Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

WOW! DeepMind just dropped Magenta Real-time - Apache 2.0 licensed 🔥 > 800M params transformer, trained on ~190K hours of instrumental stock music > adapts MusicLM for real-time generation via 2s audio chunks (conditioned on prior 10s context) > 48 KHz Stereo > MusicCoCa: New joint music-text embedding model,... show more

Vaibhav (VB) Srivastav

32,478 subscribers

90,219 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie Musik

Anya Rossi• Live Now

Private livecam show

4 Kommentare

Profilbild von Vaibhav (VB) Srivastav

Vaibhav (VB) Srivastavvor 1 Jahr

Try it out directly from the model on Hugging Face:

Profilbild von Maxence Pastor

Maxence Pastorvor 1 Jahr

Now, use that during a D&D session to create an evolutive soundtrack, and you’ve got a banger !

Profilbild von Ethan vs Machines

Ethan vs Machinesvor 1 Jahr

🔥 48KHz Stereo in real-time? DeepMind just transformed music gen! On-device fine-tuning + open weights = a creative playground for devs. The future sounds amazing! 🎵

Profilbild von Sven St.

Sven St.vor 1 Jahr

@huggingface License is not apache 2.0?

Ähnliche Videos

Wow! New Speech to Speech model - Fish Agent v0.1 3B by Fish Audio 🔥 > Trained on 700K hours of multilingual audio > Continue-pretrained version of Qwen-2.5-3B-Instruct for 200B audio & text tokens > Zero-shot voice cloning > Text + audio input/ Audio output > Ultra-fast inference w/ 200ms TTFA > Models on the Hub & Finetuning code on its way! 🚀 What an amazing time to be alive 🤗

Wow! New Speech to Speech model - Fish Agent v0.1 3B by Fish Audio 🔥 > Trained on 700K hours of multilingual audio > Continue-pretrained version of Qwen-2.5-3B-Instruct for 200B audio & text tokens > Zero-shot voice cloning > Text + audio input/ Audio output > Ultra-fast inference w/ 200ms TTFA > Models on the Hub & Finetuning code on its way! 🚀 What an amazing time to be alive 🤗

Vaibhav (VB) Srivastav

66,979 Aufrufe • vor 1 Jahr

Multimodal Ichigo Llama 3.1 - Real Time Voice AI 🔥 > WhisperSpeech X Llama 3.1 8B > Trained on 50K hours of speech (7 languages) > Continually trained on 45hrs 10x A1000s > MLS -> WhisperVQ tokens -> Llama 3.1 > Instruction tuned on 1.89M samples > 70% speech, 20% transcription, 10% text > Apache 2.0 licensed ⚡ Architecture: > WhisperSpeech/ VQ for Semantic Tokens > Llama 3.1 8B Instruct for Text backbone > Early fusion (Chameleon) I'm super bullish on Homebrew to Menlo and early fusion, audio and text, multimodal models! (P.S. Play with the demo on Hugging Face)

Multimodal Ichigo Llama 3.1 - Real Time Voice AI 🔥 > WhisperSpeech X Llama 3.1 8B > Trained on 50K hours of speech (7 languages) > Continually trained on 45hrs 10x A1000s > MLS -> WhisperVQ tokens -> Llama 3.1 > Instruction tuned on 1.89M samples > 70% speech, 20% transcription, 10% text > Apache 2.0 licensed ⚡ Architecture: > WhisperSpeech/ VQ for Semantic Tokens > Llama 3.1 8B Instruct for Text backbone > Early fusion (Chameleon) I'm super bullish on Homebrew to Menlo and early fusion, audio and text, multimodal models! (P.S. Play with the demo on Hugging Face)

Vaibhav (VB) Srivastav

82,126 Aufrufe • vor 1 Jahr

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! 🔥 > 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 🤗

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! 🔥 > 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 🤗

