cartesia 1.3.1__py3-none-any.whl → 2.0.0a0__py3-none-any.whl

cartesia/tts/types/cancel_context_request.py

@@ -0,0 +1,28 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+from .context_id import ContextId
+import pydantic
+import typing
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+
+
+class CancelContextRequest(UniversalBaseModel):
+    context_id: ContextId = pydantic.Field()
+    """
+    The ID of the context to cancel.
+    """
+
+    cancel: typing.Literal[True] = pydantic.Field(default=True)
+    """
+    Whether to cancel the context, so that no more messages are generated for that context.
+    """
+
+    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

cartesia/tts/types/context_id.py

@@ -0,0 +1,3 @@
+# This file was auto-generated by Fern from our API Definition.
+
+ContextId = str

cartesia/tts/types/controls.py

@@ -0,0 +1,22 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+from .speed import Speed
+import typing
+from .emotion import Emotion
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class Controls(UniversalBaseModel):
+    speed: Speed
+    emotion: typing.List[Emotion]
+
+    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

cartesia/tts/types/emotion.py

@@ -0,0 +1,29 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+Emotion = typing.Union[
+    typing.Literal[
+        "anger:lowest",
+        "anger:low",
+        "anger:high",
+        "anger:highest",
+        "positivity:lowest",
+        "positivity:low",
+        "positivity:high",
+        "positivity:highest",
+        "surprise:lowest",
+        "surprise:low",
+        "surprise:high",
+        "surprise:highest",
+        "sadness:lowest",
+        "sadness:low",
+        "sadness:high",
+        "sadness:highest",
+        "curiosity:lowest",
+        "curiosity:low",
+        "curiosity:high",
+        "curiosity:highest",
+    ],
+    typing.Any,
+]

cartesia/tts/types/flush_id.py

@@ -0,0 +1,3 @@
+# This file was auto-generated by Fern from our API Definition.
+
+FlushId = int

cartesia/tts/types/generation_request.py

@@ -0,0 +1,66 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+import pydantic
+import typing
+from .tts_request_voice_specifier import TtsRequestVoiceSpecifier
+from .supported_language import SupportedLanguage
+from .web_socket_raw_output_format import WebSocketRawOutputFormat
+from .context_id import ContextId
+import typing_extensions
+from ...core.serialization import FieldMetadata
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+
+
+class GenerationRequest(UniversalBaseModel):
+    model_id: str = pydantic.Field()
+    """
+    The ID of the model to use for the generation. See [Models](/build-with-sonic/models) for available models.
+    """
+
+    transcript: typing.Optional[typing.Any] = pydantic.Field(default=None)
+    """
+    The transcript to generate speech for. This can be a string or an iterator over strings.
+    """
+
+    voice: TtsRequestVoiceSpecifier
+    language: typing.Optional[SupportedLanguage] = None
+    output_format: WebSocketRawOutputFormat
+    duration: typing.Optional[float] = pydantic.Field(default=None)
+    """
+    The maximum duration of the audio in seconds. You do not usually need to specify this.
+    If the duration is not appropriate for the length of the transcript, the output audio may be truncated.
+    """
+
+    context_id: typing.Optional[ContextId] = None
+    continue_: typing_extensions.Annotated[typing.Optional[bool], FieldMetadata(alias="continue")] = pydantic.Field(
+        default=None
+    )
+    """
+    Whether this input may be followed by more inputs.
+    If not specified, this defaults to `false`.
+    """
+
+    flush: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Whether to flush the context.
+    """
+
+    add_timestamps: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Whether to return word-level timestamps.
+    """
+
+    add_phoneme_timestamps: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Whether to return phoneme-level timestamps.
+    """
+
+    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

cartesia/tts/types/mp_3_output_format.py

@@ -0,0 +1,23 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+import pydantic
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import typing
+
+
+class Mp3OutputFormat(UniversalBaseModel):
+    sample_rate: int
+    bit_rate: int = pydantic.Field()
+    """
+    The bit rate of the audio in bits per second. Supported bit rates are 32000, 64000, 96000, 128000, 192000.
+    """
+
+    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

