Speech-to-Text
POST https://{{region}}.stt.speech.microsoft.com/speech/recognition/conversation/cognitiveservices/v1?language=en-US
This section teaches you how to convert speech (audio) to text. This can be used in a variety of applications, such as captioning.
The selected audio file should be uploaded in the form of binary data in the query Body.
You may refer to Query Parameters for other optional parameters (e.g. how to handle profanities) to refine your POST request.
Please refer to Supported Languages for the language abbreviation that you may be looking for.
Request Params
| Key | Datatype | Required | Description |
|---|---|---|---|
language | string |
HEADERS
| Key | Datatype | Required | Description |
|---|---|---|---|
Content-Type | string | The format and codec of the provided audio data; audio/ogg; codecs=opus is also accepted | |
Accept | string |
RESPONSES
status: OK
{"RecognitionStatus":"Success","Offset":1500000,"Duration":32400000,"DisplayText":"What's the weather like?"}