Regarding the bit rate of sound files for ASR services

连博10335043 65 Reputation points
2024-08-22T02:50:36.6766667+00:00

When using the REST API for short audio to text conversion, the official documentation requires 256kbps, but sometimes 128kbps can also be recognized.

When using the fast transcription REST API, no official documentation requiring a baud rate, I can recognize files using 128kbps.

My question is, are there minimum requirements for the speech baud rate of the two APIs mentioned above?

When using the REST API for short audio to text conversion, sometimes recognition can be achieved at 128kbps,xiaoaitongxue_low.txt, but sometimes the recognition result is empty without any error，voice2024-08-22-10-34-32.txt.ps:Please modify the file extension of the above two files to. wav

Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
1,675 questions
Accepted answer
  1. romungi-MSFT 44,771 Reputation points Microsoft Employee
    2024-08-23T11:15:56.25+00:00

    @连博10335043 I just used the files with REST API and in both cases the audio was recognized. My resource is in eastus, maybe the documentation is not updated with respect to type of files supported by short audio. Here is a screenshot of the responses.

    User's image

    User's image

    If this answers your query, do click Accept Answer and Yes for was this answer helpful. And, if you have any further query do let us know.

    1 person found this answer helpful.
    0 comments

0 additional answers

Sort by: Most helpful
Most helpful Newest Oldest

Your answer

Answers can be marked as Accepted Answers by the question author, which helps users to know the answer solved the author's problem.