese, Chinese, French, and German > Audio Quality & Emotion Control: Fine-tune speaking rate, pitch, frequency, audio quality, and emotions (e.g., happiness, anger, sadness, fear) > Fast Performance: Runs at ~2x real-time speed on an RTX 4090 > Available on the Hugging Face Hub ๐Ÿค—
1:21

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! ๐Ÿ”ฅ > Zero-shot TTS with Voice Cloning: Input text and a 10-30 second speaker sample to generate high-quality text-to-speech output > Audio Prefix Inputs: Enhance speaker matching by adding an audio prefix to the text, enabling behaviors like whispering that are hard to achieve with voice cloning alone > Multilingual Support: Supports English, Japanese, Chinese, French, and German > Audio Quality & Emotion Control: Fine-tune speaking rate, pitch, frequency, audio quality, and emotions (e.g., happiness, anger, sadness, fear) > Fast Performance: Runs at ~2x real-time speed on an RTX 4090 > Available on the Hugging Face Hub ๐Ÿค—

Vaibhav (VB) Srivastav

298,858 Aufrufe โ€ข vor 1 Jahr

BOOM! IBM just released an updated SmolDocling - tiny 258M param SoTA VLM - Apache 2.0 licensed! ๐Ÿ”ฅ Capable of doing OCR, Visual QA, Translation and much more - try it out now!
0:40

BOOM! IBM just released an updated SmolDocling - tiny 258M param SoTA VLM - Apache 2.0 licensed! ๐Ÿ”ฅ Capable of doing OCR, Visual QA, Translation and much more - try it out now!

Vaibhav (VB) Srivastav

52,852 Aufrufe โ€ข 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 ๐Ÿš€

45,206 Aufrufe โ€ข vor 3 Monaten

NEW: Kokoro 82M - APACHE 2.0 licensed, Text to Speech model, trained on < 100 hours of audio ๐Ÿ”ฅ
1:54

NEW: Kokoro 82M - APACHE 2.0 licensed, Text to Speech model, trained on < 100 hours of audio ๐Ÿ”ฅ

Vaibhav (VB) Srivastav

330,034 Aufrufe โ€ข vor 1 Jahr

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 โ€ข vor 7 Monaten

๐Ÿšจ 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 ๐Ÿ‘‡ VibeVoice ASR - Speech Recognition: โ†’ Processes 60 minutes of continuous audio in a single pass โ†’ Never slices audio into chunks so global context is never lost โ†’ Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously โ†’ Supports customized hotwords for domain specific accuracy โ†’ Works in 50+ languages natively โ†’ Already adopted by Hugging Face Transformers library โ†’ 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: โ†’ Generates up to 90 minutes of speech in a single pass โ†’ Supports up to 4 distinct speakers in one conversation โ†’ Natural turn taking and speaker consistency throughout โ†’ Expressive speech that captures emotional nuances โ†’ Supports English, Chinese and multiple other languages VibeVoice Realtime - Streaming TTS: โ†’ Only 300 millisecond first audible latency โ†’ Streams text input in real time โ†’ 0.5B parameters so it actually deploys anywhere โ†’ Robust long form generation up to 10 minutes โ†’ 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: โ†’ VibeVoice ASR 7B - available now on Hugging Face โ†’ VibeVoice Realtime 0.5B - try it on Colab right now โ†’ 50+ supported languages โ†’ 11 distinct English voice styles โ†’ 9 multilingual speaker voices โ†’ Already integrated into Hugging Face Transformers โ†’ 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. ๐Ÿ”– Save this before your competitors find it first. ๐Ÿ‘‡
0:44

๐Ÿšจ 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 ๐Ÿ‘‡ VibeVoice ASR - Speech Recognition: โ†’ Processes 60 minutes of continuous audio in a single pass โ†’ Never slices audio into chunks so global context is never lost โ†’ Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously โ†’ Supports customized hotwords for domain specific accuracy โ†’ Works in 50+ languages natively โ†’ Already adopted by Hugging Face Transformers library โ†’ 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: โ†’ Generates up to 90 minutes of speech in a single pass โ†’ Supports up to 4 distinct speakers in one conversation โ†’ Natural turn taking and speaker consistency throughout โ†’ Expressive speech that captures emotional nuances โ†’ Supports English, Chinese and multiple other languages VibeVoice Realtime - Streaming TTS: โ†’ Only 300 millisecond first audible latency โ†’ Streams text input in real time โ†’ 0.5B parameters so it actually deploys anywhere โ†’ Robust long form generation up to 10 minutes โ†’ 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: โ†’ VibeVoice ASR 7B - available now on Hugging Face โ†’ VibeVoice Realtime 0.5B - try it on Colab right now โ†’ 50+ supported languages โ†’ 11 distinct English voice styles โ†’ 9 multilingual speaker voices โ†’ Already integrated into Hugging Face Transformers โ†’ 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. ๐Ÿ”– Save this before your competitors find it first. ๐Ÿ‘‡

Kanika

220,656 Aufrufe โ€ข vor 3 Monaten

End to End Speech models are on fire - LLAMA-OMNI 8B - Apache licensed! ๐Ÿ”ฅ > Speech Encoder - Whisper Large v3 > LLM backbone - Llama 3.1 8B Instruct > Speech Decoder - HuBERT (UnitY) > Simultaneously generate Speech + Text > Less than 250 ms latency > Trained in less than 3 days on 4x GPUs > Used 200K instruct pairs > Model checkpoints on the Hub ๐Ÿค— > Space incoming! GG! I'm here for this trend! ๐Ÿ
0:36

