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/Azure-Language-Text-Analytics-for-Health@1
Text Analytics for Health extracts and labels relevant medical information from unstructured clinical text, including doctors' notes, discharge summaries, and electronic health records, using named entity recognition, relation extraction, entity linking, a
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-cogsvc/Azure-Language-Text-PII-redaction@1
PII Redaction for Text automatically detects and masks sensitive information such as names, addresses, phone numbers, credit card details, and other personally identifiable information (PII) in unstructured text.
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-cogsvc/Azure-Speech-Speech-to-text@1
Transcribes streaming or recorded audio into readable text across 140+ languages and dialects. Accuracy can be further optimized with custom models for your specialized use cases.
- Input modalities
- audio
- Output modalities
- text
- Capabilities
- audioInput
azureFoundry/azureml-cogsvc/Azure-Speech-Speech-Translation@1
Translates streaming or recorded audio into text or audio across 140+ languages and dialects. Accuracy can be further optimized with custom models for your specialized use cases.
- Input modalities
- audio
- Output modalities
- text, audio
- Capabilities
- audioInput, multimodal, speechOutput
azureFoundry/azureml-cogsvc/Azure-Speech-Text-to-speech-Avatar@1
Text to speech avatar converts text into a digital video of a human (either a standard avatar or a custom text to speech avatar) speaking with a natural-sounding voice. The text to speech avatar video can be synthesized asynchronously or in real time. Deve
- Input modalities
- text
- Output modalities
- video
- Capabilities
- videoOutput
azureFoundry/azureml-cogsvc/Azure-Speech-Text-to-speech@1
Text-to-speech enables your applications, tools, or devices to convert text into natural synthesized speech. It leverages advanced out-of-the-box [prebuilt neural voices](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?t
- Input modalities
- text
- Output modalities
- audio
- Capabilities
- speechOutput
azureFoundry/azureml-cogsvc/Azure-Speech-Voice-Live@1
Voice Live API is a single unified API that enables low-latency, high-quality speech to speech interactions for voice agents.
- Input modalities
- text, audio
- Output modalities
- text, audio
- Capabilities
- audioInput, multimodal, speechOutput
azureFoundry/azureml-cogsvc/Azure-Translator-Document-translation@1
Document translation is a cloud-based, multilingual service that uses AI to translate documents from one language to another while preserving the document layout.
- Input modalities
- pdf
- Output modalities
- pdf
azureFoundry/azureml-cogsvc/Azure-Translator-Text-translation@1
Text translation is a cloud-based, multilingual service that uses neural machine translation models (NMT) and/or large language models (LLM) to translate text from one language to another, supporting 135 languages.
- Context window
- 50,000
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/BioEmu@1
<!-- DO NOT CHANGE MARKDOWN HEADERS. IF CHANGED, MODEL CARD MAY BE REJECTED BY A REVIEWER --> <!-- `description.md` is required. --> Biomolecular Emulator (BioEmu) is a deep learning model that, given a protein sequence, can sample thousands of statistically independent structu
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/BioEmu@2
Biomolecular Emulator (BioEmu) is a deep learning model that emulates protein structural ensembles at a speed that is orders of magnitude faster than traditional molecular dynamics simulations. By leveraging novel training methods and vast data of protein structures, over 200 mil
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/BioEmu@3
Biomolecular Emulator (BioEmu) is a deep learning model that emulates protein structural ensembles at a speed that is orders of magnitude faster than traditional molecular dynamics simulations. By leveraging novel training methods and vast data of protein structures, over 200 mil
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/BioEmu@4
# Key capabilities ## About this model The BioEmu model is intended for prediction of protein equilibrium structure ensembles. The model is used for predicting diverse protein structures that emulate the thermodynamic ensemble (i.e., Boltzmann distribution) given an amino acid
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/microsoft/models/bio-gpt@biogpt
vertexAI/publishers/microsoft/models/microsoft-biomedclip@biomedclip
azureFoundry/azureml/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224@1
BiomedCLIP is a biomedical vision-language foundation model that is pretrained on PMC-15M, a dataset of 15 million figure-caption pairs extracted from biomedical research articles in PubMed Central, using contrastive learning. It uses PubMedBERT as the text encoder and Vision Tra
azureFoundry/azureml/BiomedCLIP-PubMedBERT_256-vit_base_patch16_224@2
BiomedCLIP is a biomedical vision-language foundation model that is pretrained on PMC-15M, a dataset of 15 million figure-caption pairs extracted from biomedical research articles in PubMed Central, using contrastive learning. It uses PubMedBERT as the text encoder and Vision Tra
azureFoundry/azureml-ai-frontiers/Boltz-1@1
Boltz-1 is an open-source biomolecular structure prediction model for proteins, protein-protein assemblies, and protein-ligand complexes-providing high-quality 3D structural hypotheses to accelerate drug discovery, structural biology, and biotechnology wor
- Input modalities
- text
- Output modalities
- text