Vaibhav (VB) Srivastav

298,858 Aufrufe • vor 1 Jahr

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗

Vaibhav (VB) Srivastav

79,585 Aufrufe • vor 1 Jahr

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Stability AI

976,344 Aufrufe • vor 2 Jahren

Type a sentence, get any sound - from talking cats to singing saxophones. Brilliant release by NVIDIA ✨ NVIDIA just unveiled Fugatto, a groundbreaking 2.5B parameter audio AI model that can generate and transform any combination of music, voices, and sounds using text prompts and audio inputs Fugatto could ultimately allow developers and creators to bring sounds to life simply by inputting text prompts, → The model demonstrates unique capabilities like creating hybrid sounds (trumpet barking), changing accents/emotions in voices, and allowing fine-grained control over sound transitions - trained on millions of audio samples using 32 NVIDIA H100 GPUs 👨‍🔧 Architecture Built as a foundational generative transformer model leveraging NVIDIA's previous work in speech modeling and audio understanding. The training process involved creating a specialized blended dataset containing millions of audio samples → ComposableART's Innovation in Audio Control Introduces a novel technique allowing combination of instructions that were only seen separately during training. Users can blend different audio attributes and control their intensity → Temporal Interpolation Capabilities Enables generation of evolving soundscapes with precise control over transitions. Can create dynamic audio sequences like rainstorms fading into birdsong at dawn → Processes both text and audio inputs flexibly, enabling tasks like removing instruments from songs or modifying specific audio characteristics while preserving others → Shows capabilities beyond its training data, creating entirely new sound combinations through interaction between different trained abilities 🔍 Real-world Applications → Allows rapid prototyping of musical ideas, style experimentation, and real-time sound creation during studio sessions → Enables dynamic audio asset generation matching gameplay situations, reducing pre-recorded audio requirements → Can modify voice characteristics for language learning applications, allowing content delivery in familiar voices NVIDIA AI Developer

Type a sentence, get any sound - from talking cats to singing saxophones. Brilliant release by NVIDIA ✨ NVIDIA just unveiled Fugatto, a groundbreaking 2.5B parameter audio AI model that can generate and transform any combination of music, voices, and sounds using text prompts and audio inputs Fugatto could ultimately allow developers and creators to bring sounds to life simply by inputting text prompts, → The model demonstrates unique capabilities like creating hybrid sounds (trumpet barking), changing accents/emotions in voices, and allowing fine-grained control over sound transitions - trained on millions of audio samples using 32 NVIDIA H100 GPUs 👨‍🔧 Architecture Built as a foundational generative transformer model leveraging NVIDIA's previous work in speech modeling and audio understanding. The training process involved creating a specialized blended dataset containing millions of audio samples → ComposableART's Innovation in Audio Control Introduces a novel technique allowing combination of instructions that were only seen separately during training. Users can blend different audio attributes and control their intensity → Temporal Interpolation Capabilities Enables generation of evolving soundscapes with precise control over transitions. Can create dynamic audio sequences like rainstorms fading into birdsong at dawn → Processes both text and audio inputs flexibly, enabling tasks like removing instruments from songs or modifying specific audio characteristics while preserving others → Shows capabilities beyond its training data, creating entirely new sound combinations through interaction between different trained abilities 🔍 Real-world Applications → Allows rapid prototyping of musical ideas, style experimentation, and real-time sound creation during studio sessions → Enables dynamic audio asset generation matching gameplay situations, reducing pre-recorded audio requirements → Can modify voice characteristics for language learning applications, allowing content delivery in familiar voices NVIDIA AI Developer

Rohan Paul

96,354 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 6 Monaten

Today we're announcing the open-source release of HunyuanVideo-Foley, our new end-to-end Text-Video-to-Audio (TV2A) framework for generating high-fidelity audio.🚀 This tool empowers creators in video production, filmmaking, and game development to generate professional-grade audio that precisely aligns with visual dynamics and semantic context, addressing key challenges in V2A generation.🔊 Key Innovations: 🔹Exceptional Generalization: Trained on a massive 100k-hour multimodal dataset, the model generates contextually-aware soundscapes for a wide range of scenes, from natural landscapes to animated shorts. 🔹Balanced Multimodal Response: Our innovative multimodal diffusion transformer (MMDiT) architecture ensures the model balances video and text cues, generating rich, layered sound effects that capture every detail—from the main subject to subtle background elements. 🔹High-Fidelity Audio: Using a Representation Alignment (REPA) loss function and a powerful Audio VAE, we've improved generation stability and producing professional-grade audio, free of noise and inconsistencies. HunyuanVideo-Foley achieves SOTA on multiple benchmarks, surpassing all open-source models in audio quality, visual-semantic alignment, and temporal alignment. 👉Try it now: 🌐Project Page: 🔗Code: 📄Technical Report: 🤗Hugging Face:

