feat: Add flat language_codes field to AudioTranscriptionConfig.

PiperOrigin-RevId: 955519477

Author: google-genai-bot

google/genai/_gaos/types/interactions/transcriptionconfig.py

@@ -27,11 +27,6 @@
 class TranscriptionConfigParam(TypedDict):
     r"""Configuration for speech recognition (transcription)."""
 
-    language_hints: List[str]
-    r"""Required. BCP-47 language codes providing hints about the languages present in the
-    audio. At least one must be specified, or set to [\"auto\"] to enable
-    automatic language detection.
-    """
     adaptation_phrases: NotRequired[List[str]]
     r"""Optional. A list of phrases to bias the ASR model towards."""
     custom_vocabulary: NotRequired[List[str]]
@@ -40,6 +35,10 @@ class TranscriptionConfigParam(TypedDict):
     """
     diarization_mode: NotRequired[str]
     r"""Optional. Configures speaker diarization. Supported values: \"speaker\"."""
+    language_codes: NotRequired[List[str]]
+    r"""Optional. BCP-47 language codes providing hints about the languages present in the
+    audio. If omitted or empty, defaults to automatic language detection.
+    """
     timestamp_granularities: NotRequired[List[str]]
     r"""Optional. The granularity of timestamps to include in the transcription output.
     Supported values: \"word\". If empty, no timestamps are generated.
@@ -49,12 +48,6 @@ class TranscriptionConfigParam(TypedDict):
 class TranscriptionConfig(BaseModel):
     r"""Configuration for speech recognition (transcription)."""
 
-    language_hints: List[str]
-    r"""Required. BCP-47 language codes providing hints about the languages present in the
-    audio. At least one must be specified, or set to [\"auto\"] to enable
-    automatic language detection.
-    """
-
     adaptation_phrases: Annotated[
         Optional[List[str]],
         pydantic.Field(
@@ -71,6 +64,11 @@ class TranscriptionConfig(BaseModel):
     diarization_mode: Optional[str] = None
     r"""Optional. Configures speaker diarization. Supported values: \"speaker\"."""
 
+    language_codes: Optional[List[str]] = None
+    r"""Optional. BCP-47 language codes providing hints about the languages present in the
+    audio. If omitted or empty, defaults to automatic language detection.
+    """
+
     timestamp_granularities: Optional[List[str]] = None
     r"""Optional. The granularity of timestamps to include in the transcription output.
     Supported values: \"word\". If empty, no timestamps are generated.
@@ -83,6 +81,7 @@ def serialize_model(self, handler):
                 "adaptation_phrases",
                 "custom_vocabulary",
                 "diarization_mode",
+                "language_codes",
                 "timestamp_granularities",
             ]
         )

google/genai/_live_converters.py

@@ -23,46 +23,6 @@
 from ._common import set_value_by_path as setv
 
 
-def _AudioTranscriptionConfig_to_mldev(
-    from_object: Union[dict[str, Any], object],
-    parent_object: Optional[dict[str, Any]] = None,
-) -> dict[str, Any]:
-  to_object: dict[str, Any] = {}
-  if getv(from_object, ['language_codes']) is not None:
-    raise ValueError(
-        'language_codes parameter is only supported in Gemini Enterprise Agent'
-        ' Platform mode, not in Gemini Developer API mode.'
-    )
-
-  if getv(from_object, ['language_auto']) is not None:
-    setv(to_object, ['languageAuto'], getv(from_object, ['language_auto']))
-
-  if getv(from_object, ['language_hints']) is not None:
-    setv(to_object, ['languageHints'], getv(from_object, ['language_hints']))
-
-  if getv(from_object, ['custom_vocabulary']) is not None:
-    setv(
-        to_object,
-        ['customVocabulary'],
-        getv(from_object, ['custom_vocabulary']),
-    )
-
-  if getv(from_object, ['adaptation_phrases']) is not None:
-    setv(
-        to_object,
-        ['adaptationPhrases'],
-        getv(from_object, ['adaptation_phrases']),
-    )
-
-  if getv(from_object, ['word_timestamp']) is not None:
-    setv(to_object, ['wordTimestamp'], getv(from_object, ['word_timestamp']))
-
-  if getv(from_object, ['diarization']) is not None:
-    setv(to_object, ['diarization'], getv(from_object, ['diarization']))
-
-  return to_object
-
-
 def _AuthConfig_to_mldev(
     from_object: Union[dict[str, Any], object],
     parent_object: Optional[dict[str, Any]] = None,
@@ -733,18 +693,14 @@ def _LiveClientSetup_to_mldev(
     setv(
         to_object,
         ['inputAudioTranscription'],
-        _AudioTranscriptionConfig_to_mldev(
-            getv(from_object, ['input_audio_transcription']), to_object
-        ),
+        getv(from_object, ['input_audio_transcription']),
     )
 
