正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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

358,331 subscribers

80,676 次观看 • 6 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

1-Click Vibevoice-Realtime for ALL machines Finally a Realtime TTS that is ACTUALLY realtime, thanks to its tiny size! (0.5B params) This video is from my Windows machine, recorded in realtime. All you need is around 2.5GB VRAM, it even works on Macs!

1-Click Vibevoice-Realtime for ALL machines Finally a Realtime TTS that is ACTUALLY realtime, thanks to its tiny size! (0.5B params) This video is from my Windows machine, recorded in realtime. All you need is around 2.5GB VRAM, it even works on Macs!

cocktail peanut

37,149 次观看 • 6 个月前

Inworlds new Realtime TTS-2 model just dropped

Inworlds new Realtime TTS-2 model just dropped

Luis Catacora

24,720 次观看 • 1 个月前

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!

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!

mrfakename

168,359 次观看 • 9 个月前

OpenAI just dropped GPT-Realtime-2, Realtime-Translate and Realtime-Whisper. Reason. Translate. Transcribe. In real time.

OpenAI just dropped GPT-Realtime-2, Realtime-Translate and Realtime-Whisper. Reason. Translate. Transcribe. In real time.

Min Choi

60,081 次观看 • 1 个月前

Physics in #UE5 is insanely fast and accurate. Unreal indeed! #UnrealEngine #realtime #animation

Physics in #UE5 is insanely fast and accurate. Unreal indeed! #UnrealEngine #realtime #animation

Arsenii Turgulainen

43,553 次观看 • 1 年前

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 🚀

45,100 次观看 • 2 个月前

the new OpenAI realtime voice model just released + gpt 5.5 fast mode brings us a new possibility - realtime speech to live presentation! i just talk, and the whiteboard would whiteboard itself prototype is open sourced. details in thread below -

the new OpenAI realtime voice model just released + gpt 5.5 fast mode brings us a new possibility - realtime speech to live presentation! i just talk, and the whiteboard would whiteboard itself prototype is open sourced. details in thread below -

Kun Chen

113,700 次观看 • 1 个月前

🚨 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

220,075 次观看 • 2 个月前

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

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

Min Choi

94,614 次观看 • 9 个月前

Here’s OpenAI’s latest realtime voice model, GPT-Realtime-2, wired up to OpenClaw. It’s amazing. Realtime continuous chat and fast OpenClaw agent action on real tasks. Truly excellent.

Here’s OpenAI’s latest realtime voice model, GPT-Realtime-2, wired up to OpenClaw. It’s amazing. Realtime continuous chat and fast OpenClaw agent action on real tasks. Truly excellent.

Ben Badejo

141,052 次观看 • 1 个月前

Microsoft just dropped MineWorld on Hugging Face a Real-Time and Open-Source Interactive World Model on Minecraft

Microsoft just dropped MineWorld on Hugging Face a Real-Time and Open-Source Interactive World Model on Minecraft

AK

95,035 次观看 • 1 年前

It's over --- This entire 7 minute podcast was 100% generated on my local PC, using an open source model called Vibevoice, from Microsoft.

It's over --- This entire 7 minute podcast was 100% generated on my local PC, using an open source model called Vibevoice, from Microsoft.

cocktail peanut

236,154 次观看 • 6 个月前

Introducing an open-source template for broadcasting realtime transcripts. • Generate live transcripts with Scribe • Broadcast to many using Supabase • Translate with Chrome’s built-in AI Demo and open source template below.

Introducing an open-source template for broadcasting realtime transcripts. • Generate live transcripts with Scribe • Broadcast to many using Supabase • Translate with Chrome’s built-in AI Demo and open source template below.

ElevenLabs Developers

28,069 次观看 • 7 个月前

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

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

118,352 次观看 • 7 个月前

Introducing Realtime TTS-2, a new generation of voice model built for realtime conversation. It is the first voice model that hears the conversation, takes natural-language voice direction, holds one voice identity across over 100 languages, and speaks like a person who is paying attention. The result is voice AI that feels as good as it sounds. Try it out: Learn More:

Introducing Realtime TTS-2, a new generation of voice model built for realtime conversation. It is the first voice model that hears the conversation, takes natural-language voice direction, holds one voice identity across over 100 languages, and speaks like a person who is paying attention. The result is voice AI that feels as good as it sounds. Try it out: Learn More:

Inworld AI

323,074 次观看 • 1 个月前

Realtime AI Conversations are here! Introducing PlayHT 2.0 Turbo ⚡️ Our new blazing fast Conversational AI Text-to-Speech model with <300ms latency! ✅ Input text streaming from LLMs ✅ Output audio streaming ✅ Clone any voice & accent Try here -

Realtime AI Conversations are here! Introducing PlayHT 2.0 Turbo ⚡️ Our new blazing fast Conversational AI Text-to-Speech model with <300ms latency! ✅ Input text streaming from LLMs ✅ Output audio streaming ✅ Clone any voice & accent Try here -

PlayAI

392,536 次观看 • 2 年前

Voice workflows just got stronger with gpt-realtime-1.5 in the Realtime API. The model offers more reliable instruction following, tool calling, and multilingual accuracy. Demo with Charlie Guo

Voice workflows just got stronger with gpt-realtime-1.5 in the Realtime API. The model offers more reliable instruction following, tool calling, and multilingual accuracy. Demo with Charlie Guo

OpenAI Developers

417,365 次观看 • 3 个月前

Not a Qwen-TTS, but the small and fast LuxTTS delivers SOTA voice cloning from just 1GB VRAM; - >150x realtime speed, - outputs crisp 48kHz audio, and matches models 10x its size.

Not a Qwen-TTS, but the small and fast LuxTTS delivers SOTA voice cloning from just 1GB VRAM; - >150x realtime speed, - outputs crisp 48kHz audio, and matches models 10x its size.

Wildminder

25,238 次观看 • 4 个月前

Ethereum has a 12-second blocktime. By slicing the block into sub-blocks, Realtime Ethereum moves in milliseconds ⚡️ No more waiting. No more uncertainty. Just 100x faster. The era of Realtime Ethereum starts now. Go Realtime at :

Ethereum has a 12-second blocktime. By slicing the block into sub-blocks, Realtime Ethereum moves in milliseconds ⚡️ No more waiting. No more uncertainty. Just 100x faster. The era of Realtime Ethereum starts now. Go Realtime at :

ETHGAS

181,863 次观看 • 4 个月前

🎙️Do you know you now have all the building blocks for full speech-to-speech? - Voxtral Realtime: High-quality, real-time speech-to-text. - Mistral Small 4: Fast, efficient, general-purpose agentic model. - Voxtral TTS: Realistic customizable text-to-speech with streaming output.

🎙️Do you know you now have all the building blocks for full speech-to-speech? - Voxtral Realtime: High-quality, real-time speech-to-text. - Mistral Small 4: Fast, efficient, general-purpose agentic model. - Voxtral TTS: Realistic customizable text-to-speech with streaming output.

Mistral AI for Developers

27,647 次观看 • 2 个月前