cartesia/tts/types/natural_specifier.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+NaturalSpecifier = typing.Union[typing.Literal["slowest", "slow", "normal", "fast", "fastest"], typing.Any]

cartesia/tts/types/numerical_specifier.py

@@ -0,0 +1,3 @@
+# This file was auto-generated by Fern from our API Definition.
+
+NumericalSpecifier = float

cartesia/tts/types/output_format.py

@@ -0,0 +1,58 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+from ...core.pydantic_utilities import UniversalBaseModel
+import typing
+from .raw_encoding import RawEncoding
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class OutputFormat_Raw(UniversalBaseModel):
+    container: typing.Literal["raw"] = "raw"
+    encoding: RawEncoding
+    sample_rate: int
+    bit_rate: typing.Optional[int] = 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
+
+
+class OutputFormat_Wav(UniversalBaseModel):
+    container: typing.Literal["wav"] = "wav"
+    encoding: RawEncoding
+    sample_rate: int
+    bit_rate: typing.Optional[int] = 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
+
+
+class OutputFormat_Mp3(UniversalBaseModel):
+    container: typing.Literal["mp3"] = "mp3"
+    sample_rate: int
+    bit_rate: int
+
+    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
+
+
+OutputFormat = typing.Union[OutputFormat_Raw, OutputFormat_Wav, OutputFormat_Mp3]

cartesia/tts/types/phoneme_timestamps.py

@@ -0,0 +1,21 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+import typing
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class PhonemeTimestamps(UniversalBaseModel):
+    phonemes: typing.List[str]
+    start: typing.List[float]
+    end: typing.List[float]
+
+    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

cartesia/tts/types/raw_encoding.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+RawEncoding = typing.Union[typing.Literal["pcm_f32le", "pcm_s16le", "pcm_mulaw", "pcm_alaw"], typing.Any]

cartesia/tts/types/raw_output_format.py

@@ -0,0 +1,22 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+from .raw_encoding import RawEncoding
+import typing
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class RawOutputFormat(UniversalBaseModel):
+    encoding: RawEncoding
+    sample_rate: int
+    bit_rate: typing.Optional[int] = 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

cartesia/tts/types/speed.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+from .numerical_specifier import NumericalSpecifier
+from .natural_specifier import NaturalSpecifier
+
+Speed = typing.Union[NumericalSpecifier, NaturalSpecifier]

cartesia/tts/types/supported_language.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+SupportedLanguage = typing.Union[
+    typing.Literal["en", "fr", "de", "es", "pt", "zh", "ja", "hi", "it", "ko", "nl", "pl", "ru", "sv", "tr"], typing.Any
+]

cartesia/tts/types/tts_request.py

@@ -0,0 +1,35 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+import pydantic
+from .tts_request_voice_specifier import TtsRequestVoiceSpecifier
+import typing
+from .supported_language import SupportedLanguage
+from .output_format import OutputFormat
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+
+
+class TtsRequest(UniversalBaseModel):
+    model_id: str = pydantic.Field()
+    """
+    The ID of the model to use for the generation. See [Models](/build-with-sonic/models) for available models.
+    """
+
+    transcript: str
+    voice: TtsRequestVoiceSpecifier
+    language: typing.Optional[SupportedLanguage] = None
+    output_format: OutputFormat
+    duration: typing.Optional[float] = pydantic.Field(default=None)
+    """
+    The maximum duration of the audio in seconds. You do not usually need to specify this.
+    If the duration is not appropriate for the length of the transcript, the output audio may be truncated.
+    """
+
+    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

