Multimodal models

Read the Portuguese translation →

The synthesis for this topic is available in Portuguese.

Videos in this topic

• Cute #Avatars as #AIMalware - #OpenAI #Dots
• Someone Rebuilt Premiere Pro in Rust. I Installed It. (Honest Test)
• Speech-to-Speech Model Research at Google DeepMind — Valeria Wu Fon & Tom Ouyang, Google DeepMind
• NOVO Claude Opus 5.5 Supera Todas as Expectativas e dá Show
• Gemini 4 and Muse Wonder Dropped… But Fable 5.5 Is TERRIFYING
• Qwen3.8-Omni-Flash: mudou o FUTURO dos AGENTES de IA
• The Voice AI Platform Powering a Billion Calls a Year
• What’s new in the Gemini Live API
• Flint 40B vs Qwen3.8 27B
• Block’s Dessa AI Voice Is CRAZY: It LAUGHS Mid-Sentence (I Played the Real Demos)
• MiniCPM-V 4.7 1B: Install with Ollama and llama.cpp, Then Push It to the Limit
• DeepSeek Solved AI’s Memory Problem
• Claude Opus 6 LEAKED, Gemini 4 Carbon Leaks, HUGE OpenAI Update, Claude 24/7 Agent, & More! AI NEWS
• Gemini 4 Argon - Out and Tested!!
• Understand the Gemma 4 model family
• MAI-Base-2: Microsoft’s 2.8T Model is a BREAKTHROUGH
• Indra OCR | Read a 568-Page Book in 77 Seconds (No GPU)
• FLUX 3 Image Klein Hands-On is CRAZY
• Juntei Claude Code e Codex pra consertar meu app. Deu certo.
• They Hacked OpenAI With a Photo… #openai #hack #security
• This Local 1.2B OCR Model Beats GPT-5.2 (and Runs on 8GB GPU) — TeleOCR
• NVIDIA RTX Pro 5500 Blackwell Review
• An Interaction Is All You Need — Ivan Leo, Google DeepMind
• Qwen-Drive-1.0-4B: Why You Still Can’t Trust AI with Self-Driving Cars: Hands-on
• I spent $10,000 on tokens. It should’ve cost $100!!
• Introducing AssemblyAI-TTS-1: Text-to-speech built for voice agents
• Bonsai 2 27B Locally: Near-Lossless Compression in a 9x Smaller
• Qwen3.8 Omni Flash: Fed It Images, Video, and Audio All at Once
• The Tiny TTS Everyone Loved Isn’t Tiny Anymore (KittenTTS 2)
• OlmoEarth v1.3: INSANE Satellite AI or Fooled by WINTER? I Tested It on My RTX 4060
• MiniMax M3.1 Flash IS REALLY GOOD! INSANELY FAST & FREE! (Fully Tested)
• The Best Models Still Reason Like Toddlers — Andrew Dai, Elorian
• Lançou o NOVO DeepSeek V4.1 Flash 1017 e ele é INSANO! (teste completo)
• I Ran IBM’s New 8B Model in 6GB. Here’s the Catch
• Nemotron 3 Diarization with Parakeet Locally: Who Spoke When
• Grounding intelligence in the physical world | Runway Summit SF 2026
• NVIDIA Nemotron-3.5 Bolt-74B-A9B Locally: It’s Not Over
• OpenMobile-2 Is a CRAZY Open-Source Phone AI - I Tested It on a Fake Phone
• I Ran Agent Garten’s Neural Renderer on an H100 (and Built My Own Code World)
• The Self-Driving Eval Trick No AI Benchmark Beats
• Introducing Universal-3.6 Pro Realtime: Short Answers, Heard Right
• AI Engineer Paris 2026 Opening Keynotes: Mistral, Langfuse & Sizzy | Day 1
• Google Vids agora gera vídeos a partir de um só documento
• 🚨 RECRIARAM A ELEVENLABS! Agora Você Pode Usar de GRAÇA 😱
• Audio8 ASR Infinite: 89% Wrong vs 6% Wrong, Same Audio
• NVIDIA Nemotron 3 Diarization Explained
• ByteDance’s New World Model Can Re-Shoot Scenes!
