v0.1.6 release

• Fixed breaking change caused by latest websockets version. Also requires updating to latest version. #20
• Improved session update, stores the options if client is not running and use updated options for session in the next start.
• Internal class variable naming changes
• Minor logic improvement to keyword sample on when to cancel timer for rearming
• Updated version to 0.1.6

v0.1.5 release

-Support added for Azure configuration

v0.1.4 release

• Add support to enable automatic reconnection via enable_auto_reconnect under RealtimeOptions. When auto reconnect is enabled, the websocket manager will reconnect in case OpenAI service disconnects due to session expiration after 15minutes. This will raise Reconnected event to the client application.
• Fix for InputAudioBufferCleared event
• Added keyword-based sample for async

v0.1.3 release

-Fix clearing consume event buffer queue in stop

v0.1.2 release

• Fixes to update modalities for session
  • There is apparently an issue with the updating the modalities inside the session in the OpenAI service side. You may see following error message "Error: The server had an error while processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if the error persists"
• Added sample for text input which supports text input + audio output and text input

v0.1.1 release

-Added start and stop for audio capture and playback. This is to make it easier to control when to start and stop the audios.
-Improved audio quality in playback and simplified the interruption by removing the fade out which was not really useful
-Added update_session method to realtime client to be able to update session details once client has been started
-Fixes on realtime sync version stopping, much faster. There are still issues on async version stopping but not included in this PR
-Other minor fixes and updates
-Version updated to 0.1.1

v0.1.0 release

Release from the existing repo containing

1. Experimental Python SDK for OpenAI's Realtime API
2. Samples which utilize local voice activity detection and keyword recognition