Today we're announcing the open-source release of HunyuanVideo-Foley, our new end-to-end Text-Video-to-Audio (TV2A) framework for generating high-fidelity audio.🚀 This tool empowers creators in video production, filmmaking, and game development to generate professional-grade audio that precisely aligns with visual dynamics and semantic context, addressing key challenges in V2A generation.🔊 Key Innovations: 🔹Exceptional Generalization: Trained on a massive 100k-hour multimodal dataset, the model generates contextually-aware soundscapes for a wide range of scenes, from natural landscapes to animated shorts. 🔹Balanced Multimodal Response: Our innovative multimodal diffusion transformer (MMDiT) architecture ensures the model balances video and text cues, generating rich, layered sound effects that capture every detail—from the main subject to subtle background elements. 🔹High-Fidelity Audio: Using a Representation Alignment (REPA) loss function and a powerful Audio VAE, we've improved generation stability and producing professional-grade audio, free of noise and inconsistencies. HunyuanVideo-Foley achieves SOTA on multiple benchmarks, surpassing all open-source models in audio quality, visual-semantic alignment, and temporal alignment. 👉Try it now: 🌐Project Page: 🔗Code: 📄Technical Report: 🤗Hugging Face:

Tencent Hy

122,706 Aufrufe • vor 11 Monaten

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,257 Aufrufe • vor 10 Monaten

🥳Excited to share our latest work: "Diff-A-Riff"! 🥁 A Latent Diffusion Model that generates instrumental accompaniments for any musical input, specifically tailored for music producers! It's faster, lighter, and produces superior audio quality. Control via text/audio references. 48kHz sample rate, (pseudo) stereo, ~3Gb memory, takes 6 seconds to generate 90 seconds of music. Trained on a single GPU. 📜 🎶 🎸 "Diff-A-Riff" adapts to any musical input, following the artist's unique style. 🎛️ Optional controls via text prompts, audio references, interpolation slider, pseudo-stereo width and loop intensity. 🎚️ It produces state-of-the-art audio quality indistinguishable from real data by human raters and operates at unprecedented speed. 🧠 "Diff-A-Riff" is smaller and more efficient than previous models thanks to its Consistency Autoencoder, making it accessible and practical for various applications. Big shoutout to my outer space colleagues: Javier Nistal, the Machine in "machine learning" 🚄, Marco Pasini, the neural net whisperer 🤫, Cyran Aouameur, the troubleshootah 🛠️, Maarten Grachten, aka MaartenGPT 🤖. #Teamwork #AI #MusicTech #Innovation Javier Nistal Marco Pasini Cyran Aouameur SonyCSL(Paris)_Music Team

🥳Excited to share our latest work: "Diff-A-Riff"! 🥁 A Latent Diffusion Model that generates instrumental accompaniments for any musical input, specifically tailored for music producers! It's faster, lighter, and produces superior audio quality. Control via text/audio references. 48kHz sample rate, (pseudo) stereo, ~3Gb memory, takes 6 seconds to generate 90 seconds of music. Trained on a single GPU. 📜 🎶 🎸 "Diff-A-Riff" adapts to any musical input, following the artist's unique style. 🎛️ Optional controls via text prompts, audio references, interpolation slider, pseudo-stereo width and loop intensity. 🎚️ It produces state-of-the-art audio quality indistinguishable from real data by human raters and operates at unprecedented speed. 🧠 "Diff-A-Riff" is smaller and more efficient than previous models thanks to its Consistency Autoencoder, making it accessible and practical for various applications. Big shoutout to my outer space colleagues: Javier Nistal, the Machine in "machine learning" 🚄, Marco Pasini, the neural net whisperer 🤫, Cyran Aouameur, the troubleshootah 🛠️, Maarten Grachten, aka MaartenGPT 🤖. #Teamwork #AI #MusicTech #Innovation Javier Nistal Marco Pasini Cyran Aouameur SonyCSL(Paris)_Music Team