   if getv(from_object, ['output_audio_transcription']) is not None:
     setv(
         to_object,
         ['outputAudioTranscription'],
-        _AudioTranscriptionConfig_to_mldev(
-            getv(from_object, ['output_audio_transcription']), to_object
-        ),
+        getv(from_object, ['output_audio_transcription']),
     )
 
   if getv(from_object, ['proactivity']) is not None:
@@ -982,18 +938,14 @@ def _LiveConnectConfig_to_mldev(
     setv(
         parent_object,
         ['setup', 'inputAudioTranscription'],
-        _AudioTranscriptionConfig_to_mldev(
-            getv(from_object, ['input_audio_transcription']), to_object
-        ),
+        getv(from_object, ['input_audio_transcription']),
     )
 
   if getv(from_object, ['output_audio_transcription']) is not None:
     setv(
         parent_object,
         ['setup', 'outputAudioTranscription'],
-        _AudioTranscriptionConfig_to_mldev(
-            getv(from_object, ['output_audio_transcription']), to_object
-        ),
+        getv(from_object, ['output_audio_transcription']),
     )
 
   if getv(from_object, ['realtime_input_config']) is not None:

google/genai/_tokens_converters.py

@@ -23,46 +23,6 @@
 from ._common import set_value_by_path as setv
 
 
-def _AudioTranscriptionConfig_to_mldev(
-    from_object: Union[dict[str, Any], object],
-    parent_object: Optional[dict[str, Any]] = None,
-) -> dict[str, Any]:
-  to_object: dict[str, Any] = {}
-  if getv(from_object, ['language_codes']) is not None:
-    raise ValueError(
-        'language_codes parameter is only supported in Gemini Enterprise Agent'
-        ' Platform mode, not in Gemini Developer API mode.'
-    )
-
-  if getv(from_object, ['language_auto']) is not None:
-    setv(to_object, ['languageAuto'], getv(from_object, ['language_auto']))
-
-  if getv(from_object, ['language_hints']) is not None:
-    setv(to_object, ['languageHints'], getv(from_object, ['language_hints']))
-
-  if getv(from_object, ['custom_vocabulary']) is not None:
-    setv(
-        to_object,
-        ['customVocabulary'],
-        getv(from_object, ['custom_vocabulary']),
-    )
-
-  if getv(from_object, ['adaptation_phrases']) is not None:
-    setv(
-        to_object,
-        ['adaptationPhrases'],
-        getv(from_object, ['adaptation_phrases']),
-    )
-
-  if getv(from_object, ['word_timestamp']) is not None:
-    setv(to_object, ['wordTimestamp'], getv(from_object, ['word_timestamp']))
-
-  if getv(from_object, ['diarization']) is not None:
-    setv(to_object, ['diarization'], getv(from_object, ['diarization']))
-
-  return to_object
-
-
 def _AuthConfig_to_mldev(
     from_object: Union[dict[str, Any], object],
     parent_object: Optional[dict[str, Any]] = None,
@@ -435,18 +395,14 @@ def _LiveConnectConfig_to_mldev(
     setv(
         parent_object,
         ['setup', 'inputAudioTranscription'],
-        _AudioTranscriptionConfig_to_mldev(
-            getv(from_object, ['input_audio_transcription']), to_object
-        ),
+        getv(from_object, ['input_audio_transcription']),
     )
 
   if getv(from_object, ['output_audio_transcription']) is not None:
     setv(
         parent_object,
         ['setup', 'outputAudioTranscription'],
-        _AudioTranscriptionConfig_to_mldev(
-            getv(from_object, ['output_audio_transcription']), to_object
-        ),
+        getv(from_object, ['output_audio_transcription']),
     )
 
   if getv(from_object, ['realtime_input_config']) is not None:

google/genai/batches.py

@@ -34,46 +34,6 @@
 logger = logging.getLogger('google_genai.batches')
 
