videosdk-plugins-openai 0.0.23__tar.gz → 0.0.24__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of videosdk-plugins-openai might be problematic. Click here for more details.

@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: videosdk-plugins-openai
3
- Version: 0.0.23
3
+ Version: 0.0.24
4
4
  Summary: VideoSDK Agent Framework plugin for OpenAI services
5
5
  Author: videosdk
6
6
  License-Expression: Apache-2.0
@@ -13,7 +13,7 @@ Classifier: Topic :: Multimedia :: Video
13
13
  Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
14
14
  Requires-Python: >=3.11
15
15
  Requires-Dist: openai[realtime]>=1.68.2
16
- Requires-Dist: videosdk-agents>=0.0.23
16
+ Requires-Dist: videosdk-agents>=0.0.24
17
17
  Description-Content-Type: text/markdown
18
18
 
19
19
  # VideoSDK OpenAI Plugin
@@ -21,7 +21,7 @@ classifiers = [
21
21
  "Topic :: Scientific/Engineering :: Artificial Intelligence",
22
22
  ]
23
23
  dependencies = [
24
- "videosdk-agents>=0.0.23",
24
+ "videosdk-agents>=0.0.24",
25
25
  "openai[realtime]>=1.68.2",
26
26
  ]
27
27
 
@@ -427,12 +427,28 @@ class OpenAIRealtime(RealtimeBaseModel[OpenAIEventTypes]):
427
427
  transcript = data.get("transcript", "")
428
428
  if transcript:
429
429
  await realtime_metrics_collector.set_user_transcript(transcript)
430
+ try:
431
+ self.emit("realtime_model_transcription", {
432
+ "role": "user",
433
+ "text": transcript,
434
+ "is_final": True
435
+ })
436
+ except Exception:
437
+ pass
430
438
 
431
439
  async def _handle_response_done(self, data: dict) -> None:
432
440
  """Handle response completion for agent transcript"""
433
441
  if hasattr(self, '_current_audio_transcript') and self._current_audio_transcript:
434
442
  await realtime_metrics_collector.set_agent_response(self._current_audio_transcript)
435
443
  global_event_emitter.emit("text_response", {"text": self._current_audio_transcript, "type": "done"})
444
+ try:
445
+ self.emit("realtime_model_transcription", {
446
+ "role": "agent",
447
+ "text": self._current_audio_transcript,
448
+ "is_final": True
449
+ })
450
+ except Exception:
451
+ pass
436
452
  self._current_audio_transcript = ""
437
453
  await realtime_metrics_collector.set_agent_speech_end(timeout=1.0)
438
454
  self._agent_speaking = False
@@ -0,0 +1 @@
1
+ __version__ = "0.0.24"
@@ -1 +0,0 @@
1
- __version__ = "0.0.23"