Add comprehensive type definitions for text-to-speech streaming and processing

Author: NeuralAudioAI

src/neuralaudio/text_to_speech/types/__init__.py

@@ -0,0 +1,29 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .body_text_to_speech_streaming_v_1_text_to_speech_voice_id_stream_post_apply_text_normalization import (
+    BodyTextToSpeechStreamingV1TextToSpeechVoiceIdStreamPostApplyTextNormalization,
+)
+from .body_text_to_speech_streaming_with_timestamps_v_1_text_to_speech_voice_id_stream_with_timestamps_post_apply_text_normalization import (
+    BodyTextToSpeechStreamingWithTimestampsV1TextToSpeechVoiceIdStreamWithTimestampsPostApplyTextNormalization,
+)
+from .body_text_to_speech_v_1_text_to_speech_voice_id_post_apply_text_normalization import (
+    BodyTextToSpeechV1TextToSpeechVoiceIdPostApplyTextNormalization,
+)
+from .body_text_to_speech_with_timestamps_v_1_text_to_speech_voice_id_with_timestamps_post_apply_text_normalization import (
+    BodyTextToSpeechWithTimestampsV1TextToSpeechVoiceIdWithTimestampsPostApplyTextNormalization,
+)
+from .text_to_speech_stream_with_timestamps_response import TextToSpeechStreamWithTimestampsResponse
+from .text_to_speech_stream_with_timestamps_response_alignment import TextToSpeechStreamWithTimestampsResponseAlignment
+from .text_to_speech_stream_with_timestamps_response_normalized_alignment import (
+    TextToSpeechStreamWithTimestampsResponseNormalizedAlignment,
+)
+
+__all__ = [
+    "BodyTextToSpeechStreamingV1TextToSpeechVoiceIdStreamPostApplyTextNormalization",
+    "BodyTextToSpeechStreamingWithTimestampsV1TextToSpeechVoiceIdStreamWithTimestampsPostApplyTextNormalization",
+    "BodyTextToSpeechV1TextToSpeechVoiceIdPostApplyTextNormalization",
+    "BodyTextToSpeechWithTimestampsV1TextToSpeechVoiceIdWithTimestampsPostApplyTextNormalization",
+    "TextToSpeechStreamWithTimestampsResponse",
+    "TextToSpeechStreamWithTimestampsResponseAlignment",
+    "TextToSpeechStreamWithTimestampsResponseNormalizedAlignment",
+]

src/neuralaudio/text_to_speech/types/body_text_to_speech_streaming_v_1_text_to_speech_voice_id_stream_post_apply_text_normalization.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+BodyTextToSpeechStreamingV1TextToSpeechVoiceIdStreamPostApplyTextNormalization = typing.Union[
+    typing.Literal["auto", "on", "off"], typing.Any
+]

src/neuralaudio/text_to_speech/types/body_text_to_speech_streaming_with_timestamps_v_1_text_to_speech_voice_id_stream_with_timestamps_post_apply_text_normalization.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+BodyTextToSpeechStreamingWithTimestampsV1TextToSpeechVoiceIdStreamWithTimestampsPostApplyTextNormalization = (
+    typing.Union[typing.Literal["auto", "on", "off"], typing.Any]
+)

src/neuralaudio/text_to_speech/types/body_text_to_speech_v_1_text_to_speech_voice_id_post_apply_text_normalization.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+BodyTextToSpeechV1TextToSpeechVoiceIdPostApplyTextNormalization = typing.Union[
+    typing.Literal["auto", "on", "off"], typing.Any
+]

src/neuralaudio/text_to_speech/types/body_text_to_speech_with_timestamps_v_1_text_to_speech_voice_id_with_timestamps_post_apply_text_normalization.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+BodyTextToSpeechWithTimestampsV1TextToSpeechVoiceIdWithTimestampsPostApplyTextNormalization = typing.Union[
+    typing.Literal["auto", "on", "off"], typing.Any
+]

src/neuralaudio/text_to_speech/types/text_to_speech_stream_with_timestamps_response.py

@@ -0,0 +1,33 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.unchecked_base_model import UncheckedBaseModel
+import typing_extensions
+import typing
+from ...core.serialization import FieldMetadata
+import pydantic
+from .text_to_speech_stream_with_timestamps_response_alignment import TextToSpeechStreamWithTimestampsResponseAlignment
+from .text_to_speech_stream_with_timestamps_response_normalized_alignment import (
+    TextToSpeechStreamWithTimestampsResponseNormalizedAlignment,
+)
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+
+
+class TextToSpeechStreamWithTimestampsResponse(UncheckedBaseModel):
+    audio_base_64: typing_extensions.Annotated[typing.Optional[str], FieldMetadata(alias="audio_base64")] = (
+        pydantic.Field(default=None)
+    )
+    """
+    Base64 encoded audio chunk
+    """
+
+    alignment: typing.Optional[TextToSpeechStreamWithTimestampsResponseAlignment] = None
+    normalized_alignment: typing.Optional[TextToSpeechStreamWithTimestampsResponseNormalizedAlignment] = None
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

src/neuralaudio/text_to_speech/types/text_to_speech_stream_with_timestamps_response_alignment.py

@@ -0,0 +1,32 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.unchecked_base_model import UncheckedBaseModel
+import typing
+import pydantic
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+
+
+class TextToSpeechStreamWithTimestampsResponseAlignment(UncheckedBaseModel):
+    characters: typing.Optional[typing.List[str]] = pydantic.Field(default=None)
+    """
+    Array of individual characters from the input text
+    """
+
+    character_start_times_seconds: typing.Optional[typing.List[float]] = pydantic.Field(default=None)
+    """
+    Array of start times (in seconds) for each character
+    """
+
+    character_end_times_seconds: typing.Optional[typing.List[float]] = pydantic.Field(default=None)
+    """
+    Array of end times (in seconds) for each character
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

src/neuralaudio/text_to_speech/types/text_to_speech_stream_with_timestamps_response_normalized_alignment.py

@@ -0,0 +1,32 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.unchecked_base_model import UncheckedBaseModel
+import typing
+import pydantic
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+
+
+class TextToSpeechStreamWithTimestampsResponseNormalizedAlignment(UncheckedBaseModel):
+    characters: typing.Optional[typing.List[str]] = pydantic.Field(default=None)
+    """
+    Array of individual characters from the normalized text
+    """
+
+    character_start_times_seconds: typing.Optional[typing.List[float]] = pydantic.Field(default=None)
+    """
+    Array of start times (in seconds) for each normalized character
+    """
+
+    character_end_times_seconds: typing.Optional[typing.List[float]] = pydantic.Field(default=None)
+    """
+    Array of end times (in seconds) for each normalized character
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow