Content by jangoergen (2)
JanGoergen outlines the general availability of multilingual post-stream refinement in Azure Speech. A new LLM Speech streaming model delivers final transcripts in around 100 milliseconds, while expanded locale coverage and phrase lists support multilingual applications. Existing users receive the new engine without code changes.
JanGoergen announces general availability of Real-Time Multichannel Speech-to-Text in Azure Speech. Developers can transcribe two audio channels independently in one session, identify each channel’s language, and retain channel metadata at single-channel pricing. The post includes Python configuration guidance, SDK requirements, and limitations for production workloads.
End of content