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-cogsvc/MAI-Voice-2.1-Flash@2026-09-19
MAI-Voice-2.1-Flash is a text-to-speech (TTS) model built for ultra-fast, low-latency generation. It delivers high-fidelity, natural, and expressive speech across 15 languages, while being optimized for real-time responsiveness for voice agents, assistants
- Input modalities
- text
- Output modalities
- audio
- Capabilities
- speechOutput
azureFoundry/azureml-cogsvc/MAI-Voice-2@2026-06-02
MAI-Voice-2 is a prompted text-to-speech (TTS) model that generates high-fidelity, natural, and expressive speech across 10+ languages. It captures human-like intonation, rhythm, and emotional nuance for engaging conversational experiences.
- Input modalities
- text
- Output modalities
- audio
- Capabilities
- speechOutput
cheaperInference/mai-voice-2-flash
- Output modalities
- audio
- Capabilities
- speechOutput
vercelAIGatewayCatalog/microsoft/mai-voice-2-flash
Microsoft AI's low-latency text-to-speech model for voice agents and assistants, with the expressive multilingual voices of MAI-Voice-2 at twice the speed.
- Input modalities
- text
- Output modalities
- audio
- Capabilities
- audioOutput, speechOutput
azureFoundry/azureml-cogsvc/MAI-Voice-2-Flash@2026-07-22
MAI-Voice-2-Flash is a text-to-speech (TTS) model built for ultra-fast, low-latency generation. It delivers high-fidelity, natural, and expressive speech across 15 languages, while being optimized for real-time responsiveness for voice agents, assistants,
- Input modalities
- text
- Output modalities
- audio
- Capabilities
- speechOutput
azureFoundry/azureml-spectre-p/mars-map-autoregressive@1
An automated feature extraction model that converts satellite imagery into accurate, attributed, vectorized GIS data for map workflows.
- Input modalities
- image
- Output modalities
- text
- Capabilities
- visionInput
azureFoundry/azureml-spectre-p/mars-map-autoregressive@2
An automated feature extraction model that converts satellite imagery into accurate, attributed, vectorized GIS data for map workflows.
- Input modalities
- image
- Output modalities
- text
- Capabilities
- visionInput
azureFoundry/azureml-spectre-p/mars-map-autoregressive@3
An automated feature extraction model that converts satellite imagery into accurate, attributed, vectorized GIS data for map workflows.
- Input modalities
- image
- Output modalities
- text
- Capabilities
- visionInput
azureFoundry/azureml-spectre-p/mars-map-autoregressive@4
An automated feature extraction model that converts satellite imagery into accurate, attributed, vectorized GIS data for map workflows.
- Input modalities
- image
- Output modalities
- text
- Capabilities
- visionInput
azureFoundry/azureml-msr/MatterGen@1
A generative model for inorganic materials design
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-msr/MatterGen@2
A generative model for inorganic materials design
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/MatterSim@1
MatterSim is a large-scale pretrained deep learning model for efficient materials emulations and property predictions. MatterSim is a deep learning model for general materials design tasks. It supports efficient atomistic simulations at first-principles level and accurate predic
azureFoundry/azureml/MatterSim@2
MatterSim is a large-scale pretrained deep learning model for efficient materials emulations and property predictions. MatterSim is a deep learning model for general materials design tasks. It supports efficient atomistic simulations at first-principles level and accurate predic
azureFoundry/azureml-ai-frontiers/MedImageInsight@1
Multimodal medical image embedding model for classification, search, and retrieval across imaging modalities
- Input modalities
- image, text
- Output modalities
- embeddings
- Capabilities
- embeddings, multimodal, visionInput
azureFoundry/azureml-ai-frontiers/MedImageInsight@2
Multimodal medical image embedding model for classification, search, and retrieval across imaging modalities
- Input modalities
- image, text
- Output modalities
- embeddings
- Capabilities
- embeddings, multimodal, visionInput
azureFoundry/azureml/MedImageInsight-onnx@1
Most medical imaging AI today is narrowly built to detect a small set of individual findings on a single modality like chest X-rays. This training approach is data- and computationally inefficient, requiring ~6-12 months per finding[1], and often fails to generalize in real world
- Input modalities
- image, text
- Output modalities
- embeddings
- Capabilities
- embeddings, multimodal, visionInput
azureFoundry/azureml/MedImageInsight-onnx@2
Most medical imaging AI today is narrowly built to detect a small set of individual findings on a single modality like chest X-rays. This training approach is data- and computationally inefficient, requiring ~6-12 months per finding[1], and often fails to generalize in real world
- Input modalities
- image, text
- Output modalities
- embeddings
- Capabilities
- embeddings, multimodal, visionInput
azureFoundry/azureml-ai-frontiers-p/MedImageInsight-Premium@1
A multimodal foundation model that generalizes across various medical imaging modalities, anatomies, locations, severities, and types of medical data, producing high-quality image embeddings for retrieval, search, comparison, classification, and tagging ta
- Input modalities
- image, text
- Output modalities
- text
- Capabilities
- multimodal, visionInput