• Insane Interactive World Creator (Genie 4)
• Don’t Buy a GPU for AI. Use These 4 Free Ones First
• Nemotron 3.5 Super VL with Native Speculative Decoding
• Claude OPUS 6 EAP SPOTTED?! Muse Spark Open, GPT-6.1 Astra, MAI-Base-2, & Fable 5.5 LEAKS! AI NEWS
• Remnants — Official Reaction Trailer | Apple Vision Pro
• Two AI Models on One 8GB GPU. Zero Stutter? I Tested It
• Amos 1 Small: 69.5% Accurate, Zero Tokens, 5 GB VRAM
• Introducing the Decisions API
• New Way Now: Captur delivers last-mile AI visual verification at the edge with Google Cloud
• Hybrid Production With Higgsfield Genjutsu | From Studio to Any Scene
• Cloudflare Clef vs Jev: I Tested Q4_K_M Locally in Ollama
• Every Building Is a Balance Sheet: Spatial Memory for Real-World Assets — Jordi Spranger, Spranic
• Gemini 3.8 Flash TTS with Voice Cloning
• Claude Makes a New Kind of Video - Full Tutorial
• GPT-Live-1.1 has new voices and better accents.
• Claude Can Now Make AI Videos By Itself (Higgsfield MCP)
• Build a Full Game with Claude Code (Story, Voices, Ending)
• Introducing Agent Tagging | Runway
• Microsoft’s TRELLIS.2 Is INSANE: One Photo to a Full 3D Model (I Ran It)
• Xiaomi Launches MiMo-V2.6-Pro as Top Open AI Model: Let’s Verify
• Order in any language with Gemini 3.5 Live Translate
• “My name is… my name is…”: A Linguistic Map for Voice Agents — Midam Kim, ServiceNow
• Apple Hasn’t Put an LLM on Your Watch. So I Did.
• NVIDIA’s NEW Nemotron 3.5 Bolt 4B Model Is INSANE… I Tested It 10 Ways On An 8GB Laptop
• Every Audio Workflow You Need For Free (VoiceStudio)
• Top AI Agent Projects : OpenSwarm, Claude Haiku 5.5, NOVA CLI, Semwright & Velozity
• The newest Hermes agent update is unbelievable
• AI News: 6 New Models & A Nano Banana Killer
• AI News: All AI Labs Want To Slow Down (Except One)
• Image Decision Models for RPA: Forms, Scans and Screenshots
• Blurt: push-to-talk dictation on the AssemblyAI Dictation API
• Clef 27B Locally: Multimodal Decision-Maker From Text, Images and Video
• Introducing Genie 4
• Baidu’s Unlimited OCR on an 8GB Laptop: 25 Tests
• Realtime Voice Agents with Frontier Intelligence — Bohan Li, EliseAI
• A 34 MB Turkish Text-to-Speech Model: I Tested It on My Laptop
• GLM 5.3 Flash Free API, Unlimited, No GPU
• Is Google Delaying Gemini 4 Pro? Kimi K3.1 and MiniMax M3.1 LEAKED!
• Everything is LLM - Vibe coding a robot task
• How to Build Voice Agents That Don’t Fall Apart When You Interrupt - Jesse Hall, LiveKit
• Unlimited OCR 2 is here!
• Voice Agents Can Just Do Things — Charlie Guo, OpenAI
• Stop Overpaying for ElevenLabs: Use Gemini Flash TTS Instead!
• Nemotron 3 Diarization - Who Said That?
• This AI Company Is Making The Most Underrated Models (Desert Ant Labs)
• Primeiras impressões da Siri AI em português no iOS 27.2 [Corte do MacMagazine no Ar #700]
• Can a 1B AI Model Actually See? I Tested 29 Task
• Bilibili’s New Translation Model Runs on My 8GB Laptop - I Tested the Memes
• Gemini 4 Argon Is Google’s Most Powerful AI Model + Early Tests!
