Skip to content

feat: [GenerateContentConfig] Add GenerationConfig.audio_transcription_config and Part.audio_transcription. #2763

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
copybara-service wants to merge 1 commit into
base: main
Choose a base branch
from
+64 −8
Open

feat: [GenerateContentConfig] Add GenerationConfig.audio_transcription_config and Part.audio_transcription. #2763

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
72 changes: 64 additions & 8 deletions google/genai/tests/models/test_generate_content.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,7 +148,9 @@ class InstrumentEnum(Enum):
),
pytest_helper.TestTableItem(
name='test_labels',
exception_if_mldev='only supported in Gemini Enterprise Agent Platform mode',
exception_if_mldev=(
'only supported in Gemini Enterprise Agent Platform mode'
),
parameters=types._GenerateContentParameters(
model=GEMINI_FLASH_LATEST,
contents=t.t_contents('What is your name?'),
Expand Down Expand Up @@ -283,7 +285,9 @@ class InstrumentEnum(Enum):
]
),
),
exception_if_mldev='is only supported in Gemini Enterprise Agent Platform mode',
exception_if_mldev=(
'is only supported in Gemini Enterprise Agent Platform mode'
),
),
pytest_helper.TestTableItem(
name='test_google_search_tool_with_blocking_confidence',
Expand All @@ -300,7 +304,9 @@ class InstrumentEnum(Enum):
]
),
),
exception_if_mldev='is only supported in Gemini Enterprise Agent Platform mode',
exception_if_mldev=(
'is only supported in Gemini Enterprise Agent Platform mode'
),
),
pytest_helper.TestTableItem(
name='test_enterprise_web_search_tool',
Expand All @@ -315,7 +321,9 @@ class InstrumentEnum(Enum):
]
),
),
exception_if_mldev='is only supported in Gemini Enterprise Agent Platform mode',
exception_if_mldev=(
'is only supported in Gemini Enterprise Agent Platform mode'
),
),
pytest_helper.TestTableItem(
name='test_enterprise_web_search_tool_with_exclude_domains',
Expand All @@ -332,7 +340,9 @@ class InstrumentEnum(Enum):
]
),
),
exception_if_mldev='is only supported in Gemini Enterprise Agent Platform mode',
exception_if_mldev=(
'is only supported in Gemini Enterprise Agent Platform mode'
),
),
pytest_helper.TestTableItem(
name='test_enterprise_web_search_tool_with_blocking_confidence',
Expand All @@ -349,7 +359,9 @@ class InstrumentEnum(Enum):
]
),
),
exception_if_mldev='is only supported in Gemini Enterprise Agent Platform mode',
exception_if_mldev=(
'is only supported in Gemini Enterprise Agent Platform mode'
),
),
pytest_helper.TestTableItem(
name='test_speech_with_config',
Expand Down Expand Up @@ -478,7 +490,9 @@ class InstrumentEnum(Enum):
],
config=types.GenerateContentConfig(audio_timestamp=True),
),
exception_if_mldev='is only supported in Gemini Enterprise Agent Platform mode',
exception_if_mldev=(
'is only supported in Gemini Enterprise Agent Platform mode'
),
),
pytest_helper.TestTableItem(
name='test_response_schema_with_default',
Expand Down Expand Up @@ -556,7 +570,9 @@ class InstrumentEnum(Enum):
},
},
),
exception_if_mldev='is only supported in Gemini Enterprise Agent Platform mode',
exception_if_mldev=(
'is only supported in Gemini Enterprise Agent Platform mode'
),
),
pytest_helper.TestTableItem(
name='test_service_tier',
Expand All @@ -580,6 +596,27 @@ class InstrumentEnum(Enum):
),
exception_if_vertex='400',
),
pytest_helper.TestTableItem(
name='test_audio_transcription_config',
parameters=types._GenerateContentParameters(
model='gemini-2.5-flash-preview-tts',
contents=t.t_contents('Produce a speech response saying "Cheese"'),
config=types.GenerateContentConfig(
response_modalities=['audio'],
speech_config=types.SpeechConfig(
voice_config=types.VoiceConfig(
prebuilt_voice_config=types.PrebuiltVoiceConfig(
voice_name='charon'
)
)
),
audio_transcription_config=types.AudioTranscriptionConfig(
diarization=True,
word_timestamp=True,
),
),
),
),
]

pytestmark = pytest_helper.setup(
Expand Down Expand Up @@ -2583,3 +2620,22 @@ def test_response_json_schema_with_one_of(client):
assert resource_config['size'] == 10
assert 'tier' not in resource_config
assert set(resource_config.keys()) == {'size'}


def test_audio_wav_input(client):

response = client.models.generate_content(
model='gemini-2.5-flash-preview-tts',
contents=[
'What is this audio about?',
types.Part.from_bytes(data=audio_bytes, mime_type='audio/wav'),
],
config=types.GenerateContentConfig(
audio_transcription_config=types.AudioTranscriptionConfig(
diarization=True,
word_timestamp=True,
language_auto={},
),
),
)
assert response.text is not None
Loading