About Microsoft
Explore research at Microsoft, a site featuring the impact of research along with publications, products, downloads, and research careers.
Microsoft Research conducts fundamental science and technology research across a spectrum of research areas. With labs around the globe we pursue breakthroughs across the computing and AI stack to accelerate discovery across sciences and advance the frontiers of computing and AI to create new foundations for others to build upon.
Artificial intelligence | Search & information retrieval | Human language technologies | Human-computer interaction | Computer vision | Graphics & multimedia | Audio & acoustics
Medical, health & genomics | Economics | Social sciences | Technology for emerging markets | Ecology & environment
Website ↗Documentation ↗
Source ↗ · 2026-11-12T02:17:04.301031227ZazureFoundry/azureml-ai-frontiers/MedImageParse3d@1
Biomedical foundation model for 3D volumetric image segmentation across CT, MRI, and PET modalities
- Input modalities
- image
- Output modalities
- text, image
- Capabilities
- imageOutput, multimodal, visionInput
azureFoundry/azureml-ai-frontiers/MedImageParse@1
Biomedical foundation model for image segmentation, detection, and recognition across 9 imaging modalities
- Input modalities
- image, text
- Output modalities
- image
- Capabilities
- imageOutput, multimodal, visionInput
microsoft/mai-image-2.5
Microsoft AI's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry. It produces photorealistic and artistic images from text prompts with support for various aspect ratios.
- Context window
- 4,096
- Input modalities
- text, image
- Output modalities
- image
- Capabilities
- imageOutput, multimodal, visionInput
Inference prices
- Published price : $5.00 / input_tokens_per_million · openRouter ↗
microsoft/mai-image-2.5-pro-20260723
Microsoft AI's MAI-Image-2.5 is a high-quality image generation model available via Azure AI Foundry. It produces photorealistic and artistic images from text prompts with support for various aspect ratios.
- Context window
- 4,096
- Input modalities
- text, image
- Output modalities
- image
- Capabilities
- imageOutput, multimodal, visionInput
Inference prices
- Published price : $5.00 / input_tokens_per_million · openRouter ↗
microsoft/mai-image-2.6-20260904
MAI-Image-2.6 is an image generation and editing model from Microsoft AI, the precision tier of the MAI-Image-2.6 family alongside the faster [MAI-Image-2.6 Flash](/microsoft/mai-image-2.6-flash). It is suited for design-ready visuals and controlled, iterative editing, and is par
- Context window
- 4,096
- Input modalities
- text, image
- Output modalities
- image
- Capabilities
- imageOutput, multimodal, visionInput
Inference prices
- Published price : $5.00 / input_tokens_per_million · openRouter ↗
microsoft/mai-image-2.6-flash-20260904
MAI-Image-2.6 Flash is the lower-latency, lower-cost member of the [MAI-Image-2.6](/microsoft/mai-image-2.6) family from Microsoft AI, built for latency-sensitive, high-throughput production image generation and editing at comparable quality to the precision tier. It supports the
- Context window
- 4,096
- Input modalities
- text, image
- Output modalities
- image
- Capabilities
- imageOutput, multimodal, visionInput
Inference prices
- Published price : $1.75 / input_tokens_per_million · openRouter ↗
microsoft/mai-transcribe-1.5
MAI-Transcribe 1.5 is a multilingual speech-to-text model from Microsoft AI. It is suited for captions, call transcription, subtitling, accessibility, and other voice-enabled applications, with reliable transcription across 43 languages, diverse accents, and noisy real-world audi
- Context window
- 0
- Input modalities
- audio
- Output modalities
- transcription
- Capabilities
- audioInput
microsoft/mai-transcribe-2-20260903
MAI-Transcribe 2 is a multilingual speech-to-text model from Microsoft AI, ranked #1 on the FLEURS multilingual benchmark. It supports 60 languages with automatic language identification, code switching for mixed-language speech, speaker diarization, word-level timestamps, keywor
- Context window
- 0
- Input modalities
- audio
- Output modalities
- transcription
- Capabilities
- audioInput
microsoft/mai-voice-2
MAI-Voice-2 is an expressive text-to-speech model from Microsoft AI. It is suited for conversational assistants, media narration, accessibility, education, and other long-form voice applications. It supports 15 languages across 18 locales, fine-grained control of tone and deliver
- Context window
- 0
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput
microsoft/mai-voice-2.1-20261001
MAI-Voice-2.1 is Microsoft AI's highest-fidelity, most expressive text-to-speech model. It produces natural, studio-grade speech across 23 languages, with detailed prosody, nuanced expressiveness, and speaker consistency over long-form content. It is suited for audiobooks, podcas
- Context window
- 0
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput
microsoft/mai-voice-2.1-flash-20261001
MAI-Voice-2.1-Flash is a low-latency text-to-speech model from Microsoft AI, optimized for real-time responsiveness. It produces natural, expressive speech across 23 languages, with human-like intonation, rhythm, and emotional nuance. It is suited for voice agents, assistants, ca
- Context window
- 0
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput
microsoft/mai-voice-2-flash-20260723
MAI-Voice-2-Flash is a low-latency text-to-speech model from Microsoft AI for voice agents, assistants, call centers, accessibility, narration, and other interactive applications. It generates expressive 24 kHz mono speech across 15 languages and 18 locales, with fine-grained con
- Context window
- 0
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput
azureFoundry/HuggingFace/microsoft-beit-base-finetuned-ade-640-640@1
# BEiT (base-sized model, fine-tuned on ADE20k) BEiT model pre-trained in a self-supervised fashion on ImageNet-21k (14 million images, 21,841 classes) at resolution 224x224, and fine-tuned on [ADE20k](http://sceneparsing.csail.mit.edu/) (an important benchmark for semantic se
azureFoundry/HuggingFace/microsoft-beit-base-patch16-224@1
`microsoft/beit-base-patch16-224` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/microsoft/beit-base-patch16-224) - [`image-classification` Task on Hugging Face](https://huggingface.co/tasks/image-classification) ### Send Request You c
azureFoundry/HuggingFace/microsoft-beit-base-patch16-224-pt22k-ft22k@1
# BEiT (base-sized model, fine-tuned on ImageNet-22k) BEiT model pre-trained in a self-supervised fashion on ImageNet-22k - also called ImageNet-21k (14 million images, 21,841 classes) at resolution 224x224, and fine-tuned on the same dataset at resolution 224x224. It was intr
azureFoundry/azureml/microsoft-beit-base-patch16-224-pt22k-ft22k@14
BEiT (Bidirectional Encoder representation from Image Transformers) is a vision transformer(ViT) pre-trained with Masked Image Modeling(MIM), which is a self-supervised pre-training inspired by BERT from NLP, followed by Intermediate fine-tuning using ImageNet-22k dataset. It is
azureFoundry/azureml/microsoft-beit-base-patch16-224-pt22k-ft22k@16
BEiT (Bidirectional Encoder representation from Image Transformers) is a vision transformer(ViT) pre-trained with Masked Image Modeling(MIM), which is a self-supervised pre-training inspired by BERT from NLP, followed by Intermediate fine-tuning using ImageNet-22k dataset. It is
azureFoundry/azureml/microsoft-beit-base-patch16-224-pt22k-ft22k@18
BEiT (Bidirectional Encoder representation from Image Transformers) is a vision transformer(ViT) pre-trained with Masked Image Modeling(MIM), which is a self-supervised pre-training inspired by BERT from NLP, followed by Intermediate fine-tuning using ImageNet-22k dataset. It is