Provides the ability to use OpenAI Speech-To-Text service in the Freeswitch.
Also capable to work with whisperd

If you have problems with building this module, pay attention to this issue and the comment, maybe you faced the same thing.

UPD 30-12-2024:
seems the issue with noises after playback done (play_and_detect_speech) has been fixed in Freeswitch 1.10.10+ (at least in my case)

Usage example

<extension name="openai-asr">
  <condition field="destination_number" expression="^(3222)$">
    <action application="answer"/>
    <action application="play_and_detect_speech" data="/tmp/test2.wav detect:openai"/>
    <action application="sleep" data="1000"/>
    <action application="log" data="CRIT SPEECH_RESULT=${detect_speech_result}"/>
    <action application="hangup"/>
 </condition>
</extension>