Stefan Lattner

17,703 Aufrufe • vor 2 Jahren

VoxCPM 2 just dropped by OpenBMB Only 2B-param open-source TTS (Text-to-Speech) model built for production-grade multilingual voice work. Apache-2.0 license, Can run on only 8GB VRAM. • Eliminates the "robotic" feel of traditional TTS, delivering prosody and emotional depth suitable for high-stakes professional environments like filmmaking, gaming, animation, and audiobooks. • 30-language multilingual: no language tag needed, just type in a supported language and generate directly. • Voice design: create a brand-new voice from a text description alone, like age, tone, pace, or emotion. No reference audio required. Describe the desired voice characteristics (gender, age, tone, emotion, pace …) in Control Instruction, and VoxCPM2 will craft a unique voice from your description alone. • Controllable cloning: clone from a short clip, then steer delivery style without losing the speaker’s core voice. • Ultimate cloning: use reference audio + transcript for continuation-style cloning that keeps the tiny vocal details. • 48kHz output: takes 16kHz reference audio and produces studio-quality speech without an external upsampler. • Real-time ready: around 0.3 RTF on RTX 4090, even lower with Nano-VLLM. • Commercial use: Apache-2.0 licensed. Developer-Friendly Infrastructure: - Native Torch Inference: Direct support for PyTorch-based workflows. - Training Flexibility: Supports both full-parameter and LoRA fine-tuning for specific domain adaptation. - Production Readiness: Compatible with voxcpm-nanovllm for large-scale, high-concurrency deployment.

Rohan Paul

13,541 Aufrufe • vor 3 Monaten

🚨 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 Aufrufe • vor 3 Monaten

InstantDrag Improving Interactivity in Drag-based Image Editing discuss: Drag-based image editing has recently gained popularity for its interactivity and precision. However, despite the ability of text-to-image models to generate samples within a second, drag editing still lags behind due to the challenge of accurately reflecting user interaction while maintaining image content. Some existing approaches rely on computationally intensive per-image optimization or intricate guidance-based methods, requiring additional inputs such as masks for movable regions and text prompts, thereby compromising the interactivity of the editing process. We introduce InstantDrag, an optimization-free pipeline that enhances interactivity and speed, requiring only an image and a drag instruction as input. InstantDrag consists of two carefully designed networks: a drag-conditioned optical flow generator (FlowGen) and an optical flow-conditioned diffusion model (FlowDiffusion). InstantDrag learns motion dynamics for drag-based image editing in real-world video datasets by decomposing the task into motion generation and motion-conditioned image generation. We demonstrate InstantDrag's capability to perform fast, photo-realistic edits without masks or text prompts through experiments on facial video datasets and general scenes. These results highlight the efficiency of our approach in handling drag-based image editing, making it a promising solution for interactive, real-time applications.

InstantDrag Improving Interactivity in Drag-based Image Editing discuss: Drag-based image editing has recently gained popularity for its interactivity and precision. However, despite the ability of text-to-image models to generate samples within a second, drag editing still lags behind due to the challenge of accurately reflecting user interaction while maintaining image content. Some existing approaches rely on computationally intensive per-image optimization or intricate guidance-based methods, requiring additional inputs such as masks for movable regions and text prompts, thereby compromising the interactivity of the editing process. We introduce InstantDrag, an optimization-free pipeline that enhances interactivity and speed, requiring only an image and a drag instruction as input. InstantDrag consists of two carefully designed networks: a drag-conditioned optical flow generator (FlowGen) and an optical flow-conditioned diffusion model (FlowDiffusion). InstantDrag learns motion dynamics for drag-based image editing in real-world video datasets by decomposing the task into motion generation and motion-conditioned image generation. We demonstrate InstantDrag's capability to perform fast, photo-realistic edits without masks or text prompts through experiments on facial video datasets and general scenes. These results highlight the efficiency of our approach in handling drag-based image editing, making it a promising solution for interactive, real-time applications.

