feat: Add source_text to AudioTranscriptionConfig and SmartTranscriptionMode.

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

@@ -18,28 +18,64 @@
 """Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""
 
 from __future__ import annotations
-from .. import BaseModel
+from .. import BaseModel, UNSET_SENTINEL, current_exclude_none, serialize_with_info
 from ...utils import validate_const
+from ..basemodel import current_filtered_dump
 import pydantic
+from pydantic import model_serializer
 from pydantic.functional_validators import AfterValidator
-from typing import Literal
-from typing_extensions import Annotated, TypedDict
+from typing import Literal, Optional
+from typing_extensions import Annotated, NotRequired, TypedDict
 
 
 class SmartTranscriptionModeParam(TypedDict):
     r"""Configuration for smart transcription mode."""
 
+    source_text: NotRequired[str]
+    r"""The source text to be edited or rewritten via voice instructions.
+    When provided, the model performs voice-driven editing and outputs the
+    finalized replacement text.
+    """
     type: Literal["smart"]
 
 
 class SmartTranscriptionMode(BaseModel):
     r"""Configuration for smart transcription mode."""
 
+    source_text: Optional[str] = None
+    r"""The source text to be edited or rewritten via voice instructions.
+    When provided, the model performs voice-driven editing and outputs the
+    finalized replacement text.
+    """
+
     type: Annotated[
         Annotated[Literal["smart"], AfterValidator(validate_const("smart"))],
         pydantic.Field(alias="type"),
     ] = "smart"
 
+    @model_serializer(mode="wrap")
+    def _serialize_model_with_info(self, handler, info):
+        return serialize_with_info(self.serialize_model, handler, info)
+
+    def serialize_model(self, handler):
+        optional_fields = set(["source_text"])
+        exclude_none = current_exclude_none()
+        skip_filtered = exclude_none is False or current_filtered_dump()
+        serialized = handler(self)
+        m = {}
+
+        for n, f in type(self).model_fields.items():
+            k = f.alias if f.alias is not None else n
+            if k not in serialized and n not in serialized and skip_filtered:
+                continue
+            val = serialized.get(k, serialized.get(n))
+
+            if val != UNSET_SENTINEL:
+                if val is not None or k not in optional_fields:
+                    m[k] = val
+
+        return m
+
 
 try:
     SmartTranscriptionMode.model_rebuild()

google/genai/types.py

@@ -6522,6 +6522,10 @@ class AudioTranscriptionConfig(_common.BaseModel):
       default=None,
       description="""Optional. Configures transcription mode. Supported values: `VERBATIM`, `SMART`. If unspecified, defaults to `VERBATIM` transcription. In `SMART` mode, the model performs disfluency removal (eliminating filler words, repetitions, and false starts), light grammatical cleanup, automatic formatting (paragraphs, bullet points, numbered lists), and minor user edits (inline self-corrections). Timestamps and diarization are incompatible with mode `SMART`.""",
   )
+  source_text: Optional[str] = Field(
+      default=None,
+      description="""Optional. The source text to be edited or rewritten via voice instructions. When provided in `SMART` mode, the model evaluates the audio input against this text and emits the complete replacement text in the candidate response rather than appending to it.""",
+  )
 
 
 class AudioTranscriptionConfigDict(TypedDict, total=False):
@@ -6553,6 +6557,9 @@ class AudioTranscriptionConfigDict(TypedDict, total=False):
   mode: Optional[AudioTranscriptionConfigMode]
   """Optional. Configures transcription mode. Supported values: `VERBATIM`, `SMART`. If unspecified, defaults to `VERBATIM` transcription. In `SMART` mode, the model performs disfluency removal (eliminating filler words, repetitions, and false starts), light grammatical cleanup, automatic formatting (paragraphs, bullet points, numbered lists), and minor user edits (inline self-corrections). Timestamps and diarization are incompatible with mode `SMART`."""
 
+  source_text: Optional[str]
+  """Optional. The source text to be edited or rewritten via voice instructions. When provided in `SMART` mode, the model evaluates the audio input against this text and emits the complete replacement text in the candidate response rather than appending to it."""
+
 
 AudioTranscriptionConfigOrDict = Union[
     AudioTranscriptionConfig, AudioTranscriptionConfigDict