From the course: Microsoft Azure AI Fundamentals (AI-900) Exam Tips

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Speech APIs

Speech APIs - Azure Tutorial

From the course: Microsoft Azure AI Fundamentals (AI-900) Exam Tips

Start my 1-month free trial

Speech APIs

“

- [Narrator] Speech to text is the main speech recognition transcription service in Azure, supporting over 40 languages. Here are a few notes about the service. STT has three main recognition modes. Recognize once, which is ideal for short, conversational scenarios of less than 20 seconds, continuous, which is better suited for longer conversations and dictation, which will interpret word descriptions of punctuation. For example, if you say, do you live in town? The service will recognize that you're asking a question. It can handle profanity. In this case, you have three different handling modes. Raw, which allows profanity, masked, which covers that with asterisks and removed, which the deletes the profanity. STT has a batch prescription API, for audio processing. This is ideal for customers service scenarios where you want you to transcribe longer support calls but don't need the prescription results to be immediate.…

Contents