AK

71,232 Aufrufe • vor 1 Jahr

A team tested Pi0, Pi0 Fast, Gr00t, and ACT on real robot arms in manufacturing tasks. (🔖 Bookmark this for later!) The task was precise: place thin rectangular frames from a messy stack into a holder. The team fine-tuned each model on 100 real trajectories and compared training time, inference speed, motion quality, and success rates. ⬇️ Here’s a breakdown of what they found Pi0 (Original) ✅ Strongest overall performance in precise pick-and-place ✅ High success rate even in edge cases ✅ Longest training time (~11 hours, ~$30 per run) ✅ Inference time of 80 ms causes short pauses between actions Despite delays, it handles complex scenarios well… solid for high-precision tasks, but slow to train. Gr00t ✅ Trains fast (~2 hours, ~$5 per run) ✅ Performs almost as well as Pi0 on large-object tasks ✅ Struggles with fine precision; random movement in some trials ✅ More training didn’t fix jitter or random offsets Best suited for tasks where exact precision isn’t critical. Not ready for manufacturing-grade accuracy without more tuning. Pi0 Fast ✅ Promised faster training, but results were underwhelming ✅ Training at 6 hours still showed low success rates ✅ Inference was slower than expected ✅ Not reliable for generalizing even slightly new tasks Currently too unstable for real-world deployment. Doesn’t live up to the “Fast” name yet. ACT (Baseline) ✅ 200MB model—lightweight, but limited ✅ Struggles with stacked objects or ambiguous scenes ✅ Success rates around 70% in best-case setups ✅ Can’t match newer models on precision or generalization Still a solid baseline, but clearly a generation behind in robustness. 🚨 Extra Notes All newer models share a common issue: •Inference takes longer than a frame (80 ms vs 33 ms), so robots “pause” between chunks. •This results in jittery movements, but not a dealbreaker unless tasks are time-sensitive. Language-conditioned tasks also fell short: after training on two labeled tasks, the model couldn’t generalize to a third unseen combination using only text prompts. ✅ The good news? These models adapt well to new robot arms with quick fine-tuning. ❌ The bad news? There’s still no plug-and-play solution for improving performance after deployment. Reinforcement learning or DAgger-style data collection during real-world operation may be the next big step, something many teams in robotics are actively working on.

A team tested Pi0, Pi0 Fast, Gr00t, and ACT on real robot arms in manufacturing tasks. (🔖 Bookmark this for later!) The task was precise: place thin rectangular frames from a messy stack into a holder. The team fine-tuned each model on 100 real trajectories and compared training time, inference speed, motion quality, and success rates. ⬇️ Here’s a breakdown of what they found Pi0 (Original) ✅ Strongest overall performance in precise pick-and-place ✅ High success rate even in edge cases ✅ Longest training time (~11 hours, ~$30 per run) ✅ Inference time of 80 ms causes short pauses between actions Despite delays, it handles complex scenarios well… solid for high-precision tasks, but slow to train. Gr00t ✅ Trains fast (~2 hours, ~$5 per run) ✅ Performs almost as well as Pi0 on large-object tasks ✅ Struggles with fine precision; random movement in some trials ✅ More training didn’t fix jitter or random offsets Best suited for tasks where exact precision isn’t critical. Not ready for manufacturing-grade accuracy without more tuning. Pi0 Fast ✅ Promised faster training, but results were underwhelming ✅ Training at 6 hours still showed low success rates ✅ Inference was slower than expected ✅ Not reliable for generalizing even slightly new tasks Currently too unstable for real-world deployment. Doesn’t live up to the “Fast” name yet. ACT (Baseline) ✅ 200MB model—lightweight, but limited ✅ Struggles with stacked objects or ambiguous scenes ✅ Success rates around 70% in best-case setups ✅ Can’t match newer models on precision or generalization Still a solid baseline, but clearly a generation behind in robustness. 🚨 Extra Notes All newer models share a common issue: •Inference takes longer than a frame (80 ms vs 33 ms), so robots “pause” between chunks. •This results in jittery movements, but not a dealbreaker unless tasks are time-sensitive. Language-conditioned tasks also fell short: after training on two labeled tasks, the model couldn’t generalize to a third unseen combination using only text prompts. ✅ The good news? These models adapt well to new robot arms with quick fine-tuning. ❌ The bad news? There’s still no plug-and-play solution for improving performance after deployment. Reinforcement learning or DAgger-style data collection during real-world operation may be the next big step, something many teams in robotics are actively working on.

Ilir Aliu

21,844 Aufrufe • vor 1 Jahr

Introducing Lightning V3 - it beats every model we tested against. ElevenLabs, Cartesia, OpenAI. Lightning sets a new SOTA with V3 in conversational text-to-speech. → Highest MOS score for conversational TTS at 3.9 → ~76% win rate vs gpt-4o-mini-tts on naturalness → 15 languages with mid-sentence code-switching → Built from scratch for voice agents, not read-aloud Every TTS model sounds clean in a demo. You type a sentence and you get beautiful audio. Voice agents don't work that way. They stream. They're generating audio in real-time chunks with half the context missing. That's where everything breaks. A great reading voice and a great conversational voice are fundamentally different things. A conversational voice has to sound like it's thinking - with the pauses, the rhythm shifts, the reactions. It has to handle the way real people actually talk, including switching languages mid-sentence. That's what V3 does. V3.1 also ships voice cloning. 5 to 15 seconds of audio, no fine-tuning, production-grade clone across 15 languages. Blog link in the comments.