End to End Speech models are on fire - LLAMA-OMNI 8B - Apache licensed! ๐Ÿ”ฅ > Speech Encoder - Whisper Large v3 > LLM backbone - Llama 3.1 8B Instruct > Speech Decoder - HuBERT (UnitY) > Simultaneously generate Speech + Text > Less than 250 ms latency > Trained in less than 3 days on 4x GPUs > Used 200K instruct pairs > Model checkpoints on the Hub ๐Ÿค— > Space incoming! GG! I'm here for this trend! ๐Ÿ

Vaibhav (VB) Srivastav

47,921 Aufrufe โ€ข vor 1 Jahr

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. ๐—ง๐—ต๐—ถ๐˜€ ๐—บ๐—ผ๐—ฑ๐—ฒ๐—น ๐—ด๐—ฒ๐—ป๐—ฒ๐—ฟ๐—ฎ๐˜๐—ฒ๐˜€ ๐—น๐—ผ๐—ป๐—ด, ๐—บ๐˜‚๐—น๐˜๐—ถ-๐˜€๐—ฝ๐—ฒ๐—ฎ๐—ธ๐—ฒ๐—ฟ ๐˜€๐—ฝ๐—ฒ๐—ฒ๐—ฐ๐—ต. It produces up to 90 minutes of audio. It supports up to four distinct speakers. Turn-taking stays consistent over long sessions. ๐—œ๐˜ ๐˜„๐—ผ๐—ฟ๐—ธ๐˜€ ๐—ฏ๐˜† ๐—ฟ๐—ฒ๐—ฑ๐˜‚๐—ฐ๐—ถ๐—ป๐—ด ๐˜๐—ถ๐—บ๐—ฒ ๐—ฟ๐—ฒ๐˜€๐—ผ๐—น๐˜‚๐˜๐—ถ๐—ผ๐—ป. 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. ๐—œ๐˜ ๐—ฎ๐—น๐—น๐—ผ๐˜„๐˜€ ๐—น๐—ผ๐˜„-๐—น๐—ฎ๐˜๐—ฒ๐—ป๐—ฐ๐˜† ๐˜€๐˜๐—ฟ๐—ฒ๐—ฎ๐—บ๐—ถ๐—ป๐—ด ๐—ฎ๐˜‚๐—ฑ๐—ถ๐—ผ. 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.
1:00

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. ๐—ง๐—ต๐—ถ๐˜€ ๐—บ๐—ผ๐—ฑ๐—ฒ๐—น ๐—ด๐—ฒ๐—ป๐—ฒ๐—ฟ๐—ฎ๐˜๐—ฒ๐˜€ ๐—น๐—ผ๐—ป๐—ด, ๐—บ๐˜‚๐—น๐˜๐—ถ-๐˜€๐—ฝ๐—ฒ๐—ฎ๐—ธ๐—ฒ๐—ฟ ๐˜€๐—ฝ๐—ฒ๐—ฒ๐—ฐ๐—ต. It produces up to 90 minutes of audio. It supports up to four distinct speakers. Turn-taking stays consistent over long sessions. ๐—œ๐˜ ๐˜„๐—ผ๐—ฟ๐—ธ๐˜€ ๐—ฏ๐˜† ๐—ฟ๐—ฒ๐—ฑ๐˜‚๐—ฐ๐—ถ๐—ป๐—ด ๐˜๐—ถ๐—บ๐—ฒ ๐—ฟ๐—ฒ๐˜€๐—ผ๐—น๐˜‚๐˜๐—ถ๐—ผ๐—ป. 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. ๐—œ๐˜ ๐—ฎ๐—น๐—น๐—ผ๐˜„๐˜€ ๐—น๐—ผ๐˜„-๐—น๐—ฎ๐˜๐—ฒ๐—ป๐—ฐ๐˜† ๐˜€๐˜๐—ฟ๐—ฒ๐—ฎ๐—บ๐—ถ๐—ป๐—ด ๐—ฎ๐˜‚๐—ฑ๐—ถ๐—ผ. 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

60,568 Aufrufe โ€ข vor 5 Monaten

Introducing Chat0 - Blazingly Fast, Free, Open Source AI Chat App - Multi Model Support (Gemini, GPT, DeepSeek) - Privacy-first (all data stored locally in your browser) - BYOK / Unlimited Messages - Chat Navigator (easily navigate a large chat) beta available now
0:22

Introducing Chat0 - Blazingly Fast, Free, Open Source AI Chat App - Multi Model Support (Gemini, GPT, DeepSeek) - Privacy-first (all data stored locally in your browser) - BYOK / Unlimited Messages - Chat Navigator (easily navigate a large chat) beta available now

harsh

352,517 Aufrufe โ€ข vor 1 Jahr

Web3 logins, simplified. Internet Identity 2.0 adds: - Passwordless login with passkeys - Google, Apple & Microsoft sign-in - Multi-account management Secure, fast, and user-friendly. Try it today:
1:01

Web3 logins, simplified. Internet Identity 2.0 adds: - Passwordless login with passkeys - Google, Apple & Microsoft sign-in - Multi-account management Secure, fast, and user-friendly. Try it today:

DFINITY Foundation

14,376 Aufrufe โ€ข vor 7 Monaten