[Realtime] Emit current (non-beta) OpenAI audio/transcript event names (#7339)

Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
Nick CaoandClaude Sonnet 5 authored and GitHub committed 2026-09-11 08:50:12 +08:00
1 parent 5c69fc2a8a
commit 498c41b8d6
34 files changed
+251 -189

No files matched your search

+1 -1
View File
@@ -65,7 +65,7 @@ from vllm_omni.clients.duplex import ( # noqa: E402
)
_TRANSCRIPT_DELTA_EVENTS = {
"response.audio_transcript.delta",
"response.output_audio_transcript.delta",
"response.output_text.delta",
"response.text.delta",
}
@@ -63,14 +63,14 @@ class _StreamingOutputWriter:
def handle(self, event: dict[str, object]) -> None:
event_type = event.get("type")
if event_type in {
"response.audio_transcript.delta",
"response.output_audio_transcript.delta",
"response.output_text.delta",
}:
delta = event.get("delta")
if isinstance(delta, str) and delta:
print(delta, end="", file=sys.stderr, flush=True)
return
if event_type != "response.audio.delta":
if event_type != "response.output_audio.delta":
return
delta = event.get("delta") or event.get("audio")
@@ -509,12 +509,12 @@ async def run_demo(args: argparse.Namespace) -> dict[str, object]:
audio = collector.audio_bytes()
first_text_at_s = collector.first_received_at(
"response.audio_transcript.delta",
"response.output_audio_transcript.delta",
"response.output_text.delta",
after_s=commit_sent_at_s,
)
first_audio_at_s = collector.first_received_at(
"response.audio.delta",
"response.output_audio.delta",
after_s=commit_sent_at_s,
)
response_created_at_s = collector.first_received_at(
@@ -536,7 +536,7 @@ async def run_demo(args: argparse.Namespace) -> dict[str, object]:
for event in collector.events
if event.get("type")
in {
"response.audio_transcript.delta",
"response.output_audio_transcript.delta",
"response.output_text.delta",
}
]
@@ -356,7 +356,7 @@
case 'response.speak':
beginAssistant(responseId);
break;
case 'response.audio.delta':
case 'response.output_audio.delta':
currentResponseId = responseId || currentResponseId;
assistantActive = true;
setModel('Speaking');
@@ -364,13 +364,13 @@
.then((decoded) => feedPlayback(decoded, responseId))
.catch((error) => appendLog(`audio decode failed: ${error.message || error}`, true));
break;
case 'response.audio.done':
case 'response.output_audio.done':
requestPlaybackDrain(responseId);
break;
case 'response.audio_transcript.delta':
case 'response.output_audio_transcript.delta':
addTranscript('assistant', event.delta || '');
break;
case 'response.audio_transcript.done':
case 'response.output_audio_transcript.done':
finishTranscript('assistant', event.transcript || '');
break;
case 'conversation.item.input_audio_transcription.delta':