Introducing Lightning V3 - it beats every model we tested against. ElevenLabs, Cartesia, OpenAI. Lightning sets a new SOTA with V3 in conversational text-to-speech. → Highest MOS score for conversational TTS at 3.9 → ~76% win rate vs gpt-4o-mini-tts on naturalness → 15 languages with mid-sentence code-switching → Built from scratch for voice agents, not read-aloud Every TTS model sounds clean in a demo. You type a sentence and you get beautiful audio. Voice agents don't work that way. They stream. They're generating audio in real-time chunks with half the context missing. That's where everything breaks. A great reading voice and a great conversational voice are fundamentally different things. A conversational voice has to sound like it's thinking - with the pauses, the rhythm shifts, the reactions. It has to handle the way real people actually talk, including switching languages mid-sentence. That's what V3 does. V3.1 also ships voice cloning. 5 to 15 seconds of audio, no fine-tuning, production-grade clone across 15 languages. Blog link in the comments.

Sudarshan Kamath

71,298 Aufrufe • vor 4 Monaten

Sarvam Beats GPT-4o: India’s New AI Model Claims Top Spot in Indic Speech Sarvam AI, an Indian startup, recently launched Sarvam Audio, a speech recognition model that claims superior performance over GPT-4o Transcribe on Indic language benchmarks. This development highlights India's push for AI sovereignty in handling local linguistic nuances. Sarvam Audio supports 22 Indian languages from the Eighth Schedule, plus Indian English, with strong handling of code-mixing like Hindi-English blends. It features built-in speaker diarization for up to eight speakers and processes long-form audio such as podcasts or meetings. Trained on the IndicVoices dataset 12,000 hours from over 16,000 speakers across 208 districts it captures real-world noise and spontaneous speech. The model reportedly outperforms GPT-4o Transcribe and Gemini 3 Flash in transcription accuracy (lower Word Error Rate) on IndicVoices benchmarks for unnormalized, normalized, and code-mixed speech. Sarvam attributes this to specialization on Indian accents and patterns, unlike global models trained on Western data. Detailed public benchmarks are pending independent verification. Key Applications 🔴 Call centers and logistics for multilingual transcription. 🔴 Banking, fintech, and e-commerce for customer interactions. 🔴 Podcasts, meetings, and lectures via API for real-time or batch processing. 🔴 This B2B-focused tool aligns with India's IndiaAI Mission, backed by government GPU access for sovereign LLMs. Credit : AIM Networks.

Sarvam Beats GPT-4o: India’s New AI Model Claims Top Spot in Indic Speech Sarvam AI, an Indian startup, recently launched Sarvam Audio, a speech recognition model that claims superior performance over GPT-4o Transcribe on Indic language benchmarks. This development highlights India's push for AI sovereignty in handling local linguistic nuances. Sarvam Audio supports 22 Indian languages from the Eighth Schedule, plus Indian English, with strong handling of code-mixing like Hindi-English blends. It features built-in speaker diarization for up to eight speakers and processes long-form audio such as podcasts or meetings. Trained on the IndicVoices dataset 12,000 hours from over 16,000 speakers across 208 districts it captures real-world noise and spontaneous speech. The model reportedly outperforms GPT-4o Transcribe and Gemini 3 Flash in transcription accuracy (lower Word Error Rate) on IndicVoices benchmarks for unnormalized, normalized, and code-mixed speech. Sarvam attributes this to specialization on Indian accents and patterns, unlike global models trained on Western data. Detailed public benchmarks are pending independent verification. Key Applications 🔴 Call centers and logistics for multilingual transcription. 🔴 Banking, fintech, and e-commerce for customer interactions. 🔴 Podcasts, meetings, and lectures via API for real-time or batch processing. 🔴 This B2B-focused tool aligns with India's IndiaAI Mission, backed by government GPU access for sovereign LLMs. Credit : AIM Networks.

