@@ -2256,6 +2256,16 @@ class Transcription(_common.BaseModel):
22562256 description="""Detailed word-level transcriptions and timing details.
22572257 """,
22582258 )
2259+ start_offset: Optional[str] = Field(
2260+ default=None,
2261+ description="""Start offset in time of the transcription relative to the start of the audio.
2262+ """,
2263+ )
2264+ end_offset: Optional[str] = Field(
2265+ default=None,
2266+ description="""End offset in time of the transcription relative to the start of the audio.
2267+ """,
2268+ )
22592269
22602270
22612271class TranscriptionDict(TypedDict, total=False):
@@ -2278,6 +2288,14 @@ class TranscriptionDict(TypedDict, total=False):
22782288 """Detailed word-level transcriptions and timing details.
22792289 """
22802290
2291+ start_offset: Optional[str]
2292+ """Start offset in time of the transcription relative to the start of the audio.
2293+ """
2294+
2295+ end_offset: Optional[str]
2296+ """End offset in time of the transcription relative to the start of the audio.
2297+ """
2298+
22812299
22822300TranscriptionOrDict = Union[Transcription, TranscriptionDict]
22832301
@@ -21642,6 +21660,10 @@ class RealtimeInputConfig(_common.BaseModel):
2164221660 default=None,
2164321661 description="""Defines which input is included in the user's turn.""",
2164421662 )
21663+ interim_transcript_timestamp_enabled: Optional[bool] = Field(
21664+ default=None,
21665+ description="""If true, enables interim transcript timestamps.""",
21666+ )
2164521667
2164621668
2164721669class RealtimeInputConfigDict(TypedDict, total=False):
@@ -21660,6 +21682,9 @@ class RealtimeInputConfigDict(TypedDict, total=False):
2166021682 turn_coverage: Optional[TurnCoverage]
2166121683 """Defines which input is included in the user's turn."""
2166221684
21685+ interim_transcript_timestamp_enabled: Optional[bool]
21686+ """If true, enables interim transcript timestamps."""
21687+
2166321688
2166421689RealtimeInputConfigOrDict = Union[RealtimeInputConfig, RealtimeInputConfigDict]
2166521690
0 commit comments