I have a problem with speech recognition in streaming mode. My audio source is a VoIP phone protocol (SIP), it allows you to output audio data in a format: "encoding": "Mulaw", "sampleRateHertz": 8000
- When I send a new portion of data in streaming mode, an exception occurs: "Status(StatusCode=OutOfRange, Detail="Audio data is being streamed too slow. Please stream audio data approximately at real time.")"
- For verification, I wrote the data to disk in this format. After I read the data and send it in chunks in a streaming mode, it all works correctly and the result is returned.
It turns out that the error appears only in realtime. I ask for help.