Augadh

43,429 Aufrufe • vor 5 Monaten

Mistral just released Voxtral TTS, an open-weight voice model that tries to match ElevenLabs while keeping it free. A 3-billionn param model that fits on a laptop and runs 6X faster than real-time speech. It is split into 3 parts that handle different jobs. - The 3.4B part is the main language brain that understands the text and plans what should be spoken. - The 390M part turns that plan into speech features like rhythm, pronunciation, and tone. - The 300M part converts those speech features into the final compressed audio signal you can play. That split helps because each part only does the job it is best at, which can make the whole system faster and lighter than one giant model doing everything alone. Mistral claims about 90ms to first audio, about 6x faster than real-time speech output, about 3GB RAM after quantization, 9 languages, and voice copying from 5s of audio, even across languages. Its internal tests report 62.8% preference over ElevenLabs Flash on default voices and 69.9% on custom voices, but the bigger point is that companies can keep speech data on their own machines. IMO, enterprise buyers usually care most about control, cost, and latency, So this model should give it great push for voice-based AI apps/products.

Mistral just released Voxtral TTS, an open-weight voice model that tries to match ElevenLabs while keeping it free. A 3-billionn param model that fits on a laptop and runs 6X faster than real-time speech. It is split into 3 parts that handle different jobs. - The 3.4B part is the main language brain that understands the text and plans what should be spoken. - The 390M part turns that plan into speech features like rhythm, pronunciation, and tone. - The 300M part converts those speech features into the final compressed audio signal you can play. That split helps because each part only does the job it is best at, which can make the whole system faster and lighter than one giant model doing everything alone. Mistral claims about 90ms to first audio, about 6x faster than real-time speech output, about 3GB RAM after quantization, 9 languages, and voice copying from 5s of audio, even across languages. Its internal tests report 62.8% preference over ElevenLabs Flash on default voices and 69.9% on custom voices, but the bigger point is that companies can keep speech data on their own machines. IMO, enterprise buyers usually care most about control, cost, and latency, So this model should give it great push for voice-based AI apps/products.

Rohan Paul

15,672 Aufrufe • vor 4 Monaten

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

AK

16,062 Aufrufe • vor 1 Jahr

The first open-source unified world model for scalable robot manipulation: 5B-parameter open-source unified video-action world model that combines policy and world modeling to generate robot actions, predict future visuals, and evaluate task progress from observations, language, and state. The model is trained on 27.3K hours of heterogeneous data (17.8K real-robot teleop, 6.5K UMI demos, 3K egocentric human videos), enabling it to perform complex manipulation tasks like faucet connecting, bag packing, and toolbox storing as shown in demo videos. The approach supports test-time action refinement and points toward deployment-driven continuous improvement via fleet data. Thanks for sharing, Jianlan Luo (Jianlan Luo)! 📌 Resource links for τ0-WM: • Project page: • GitHub (code): • Hugging Face (model weights): • Paper (PDF): ——- Weekly robotics and AI insights. Subscribe free:

The first open-source unified world model for scalable robot manipulation: 5B-parameter open-source unified video-action world model that combines policy and world modeling to generate robot actions, predict future visuals, and evaluate task progress from observations, language, and state. The model is trained on 27.3K hours of heterogeneous data (17.8K real-robot teleop, 6.5K UMI demos, 3K egocentric human videos), enabling it to perform complex manipulation tasks like faucet connecting, bag packing, and toolbox storing as shown in demo videos. The approach supports test-time action refinement and points toward deployment-driven continuous improvement via fleet data. Thanks for sharing, Jianlan Luo (Jianlan Luo)! 📌 Resource links for τ0-WM: • Project page: • GitHub (code): • Hugging Face (model weights): • Paper (PDF): ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

28,239 Aufrufe • vor 1 Monat

In our research lab, we are building “real-time dreaming” - the ability to generate fully playable video worlds prompted from any text or image. Our real-time, action conditioned world model (currently running internally at 16fps at 832x480p) is trained on a combination of data, including proprietary Roblox 3D avatar/world interaction data. World models are different from multiplayer engines in that they store state and memory in video latents. Roblox is multiplayer, and we are actively researching optimal ways to simultaneously store state for thousands of players, and keep them in sync with their environment. Our world model leverages database technology which stores all user interactions on Roblox in a vector format that can be used to re-render video and interaction from any camera angle. We see several immediate uses for our Roblox world model. We will use it side-by-side text, image and video prompts as a way to launch auto-generation of immersive worlds. In Roblox Studio, a creator could walk around and use prompts to “paint” a world and then convert it into a 3D representation or direct to Roblox native as a way for many people to play simultaneously. All of this comes alive as we explore the notion of a “Dream Theater” - where one user is dreaming, while others watch and prompt them. 2/4

Roblox

4,394,413 Aufrufe • vor 5 Monaten