Skip to content

[VoiceLive]Add MAI and additional transcription model support to live tests #45779

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
xitzhang wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[VoiceLive]Add MAI and additional transcription model support to live tests #45779

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 12 additions & 7 deletions sdk/voicelive/azure-ai-voicelive/tests/test_live_realtime_service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -807,17 +807,24 @@ async def test_realtime_service_tool_call_no_audio_overlap(

@pytest.mark.live_test_only
@VoiceLivePreparer()
@pytest.mark.flaky(reruns=1, reruns_delay=2)
@pytest.mark.parametrize("model", ["gpt-4o-realtime-preview"])
@pytest.mark.flaky(reruns=3, reruns_delay=2)
@pytest.mark.parametrize("model", ["gpt-realtime-mini"])
@pytest.mark.parametrize(
"transcription_model", ["gpt-4o-transcribe", "gpt-4o-mini-transcribe", "gpt-4o-transcribe-diarize"]
"transcription_model", [
"whisper-1",
"gpt-4o-transcribe",
"gpt-4o-mini-transcribe",
"gpt-4o-transcribe-diarize",
"azure-speech",
"mai-transcribe-1",
]
Comment on lines +813 to +820
)
@pytest.mark.parametrize("api_version", ["2025-05-01-preview", "2026-01-01-preview"])
async def test_realtime_service_input_audio_transcription(
self,
test_data_dir: Path,
model: str,
transcription_model: Literal["gpt-4o-transcribe", "gpt-4o-mini-transcribe", "gpt-4o-transcribe-diarize"],
transcription_model: Literal["whisper-1", "gpt-4o-transcribe", "gpt-4o-mini-transcribe", "gpt-4o-transcribe-diarize", "azure-speech", "mai-transcribe-1"],
api_version: str,
**kwargs,
):
Expand All @@ -832,12 +839,10 @@ async def test_realtime_service_input_audio_transcription(
) as conn:
input_audio_transcription = AudioInputTranscriptionOptions(
model=transcription_model,
language="en"
)
session = RequestSession(
input_audio_transcription=input_audio_transcription,
instructions="You are a helpful assistant. Please respond briefly.",
turn_detection=ServerVad(),
instructions="You are a helpful assistant.",
)

await conn.session.update(session=session)
Expand Down
Loading