MAI Multimodal - Product. Previously @GoogleDeepMind, @ShiftLabAI, @Speechmatics. Speech is core to the future AGI stack.
London
Joined February 2011
- Tweets513
- Following1K
- Followers895
- Likes2.1K
Pinned Tweet
Today, @MicrosoftAI is now 3rd on LMArena lab leaderboard with our latest model: MAI-Image-2.
arena.ai/leaderboard/text-to…
I’ve been playing with the model a lot these last few weeks and the capabilities are truly impressive.
Trevor Back retweeted
Fastest. Cheapest. Best. ... MAI-Transcribe-2
10x faster than GPT-Transcribe. 5x faster than Gemini 3.5
#1 on the Artificial Analysis accuracy-latency Pareto frontier
Priced at the lowest on the market.
Truly fantastic work from the team! Try it out below.
Trevor Back retweeted
Introducing Ode Poetry. Ode is a wonderful poetry pharmacy that reads you a poem for the moment you’re in. Just tell Ode what you're feeling, and it uses Microsoft AI audio models to connect you with the same work that poetry expert William Sieghart would recommend.
The best technology doesn't replace human creativity, it helps more people experience it. Super proud of the team for making this truly humanist tool. More in the blog:
microsoft.ai/news/ode-poetry…
This one is special, and personal.
What if you could be prescribed a poem based on how you're feeling at that exact moment?
We've launched Ode Poetry to provide an experience that creates space to feel.
youtube.com/watch?v=hnLxZYDb…
Try it out here: odepoetry.ai
A collaboration between @MicrosoftAI , Poetry Pharmacy and Gravity Road.
William's voice is just wonderful, the poems are beautiful, and the Microsoft AI audio models are incredible.
Trevor Back retweeted
Meet MAI-Image-2.5 - ranked third on the @arena text-to-image leaderboard. It's another great advance in quality. And with Build just a week away, there's much more to come from the @MicrosoftAI team. I can't wait.
An aperitif for @MicrosoftAI at Build next week:
Welcoming *MAI-Image-2.5* to the MAI multimodal family of models. +72 on our previous version, and ranking 3rd on @arena T2I leaderboard.
Don't just take my word for it...
“MAI-Image-2-Efficient shows strong progress in prompt fidelity and creative usability across a range of workflows ... what ultimately matters when teams move from experimentation into real-world use.” Vanessa Salvo, PM, Shutterstock
We're just getting started (obvs): more models ahead - stay tuned.
Read more here. microsoft.ai/news/mai-image-…
Trevor Back retweeted
MAI‑Transcribe‑1 makes speech‑to‑text clearer, faster, and more reliable even in noisy audio. Ranked #1 on the industry-standard FLEURS word error rate benchmark. Now in public preview. Learn more: msft.it/6019QLa8B
Three models. Three top-tier results. All shipped within just a few months by @MicrosoftAI .
- MAI-Transcribe-1: most accurate transcription model in the world across 25 languages on FLEURS.
- MAI-Voice-1 for natural, expressive speech.
- MAI-Image-2: a top 3 model family
and find out more about MAI-Transcribe-1 here: microsoft.ai/news/state-of-t…
Trevor Back retweeted
Meet MAI‑Image‑2. Built with creatives, for real creative work. Ranked #5 on @arena’s text‑to‑image leaderboard. Available now: msft.it/6014QUCBe
Lovely graphic from @arena showing our progress since Image-1 🙏
Let’s dive deeper into the massive improvements between MAI-Image-2 vs. MAI-Image-1 by @MicrosoftAI.
MAI-Image-2 shows significant gains across all sub-categories for Text-to-Image:
Gains across all 7 sub-categories in order of magnitude:
- Text Rendering (+115 pts)
- Portraits (+105 pts)
- Product, Branding & Commercial Design (+102 pts)
- Photorealistic & Cinematic Imagery (+97 pts)
- 3D Imaging & Modeling (+92 pts)
- Art (+87 pts)
- Cartoon, Anime & Fantasy (+81 pts)
