feat: #1614 gpt-realtime migration (Realtime API GA) #1646
+512
−166
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
rm-openai
reviewed
Sep 3, 2025
examples/realtime/app/server.py
Outdated
Comment on lines
48
to
55
| # Disable server-side interrupt_response to avoid truncating assistant audio | ||
| session_context = await runner.run( | ||
| model_config={ | ||
| "initial_model_settings": { | ||
| "turn_detection": {"type": "semantic_vad", "interrupt_response": False} | ||
| } | ||
| } | ||
| ) |
There was a problem hiding this comment.
do we need to do this by default? why?
There was a problem hiding this comment.
I explored some changes to make the audio output quality, but they're not related to the gpt-realtime migration. So, I've reverted all of them. I will continue seeing improvements for this example app, but it can be done with a separate pull request.
examples/realtime/app/server.py
Outdated
| @@ -93,7 +111,9 @@ async def _serialize_event(self, event: RealtimeSessionEvent) -> dict[str, Any]: | |||
| base_event["tool"] = event.tool.name | |||
| base_event["output"] = str(event.output) | |||
| elif event.type == "audio": | |||
| base_event["audio"] = base64.b64encode(event.audio.data).decode("utf-8") | |||
| # Coalesce raw PCM and flush on a steady timer for smoother playback. | |||
There was a problem hiding this comment.
is this just a quality improvement? would be nice to make it be a separate PR if so
There was a problem hiding this comment.
yeah, same with above (I won't repeat this for the rest)
examples/realtime/app/server.py
Outdated
| "type": event.data.type, | ||
| } | ||
| # Surface useful raw events to the UI with details. | ||
| if getattr(event.data, "type", None) == "transcript_delta": |
examples/realtime/app/server.py
Outdated
| @@ -142,7 +195,8 @@ async def websocket_endpoint(websocket: WebSocket, session_id: str): | |||
| if message["type"] == "audio": | |||
| # Convert int16 array to bytes | |||
| int16_data = message["data"] | |||
| audio_bytes = struct.pack(f"{len(int16_data)}h", *int16_data) | |||
| # Send little-endian PCM16 to the model. | |||
There was a problem hiding this comment.
did this change as part of the GA?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
this is still in progress but will resolve #1614