Skip to content

feat: [google-cloud-texttospeech] add multi-speaker markup, which allows generating dialogue between multiple speakers #13223

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

Merged
ohmayr merged 2 commits into from
Oct 28, 2024
Merged

feat: [google-cloud-texttospeech] add multi-speaker markup, which allows generating dialogue between multiple speakers #13223

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cba3be0
feat: add multi-speaker markup, which allows generating dialogue betw…
gcf-owl-bot[bot] Oct 28, 2024
941cc4b
🦉 Updates from OwlBot post-processor
gcf-owl-bot[bot] Oct 28, 2024
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
2 changes: 2 additions & 0 deletions packages/google-cloud-texttospeech/google/cloud/texttospeech/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@
CustomVoiceParams,
ListVoicesRequest,
ListVoicesResponse,
MultiSpeakerMarkup,
SsmlVoiceGender,
StreamingSynthesisInput,
StreamingSynthesizeConfig,
Expand Down Expand Up @@ -69,6 +70,7 @@
"CustomVoiceParams",
"ListVoicesRequest",
"ListVoicesResponse",
"MultiSpeakerMarkup",
"StreamingSynthesisInput",
"StreamingSynthesizeConfig",
"StreamingSynthesizeRequest",
Expand Down
2 changes: 1 addition & 1 deletion packages/google-cloud-texttospeech/google/cloud/texttospeech/gapic_version.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,4 +13,4 @@
# See the License for the specific language governing permissions and
# limitations under the License.
#
__version__ = "2.20.0" # {x-release-please-version}
__version__ = "0.0.0" # {x-release-please-version}
2 changes: 2 additions & 0 deletions packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@
CustomVoiceParams,
ListVoicesRequest,
ListVoicesResponse,
MultiSpeakerMarkup,
SsmlVoiceGender,
StreamingSynthesisInput,
StreamingSynthesizeConfig,
Expand Down Expand Up @@ -61,6 +62,7 @@
"CustomVoiceParams",
"ListVoicesRequest",
"ListVoicesResponse",
"MultiSpeakerMarkup",
"SsmlVoiceGender",
"StreamingSynthesisInput",
"StreamingSynthesizeConfig",
Expand Down
2 changes: 1 addition & 1 deletion packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/gapic_version.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,4 +13,4 @@
# See the License for the specific language governing permissions and
# limitations under the License.
#
__version__ = "2.20.0" # {x-release-please-version}
__version__ = "0.0.0" # {x-release-please-version}
2 changes: 2 additions & 0 deletions packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/types/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
CustomVoiceParams,
ListVoicesRequest,
ListVoicesResponse,
MultiSpeakerMarkup,
SsmlVoiceGender,
StreamingSynthesisInput,
StreamingSynthesizeConfig,
Expand All @@ -48,6 +49,7 @@
"CustomVoiceParams",
"ListVoicesRequest",
"ListVoicesResponse",
"MultiSpeakerMarkup",
"StreamingSynthesisInput",
"StreamingSynthesizeConfig",
"StreamingSynthesizeRequest",
Expand Down
48 changes: 48 additions & 0 deletions packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/types/cloud_tts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@
"SynthesizeSpeechRequest",
"CustomPronunciationParams",
"CustomPronunciations",
"MultiSpeakerMarkup",
"SynthesisInput",
"VoiceSelectionParams",
"AudioConfig",
Expand Down Expand Up @@ -328,6 +329,42 @@ class CustomPronunciations(proto.Message):
)


class MultiSpeakerMarkup(proto.Message):
r"""A collection of turns for multi-speaker synthesis.

Attributes:
turns (MutableSequence[google.cloud.texttospeech_v1.types.MultiSpeakerMarkup.Turn]):
Required. Speaker turns.
"""

class Turn(proto.Message):
r"""A Multi-speaker turn.

Attributes:
speaker (str):
Required. The speaker of the turn, for
example, 'O' or 'Q'. Please refer to
documentation for available speakers.
text (str):
Required. The text to speak.
"""

speaker: str = proto.Field(
proto.STRING,
number=1,
)
text: str = proto.Field(
proto.STRING,
number=2,
)

turns: MutableSequence[Turn] = proto.RepeatedField(
proto.MESSAGE,
number=1,
message=Turn,
)


class SynthesisInput(proto.Message):
r"""Contains text input to be synthesized. Either ``text`` or ``ssml``
must be supplied. Supplying both or neither returns
Expand All @@ -354,6 +391,11 @@ class SynthesisInput(proto.Message):
For more information, see
`SSML <https://cloud.google.com/text-to-speech/docs/ssml>`__.

This field is a member of `oneof`_ ``input_source``.
multi_speaker_markup (google.cloud.texttospeech_v1.types.MultiSpeakerMarkup):
The multi-speaker input to be synthesized.
Only applicable for multi-speaker synthesis.

This field is a member of `oneof`_ ``input_source``.
custom_pronunciations (google.cloud.texttospeech_v1.types.CustomPronunciations):
Optional. The pronunciation customizations to
Expand Down Expand Up @@ -383,6 +425,12 @@ class SynthesisInput(proto.Message):
number=2,
oneof="input_source",
)
multi_speaker_markup: "MultiSpeakerMarkup" = proto.Field(
proto.MESSAGE,
number=4,
oneof="input_source",
message="MultiSpeakerMarkup",
)
custom_pronunciations: "CustomPronunciations" = proto.Field(
proto.MESSAGE,
number=3,
Expand Down
2 changes: 1 addition & 1 deletion packages/google-cloud-texttospeech/google/cloud/texttospeech_v1beta1/gapic_version.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,4 +13,4 @@
# See the License for the specific language governing permissions and
# limitations under the License.
#
__version__ = "2.20.0" # {x-release-please-version}
__version__ = "0.0.0" # {x-release-please-version}
2 changes: 1 addition & 1 deletion ...texttospeech/samples/generated_samples/snippet_metadata_google.cloud.texttospeech.v1.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
],
"language": "PYTHON",
"name": "google-cloud-texttospeech",
"version": "2.20.0"
"version": "0.1.0"
},
"snippets": [
{
Expand Down
2 changes: 1 addition & 1 deletion ...ospeech/samples/generated_samples/snippet_metadata_google.cloud.texttospeech.v1beta1.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
],
"language": "PYTHON",
"name": "google-cloud-texttospeech",
"version": "2.20.0"
"version": "0.1.0"
},
"snippets": [
{
Expand Down