🚀 Audio General Intelligence (AGI) is no longer a dream — it’s here. Introducing Audio Flamingo 3 — open-source, multimodal, and groundbreaking. It listens. It understands. It reasons across sound and language. 💥 Code, weights, datasets, paper — all open. 📄Paper:

NVIDIA Just Released Audio Flamingo 3: An Open-Source Model Advancing Audio General Intelligence: ift.tt/hzl1OsK

NVIDIA Releases Audio Flamingo 3: An Open-Source Model Advancing Audio General Intelligence NVIDIA’s Audio Flamingo 3 (AF3) is a fully open-source large audio-language model that significantly advances the field of Audio General Intelligence. Unlike earlier systems focused on

Open-source audio scene is quite on 🔥 lately! - kyutai STT, TTS modules and Unmute fully open-sourced - NVIDIA drops 3 models: Parakeet (beats Whisper), Audio Flamingo 3 and Canary-Qwen-2.5B (new SOTA on Hugging Face leaderboard) - Mistral AI released 3B and 24B Voxtral

zsxkib/audio-flamingo-3 from NVIDIA a chain-of-thought audio language model (that's small+fast) on Replicate you can upload an mp3 and ask: > what instruments do you hear?🙉 > transcribe any speech you hear🗣️ > please describe the audio in detail🎨 > answer the question💬

nvidia's audio-flamingo-3 in action (sound on 🔇→🎶) > upload an audio clip saying "what are the names of some famous actors who started their careers on broadway"🎭 > prompt "answer" TIL Tom Hanks was on broadway

🎶 Meet Audio-Flamingo 3 – a fully open LALM trained on sound, speech, and music datasets. 🎶 Handles 10-min audio, long-form text, and voice conversations. Perfect for audio QA, dialog, and reasoning. On Hugging Face ➡️ huggingface.co/nvidia/audio-f… From #NVIDIAResearch.

🚨Paper Alert 🚨 ➡️Paper Title: Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models 🌟Few pointers from the paper 🎯Authors of this paper presented “Audio Flamingo 3 (AF3)”, a fully open state-of-the-art (SOTA) large audio-language model

【聴くAIの革命！NVIDIA Audio Flamingo 3 (AF3)で音声理解が進化！】 NVIDIAが画期的な技術「Audio Flamingo 3 (AF3)」を発表！✨ 音声、音、音楽を統合的に理解するオープンソースの最先端AIモデルです👂💡

That's exactly why I'm excited about the unique position of the post-training team at NVIDIA. We’re not just releasing open-weight models — we fully open source the data, code, and technical details. Small team, moving fast. The competition is fierce, and Chinese open model

We've been making a lot of progress on LLM pretraining in NVFP4: developer.nvidia.com/blog/nvfp4-tra…

We just released Nemotron-CC-Math 🚀 Equations on web aren’t just LaTeX-they’re in MathML,<pre> tags,inline,even images.Code shows up just as many ways. Most parsers drop it. Nemotron-CC-Math(133B tokens) reprocesses CommonCrawl math pages to capture math equations +code reliably

As part of Nemotron, we're releasing a new Math dataset, made by rendering webpages using Lynx and then using an LLM to rewrite the result into LaTeX. Our models got much better at math when we started using this dataset. We hope it's helpful to the community. 💚

Audio Flamingo 3 made it to a spotlight at #NeurIPS2025. See you in San Diego! #Nvidia #AGI

Off to ICCV! Also, we have an omni-modal LLM reveal coming next Monday… straight from Hawaiiiii 🌴

OmniVinci is now #1 paper on Huggingface!!! 🤗 Building omni-modal LLMs is MORE than just mixing tokens 😉 At @NVIDIA, we explored deeper possibilities in building truly omni-modal systems — leading to OmniVinci-9B, which introduces three key innovations: - OmniAlignNet – a

1/2 We’re releasing an in-depth tutorial on neural audio codecs, the secret sauce that makes it possible for audio LLMs to not sound like a horror movie:

$NVDA JUST MADE HISTORY AS THE FIRST $5T COMPANY