• A 35B Model on an iPhone Using 3GB? I Checked the Claim
• d1-omni-600M Locally: A Decision Model for Audio, Vision, and Text
• From Scratch to SOTA: Training a 3B State-Space Vision Model — Krishna Prasad Srinivasan, Sarvam
• Como mapear os Stems nos pads da DDJ-FLX2
• Realtime Venus Running Locally: A Full-Duplex Interaction System
• AI News: 24 Things You Need To Know This Week
• Agente Hermes: NOVIDADES que deixaram o App 10x MELHOR!
• Agentes de voz ao vivo são burros #Shorts
• Gemini Live Avatars
• New Mystery AI Video Model: Iron Goddess!
• Kling 4! Gemini 4! ElevenLabs v4! Ideogram 4.5! Everything Goes Four!
• Cloudflare Just Challenged Jev, So I Tested Their New Model (Clef)
• This Tiny 0.8B AI Reads Documents Better Than OCR?
• Make Any Game With AI & 2 New Open Source Video Models!
• I Built a Voice Agent You Can Interrupt (Murf Falcon 2, Real Latency Numbers)
• ByteDance’s World Model Re-Shoots Movies, Sora Returns? & Krea 3 Is Here!
• Space Bunny Alpha: Another Stealth Model, Is it Minimax?
• New Agent Models, Muse Connector & VR Apps | This Week in Replit (Sep 25, 2026)
• Voice of Reason from Kyutai on Top of GLM: Run Locally
• AMD Acquires Fei-Fei Li’s World Labs for $8.2 Billion
• Run Ornith-1.5 122B Locally: Stronger, Faster, Leaner
• Grep or Embeddings? Agentic Search Over Company Documents — George He, LlamaIndex
• This speech-to-text model of just 16.9 MB .. crazy
• Voice Standard Bench - which LLM is best for transcripts?
• Ternary Bonsai 2 9B in GGUF: A 2.4 GB Model Locally
• Gemma 4 12B: The Encoder-Free Model Explained
• DeepSeek Finally Fixed Its Biggest Problem (V4.1 Flash 1017 - Fully Tested!)
• Fish Audio Drama 3: Can You Run It Yourself?
• Jev Just Got Eyes. It Beat GPT-6.1: 9× Faster, 20× Cheaper (1,000 Photos)
• I Tested the Video AI That “Never Forgets” (It Scored 2/10)
• How I’m Actually Using Claude Duet (After 10 Hours of Testing)
• Universal‑3.5 Pro is now available on OpenRouter with the same API key!
• From VLM/VLA’s to Embodied Agents — Armen Aghajanyan, Perceptron AI
• Act, Confirm, or Stop? Smarter behavior for AI assistants, wearables & robots — Amit Desai
• MAI-Voice-2.1 and MAI-Transcribe-2: Microsoft’s New Voice AI Tested
• I Let an AI Voice Approve My Emails. 3 Were Wrong.
• Your Voice Agent is Just a Walkie Talkie — Neil Zeghidour, Gradium
• AI News: Opus 5.5, GPT-6 Sol, Jev, Muse and More!
• Do Diffusion LLMs Scale? Testing Mercury 3 + Decide
• I Got Real Speech Recognition Running on a $10 Chip (Whistle)
• Elorian Glimpse: Visual Thinking That Stays Grounded
• Kling 4.0 AI Video Generator, Claude Sonnet 5.5 + Opus 5.5, New German AI Robot
• FALHA CRÍTICA NO PYTHON!