cartesia/tts/types/tts_request_embedding_specifier.py

@@ -0,0 +1,27 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+import typing
+from ...embedding.types.embedding import Embedding
+import typing_extensions
+from .controls import Controls
+from ...core.serialization import FieldMetadata
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class TtsRequestEmbeddingSpecifier(UniversalBaseModel):
+    mode: typing.Literal["embedding"] = "embedding"
+    embedding: Embedding
+    experimental_controls: typing_extensions.Annotated[
+        typing.Optional[Controls], FieldMetadata(alias="__experimental_controls")
+    ] = 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

cartesia/tts/types/tts_request_id_specifier.py

@@ -0,0 +1,27 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+import typing
+from ...voices.types.voice_id import VoiceId
+import typing_extensions
+from .controls import Controls
+from ...core.serialization import FieldMetadata
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class TtsRequestIdSpecifier(UniversalBaseModel):
+    mode: typing.Literal["id"] = "id"
+    id: VoiceId
+    experimental_controls: typing_extensions.Annotated[
+        typing.Optional[Controls], FieldMetadata(alias="__experimental_controls")
+    ] = 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

cartesia/tts/types/tts_request_voice_specifier.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+from .tts_request_id_specifier import TtsRequestIdSpecifier
+from .tts_request_embedding_specifier import TtsRequestEmbeddingSpecifier
+
+TtsRequestVoiceSpecifier = typing.Union[TtsRequestIdSpecifier, TtsRequestEmbeddingSpecifier]

cartesia/tts/types/wav_output_format.py

@@ -0,0 +1,17 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .raw_output_format import RawOutputFormat
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import typing
+import pydantic
+
+
+class WavOutputFormat(RawOutputFormat):
+    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

cartesia/tts/types/web_socket_base_response.py

@@ -0,0 +1,22 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+import typing
+from .context_id import ContextId
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class WebSocketBaseResponse(UniversalBaseModel):
+    context_id: typing.Optional[ContextId] = None
+    status_code: int
+    done: bool
+
+    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

cartesia/tts/types/web_socket_chunk_response.py

@@ -0,0 +1,20 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .web_socket_base_response import WebSocketBaseResponse
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import typing
+import pydantic
+
+
+class WebSocketChunkResponse(WebSocketBaseResponse):
+    data: str
+    step_time: float
+
+    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

cartesia/tts/types/web_socket_done_response.py

@@ -0,0 +1,17 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .web_socket_base_response import WebSocketBaseResponse
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import typing
+import pydantic
+
+
+class WebSocketDoneResponse(WebSocketBaseResponse):
+    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

cartesia/tts/types/web_socket_error_response.py

@@ -0,0 +1,19 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .web_socket_base_response import WebSocketBaseResponse
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import typing
+import pydantic
+
+
+class WebSocketErrorResponse(WebSocketBaseResponse):
+    error: str
+
+    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

cartesia/tts/types/web_socket_flush_done_response.py

@@ -0,0 +1,21 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .web_socket_base_response import WebSocketBaseResponse
+from .flush_id import FlushId
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import typing
+import pydantic
+
+
+class WebSocketFlushDoneResponse(WebSocketBaseResponse):
+    flush_id: FlushId
+    flush_done: bool
+
+    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

cartesia/tts/types/web_socket_phoneme_timestamps_response.py

@@ -0,0 +1,20 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .web_socket_base_response import WebSocketBaseResponse
+import typing
+from .phoneme_timestamps import PhonemeTimestamps
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class WebSocketPhonemeTimestampsResponse(WebSocketBaseResponse):
+    phoneme_timestamps: typing.Optional[PhonemeTimestamps] = 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

cartesia/tts/types/web_socket_raw_output_format.py

@@ -0,0 +1,22 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+import typing
+from .raw_encoding import RawEncoding
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class WebSocketRawOutputFormat(UniversalBaseModel):
+    container: typing.Literal["raw"] = "raw"
+    encoding: RawEncoding
+    sample_rate: int
+
+    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

cartesia/tts/types/web_socket_request.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+from .generation_request import GenerationRequest
+from .cancel_context_request import CancelContextRequest
+
+WebSocketRequest = typing.Union[GenerationRequest, CancelContextRequest]