This post has been republished via RSS; it originally appeared at: Microsoft Tech Community - Latest Blogs - .
Considering incorporating speech AI for your business? Then the Azure AI Speech Studio's new demo experience is perfect for you. Our latest scenario-focused pages allow you to utilize your own audio/video input and envision how Speech services can be tailored specifically to meet your individual requirements, specifically for video captioning and call transcription & analytics solutions.
Apply Azure Speech AI and GPT to your Own Data
Until now, you could use Speech Studio's scenario pages to preview our powerful Speech AI and conversation analytics features using pre-selected samples. As of today, our newest feature inside Speech Studio enables you to preview how our Speech and Language AI can be applied to your own data.
The video captioning experience helps you envision how the Cognitive Service for Speech can be used to caption videos in real-time, or how our batch API could be used to subtitle videos and enhance the experience using features such as phrase list, profanity masking, and stable partials.
In the call transcription and analytics experience, you can get a transcript of your own agent-customer conversation, along with speaker separation for two channel (stereo) audio, speaker diarization for single channel (mono) audio, sentiment analysis, PII redaction, and conversation summary powered by OpenAI's GPT models.
Both pages also provide you with sample code, allowing you to kickstart your development and deploy your own solution in a matter of minutes.
How to Use
Get Started Today
Visit Speech Studio today to get started with our scenario experiences and use the sample code to deploy a solution. You can also use our GitHub repository for sample audios and videos, along with sample code.