• Skill issue: stop deploying vision language models, use them with Skills — Merve Noyan, Hugging Face
• Promover Apps e SaaS ACABOU de ficar muito mais FÁCIL e BARATO (caso real)
• The first API built for Dictation: AssemblyAI’s Dictation API
• 1M Parameter AI Pulls Speech Out of Music + Fan Noise
• This 164MB Speech Model Claims to Beat Whisper… I Checked
• A IA MUDOU DE NOVO: Essa Nova Categoria Vai Transformar o Mercado - Dots, Muse, Grok Bot…
• Event Recap: Build Smarter Voice Agents - New York Edition
• ZDTaichu5.0-9B Local Test: Great Tool Calling, Weak Screenshots
• HUGE Google DeepMind RSI LEAKS! GPT-6 Astra NERFED, Kimi K2.8 Code, & More! AI NEWS
• Mistral Large 4 aka “le Chonk”: Europe’s Biggest Open Model
• AI Engineer Paris 2026 Main Stage: Google DeepMind, ElevenLabs, Hugging Face & Stripe | Day 2
• Benchmark LLMs on your own transcripts with Voice Standard Bench
• Lift by Datalab: 90.2% Accuracy, 3x Faster… and the Number They Left Out
• A OpenAI acabou de matar o Jev? (Decisions API)
• New Digit 5 Humanoid Robot AI Upgrades, Gemini 3.8 Live, Claude Docs + Slides
• Como Criar um Agente de IA de Voz
• How MiniMax M3 Was Built: Sparse Attention and Native Multimodality — Olive Song
• Forget the Series 12. My Series 6 Runs an LLM Locally!
• OpenAI Dots: testei o assistente pessoal integrado ao Codex
• Diffusion at Scale: Testing Mercury 3 by Inception
• Gemini agentic video is live in the API and Claude still can’t watch
• JEV com imagens: o que dá para fazer com um modelo de decisão?
• Seedance 2.5 Just Got a Load of Awesome New Features!
• Grok Voice 3.0: World’s Most Intelligent Speech-to-Speech Model?
• Getting a Head Start with Codex | Mitchell Hashimoto
• Top 3 new model launches at Gemini Audio at Night
• Replit x Meta VR
• This is the new ChatGPT Voice, powered by GPT Live
• Tested FLUX 3 Klein Locally: Has AI Image Generation Plateaued?
• OpenAI Dot vs Grok Bot: qual assistente funciona melhor por voz?
• Everything you need to know about Muse Spark Open: A conversation with Meta and Together AI
• Perplexity’s pplx-decider-v1.2: Is It Worth Using? We Tested It Live
• ZDTaichu5.0-9B Locally: Spatial Reasoning, Vision, and Embodied AI
• Open by design: Together AI x MiniMax — Lightning talks
• New NVIDIA Powered Gen 4 AI Robot, New IRON AI Brain (CLAUDE DUET)
• ByteDance Just Made a 33B Video + Audio Model Run in 4 Steps (DMAD)
• NVIDIA’S Small Model: Nemotron-3.5 Bolt E4B 4GB Locally
• Fish Audio Drama 3: Is This Me or My Cloned Voice? Run Locally
• Your Brain Treats a Vivid Future Like a Memory
• Introducing Praxis-1 | Runway
• This 178MB Speech Model Shouldn’t Be This Good (Parakeet Redux)
• $100M ARR Founder: The Secret Behind Great AI Apps
• This Open Model Thought for 88,000 Characters… and Wrote Zero Code
• NVIDIA Just Deleted the VAE and the Vision Encoder (PixelUMM Explained)
• From 15% to 90% GPU Utilization: Fix the Data Pipeline, Not the Model
• The Autonomous Computer: Infrastructure for Computer Use Agents — Ang Li, Simular
• AI Breakthroughs Everyone Missed
• I Ran Liquid’s New Decision Model on an 8GB Laptop. Here’s What Happened.
• 5 Voice Agent Failure Modes You’ll Hit in Week One — Venky B, Plivo
• Introducing: Sessions
• Can Your Agent Hear You Now? Building Live Voice Agents with Gemini — Thor Schaeff
• VoiceStudio: Local Voice AI That Doesn’t Beat ElevenLabs
• Build a real-time voice AI agent with Google ADK and Gemini Live API
• Introducing Runway Ads | Runway
• DeepSeek Nears $12B Funding Round Ahead of Potential IPO
• O que vai acontecer com a engenharia de prompt em 2027
• I Built JARVIS With GPT-6 Astra (It’s INSANE!)
• MiniCPM-V 4.7 35B-A3B Tested Locally: OCR, SQL, Physics and Coding
• Great at coding isn’t always great at voice! Meet Voice Standard Bench.
• Grok 4.7: I Gave It a Broken Championship, a Broken LED, and Coffee
• A nova Siri AI já está em português! #iPhone #apple #siriai