 
-def _AudioTranscriptionConfig_to_mldev(
-    from_object: Union[dict[str, Any], object],
-    parent_object: Optional[dict[str, Any]] = None,
-) -> dict[str, Any]:
-  to_object: dict[str, Any] = {}
-  if getv(from_object, ['language_codes']) is not None:
-    raise ValueError(
-        'language_codes parameter is only supported in Gemini Enterprise Agent'
-        ' Platform mode, not in Gemini Developer API mode.'
-    )
-
-  if getv(from_object, ['language_auto']) is not None:
-    setv(to_object, ['languageAuto'], getv(from_object, ['language_auto']))
-
-  if getv(from_object, ['language_hints']) is not None:
-    setv(to_object, ['languageHints'], getv(from_object, ['language_hints']))
-
-  if getv(from_object, ['custom_vocabulary']) is not None:
-    setv(
-        to_object,
-        ['customVocabulary'],
-        getv(from_object, ['custom_vocabulary']),
-    )
-
-  if getv(from_object, ['adaptation_phrases']) is not None:
-    setv(
-        to_object,
-        ['adaptationPhrases'],
-        getv(from_object, ['adaptation_phrases']),
-    )
-
-  if getv(from_object, ['word_timestamp']) is not None:
-    setv(to_object, ['wordTimestamp'], getv(from_object, ['word_timestamp']))
-
-  if getv(from_object, ['diarization']) is not None:
-    setv(to_object, ['diarization'], getv(from_object, ['diarization']))
-
-  return to_object
-
-
 def _AuthConfig_to_mldev(
     from_object: Union[dict[str, Any], object],
     parent_object: Optional[dict[str, Any]] = None,
@@ -1226,9 +1186,7 @@ def _GenerateContentConfig_to_mldev(
     setv(
         to_object,
         ['audioTranscriptionConfig'],
-        _AudioTranscriptionConfig_to_mldev(
-            getv(from_object, ['audio_transcription_config']), to_object
-        ),
+        getv(from_object, ['audio_transcription_config']),
     )
 
   return to_object

google/genai/models.py

@@ -65,47 +65,6 @@ def _VideoGenerationReferenceType_to_mldev_enum_validate(
     )
 
 
-def _AudioTranscriptionConfig_to_mldev(
-    from_object: Union[dict[str, Any], object],
-    parent_object: Optional[dict[str, Any]] = None,
-    root_object: Optional[Union[dict[str, Any], object]] = None,
-) -> dict[str, Any]:
-  to_object: dict[str, Any] = {}
-  if getv(from_object, ['language_codes']) is not None:
-    raise ValueError(
-        'language_codes parameter is only supported in Gemini Enterprise Agent'
-        ' Platform mode, not in Gemini Developer API mode.'
-    )
-
-  if getv(from_object, ['language_auto']) is not None:
-    setv(to_object, ['languageAuto'], getv(from_object, ['language_auto']))
-
-  if getv(from_object, ['language_hints']) is not None:
-    setv(to_object, ['languageHints'], getv(from_object, ['language_hints']))
-
-  if getv(from_object, ['custom_vocabulary']) is not None:
-    setv(
-        to_object,
-        ['customVocabulary'],
-        getv(from_object, ['custom_vocabulary']),
-    )
-
-  if getv(from_object, ['adaptation_phrases']) is not None:
-    setv(
-        to_object,
-        ['adaptationPhrases'],
-        getv(from_object, ['adaptation_phrases']),
-    )
-
-  if getv(from_object, ['word_timestamp']) is not None:
-    setv(to_object, ['wordTimestamp'], getv(from_object, ['word_timestamp']))
-
-  if getv(from_object, ['diarization']) is not None:
-    setv(to_object, ['diarization'], getv(from_object, ['diarization']))
-
-  return to_object
-
-
 def _AuthConfig_to_mldev(
     from_object: Union[dict[str, Any], object],
     parent_object: Optional[dict[str, Any]] = None,
@@ -1508,11 +1467,7 @@ def _GenerateContentConfig_to_mldev(
     setv(
         to_object,
         ['audioTranscriptionConfig'],
-        _AudioTranscriptionConfig_to_mldev(
-            getv(from_object, ['audio_transcription_config']),
-            to_object,
-            root_object,
-        ),
+        getv(from_object, ['audio_transcription_config']),
     )
 
   return to_object