It's been a big week on the Veo front. Here are the highlights: —You can now generate vertical format videos in @FlowbyGoogle and via the Gemini API. —We reduced prices in the Gemini API by ~50%, so now developers can build with Veo 3 at $0.40/second and Veo 3 Fast at
MULTIMODAL AI
-
Copilot Labs launches MAI-Voice-1 audio generation with scripted mode
By
–
You asked, we shipped! Scripted mode just dropped for audio generation in Copilot Labs (c/o our new MAI-Voice-1 model).
— Mustafa Suleyman (@mustafasuleyman) 10 septembre 2025
Scripted mode: reads your input verbatim
Emotive: riffs a bit for max drama
Story: performs multiple voices/characters
Try out all 3 ➡️ https://t.co/9hL81LTFwF pic.twitter.com/rOVZKGbDjXYou asked, we shipped! Scripted mode just dropped for audio generation in Copilot Labs (c/o our new MAI-Voice-1 model).
Scripted mode: reads your input verbatim
Emotive: riffs a bit for max drama
Story: performs multiple voices/characters
Try out all 3 https://
copilot.microsoft.com/labs/audio-exp
ression
… -
Stable Audio 2.5 Now Available on Replicate Platform
By
–
🎼Stable Audio 2.5 from @StabilityAI is live on @replicate🎶
— Replicate (@replicate) 10 septembre 2025
up to 3min tracks in just a few seconds
Studio-quality output
Commercial licensing included
Audio inpainting & extensions
Multi-part compositions
Run it via API or web interface → https://t.co/aadY5LDMvy https://t.co/na7ah1HnUFStable Audio 2.5 from @StabilityAI is live on @replicate up to 3min tracks in just a few seconds
Studio-quality output
Commercial licensing included
Audio inpainting & extensions
Multi-part compositions Run it via API or web interface → https://
replicate.com/stability-ai/s
table-audio-2.5
… -
Model Demonstrates Image Generation Through Spreadsheet Pixel Manipulation
By
–
Looks like pure model capability to me, presumably it figured out how to write out colored cells in the spreadsheet and then used one of its other binary tools to make a pixelated the image
-
Lucid Origin Model Now Available on Replicate Platform
By
–
Lucid Origin is now on Replicate Excellent prompt adherence and text rendering for HD output The latest model by @leonardoai
-
Stable Audio 2.5: Enterprise-Grade Sound Production Model Launch
By
–
Today we’re launching Stable Audio 2.5: The first audio model built for enterprise-grade sound production 🔊
— Stability AI (@StabilityAI) 10 septembre 2025
Audio influences brand engagement by 86%, but few enterprises are leveraging audio as an extension of their brand, making customized sound an untapped differentiator.… pic.twitter.com/lCiSOO4RT2Today we’re launching Stable Audio 2.5: The first audio model built for enterprise-grade sound production 🔊 Audio influences brand engagement by 86%, but few enterprises are leveraging audio as an extension of their brand, making customized sound an untapped differentiator. Stable Audio 2.5 is purpose-built for this opportunity to create customizable, high-quality audio at scale, with capabilities that include: ▶️ Improved musical composition: Generate full songs with multi-part structure, meaning a clear intro, middle, and outro. ▶️ Audio inpainting: Input audio, select where the track should start, and the model uses the context to generate the rest of the track. ▶️ Customization: Our team can fine-tune Stable Audio 2.5 to help enterprises create the right sound for their brand. ▶️ Faster inference: The model can generate up to three-minute long tracks in under two seconds on a GPU, outputting in just eight steps (compared to ~50 in the previous model). You can learn more here 👉 bit.ly/46uYmxR
→ View original post on X — @stabilityai, 2025-09-10 14:28 UTC
-
Deploying Tiny Vision Language Models on Jetson Nano
By
–
📢 Getting Started with VLM on Jetson Nano
— Satya Mallick (@LearnOpenCV) 10 septembre 2025
Tiny Vision Language Models (VLMs) like Moondream2, LiquidAI’s LFM2-VL, Apple’s FastVLM, and Huggingface’s SmolVLM2 are bringing vision-language capabilities to the edge. In this tutorial, LearnOpenCV demonstrates how to deploy and run… pic.twitter.com/Rj7aIs4JslGetting Started with VLM on Jetson Nano Tiny Vision Language Models (VLMs) like Moondream2, LiquidAI’s LFM2-VL, Apple’s FastVLM, and Huggingface’s SmolVLM2 are bringing vision-language capabilities to the edge. In this tutorial, LearnOpenCV demonstrates how to deploy and run
-
Image Generation Model Excellence with Proper Prompt Engineering
By
–
Aparte de estas ediciones puntuales, como modelo de generación de imagen, se vé que bien prompteado es un modelo precioso!
-
AI Wearables, Microsoft-Claude Partnership, and Claude Updates
By
–
Top stories in AI today: – Alterego’s “near-telepathic” AI wearable
– Microsoft eyes Claude for Office 365
– Create mini product photos with Nano Banana
– Claude gains file creation capabilities
– 4 new AI tools, community workflows, and more Read more: https://
therundown.ai/p/alterego-deb
uts-near-telepathic-ai-wearable
… -
Nano-banana vs Seedream 4.0: Image Generation Model Comparison
By
–
Igualmente depende de la escena presentada a cada modelo. Por ejemplo con esta imagen, nano-banana logra una iluminación más atractiva y ambos modelos cumplen bien respetando el input. Original / Nano-banana / Seedream 4.0