cartesia 2.0.5__py3-none-any.whl → 2.0.7__py3-none-any.whl

cartesia/tts/requests/__init__.py

@@ -2,16 +2,20 @@
 
 from .cancel_context_request import CancelContextRequestParams
 from .controls import ControlsParams
+from .experimental_model_controls import ExperimentalModelControlsParams
+from .generation_config import GenerationConfigParams
 from .generation_request import GenerationRequestParams
 from .mp_3_output_format import Mp3OutputFormatParams
 from .output_format import OutputFormatParams, OutputFormat_Mp3Params, OutputFormat_RawParams, OutputFormat_WavParams
 from .phoneme_timestamps import PhonemeTimestampsParams
 from .raw_output_format import RawOutputFormatParams
 from .speed import SpeedParams
+from .sse_output_format import SseOutputFormatParams
 from .tts_request import TtsRequestParams
 from .tts_request_embedding_specifier import TtsRequestEmbeddingSpecifierParams
 from .tts_request_id_specifier import TtsRequestIdSpecifierParams
 from .tts_request_voice_specifier import TtsRequestVoiceSpecifierParams
+from .ttssse_request import TtssseRequestParams
 from .wav_output_format import WavOutputFormatParams
 from .web_socket_base_response import WebSocketBaseResponseParams
 from .web_socket_chunk_response import WebSocketChunkResponseParams
@@ -39,6 +43,8 @@ from .word_timestamps import WordTimestampsParams
 __all__ = [
     "CancelContextRequestParams",
     "ControlsParams",
+    "ExperimentalModelControlsParams",
+    "GenerationConfigParams",
     "GenerationRequestParams",
     "Mp3OutputFormatParams",
     "OutputFormatParams",
@@ -48,10 +54,12 @@ __all__ = [
     "PhonemeTimestampsParams",
     "RawOutputFormatParams",
     "SpeedParams",
+    "SseOutputFormatParams",
     "TtsRequestEmbeddingSpecifierParams",
     "TtsRequestIdSpecifierParams",
     "TtsRequestParams",
     "TtsRequestVoiceSpecifierParams",
+    "TtssseRequestParams",
     "WavOutputFormatParams",
     "WebSocketBaseResponseParams",
     "WebSocketChunkResponseParams",

cartesia/tts/requests/experimental_model_controls.py

@@ -0,0 +1,17 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+import typing_extensions
+
+
+class ExperimentalModelControlsParams(typing_extensions.TypedDict):
+    """
+    These controls are **experimental** and subject to breaking changes.
+    """
+
+    accent_localization: typing_extensions.NotRequired[int]
+    """
+    Toggle accent localization: 0 (disabled, default) or 1 (enabled).
+    When enabled, the voice adapts to match the transcript language's accent while preserving vocal characteristics. When disabled, maintains the original voice accent.
+    For more information, see [Localize Voices](/build-with-sonic/capabilities/localize-voices).
+    """

cartesia/tts/requests/generation_config.py

@@ -0,0 +1,23 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+import typing_extensions
+from .experimental_model_controls import ExperimentalModelControlsParams
+
+
+class GenerationConfigParams(typing_extensions.TypedDict):
+    """
+    Configure the various attributes of the generated speech. These controls are only available for `sonic-3-preview` and will have no effect on earlier models.
+    """
+
+    volume: typing_extensions.NotRequired[float]
+    """
+    Adjust the volume of the generated speech between -1.0 (softer) and 1.0 (louder). 0.0 is the default volume.
+    """
+
+    speed: typing_extensions.NotRequired[float]
+    """
+    Adjust the speed of the generated speech between -1.0 (slower) and 1.0 (faster). 0.0 is the default speed.
+    """
+
+    experimental: typing_extensions.NotRequired[ExperimentalModelControlsParams]

cartesia/tts/requests/generation_request.py

@@ -55,15 +55,15 @@ class GenerationRequestParams(typing_extensions.TypedDict):
 
     add_timestamps: typing_extensions.NotRequired[bool]
     """
-    Whether to return word-level timestamps.
+    Whether to return word-level timestamps. If `false` (default), no word timestamps will be produced at all. If `true`, the server will return timestamp events containing word-level timing information.
     """
 
     add_phoneme_timestamps: typing_extensions.NotRequired[bool]
     """
-    Whether to return phoneme-level timestamps.
+    Whether to return phoneme-level timestamps. If `false` (default), no phoneme timestamps will be produced. If `true`, the server will return timestamp events containing phoneme-level timing information.
     """
 
-    use_original_timestamps: typing_extensions.NotRequired[bool]
+    use_normalized_timestamps: typing_extensions.NotRequired[bool]
     """
-    Whether to use the original transcript for timestamps.
+    Whether to use normalized timestamps (True) or original timestamps (False).
     """

cartesia/tts/requests/sse_output_format.py

@@ -0,0 +1,11 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+import typing
+from ..types.raw_encoding import RawEncoding
+
+
+class SseOutputFormatParams(typing_extensions.TypedDict):
+    container: typing.Literal["raw"]
+    encoding: RawEncoding
+    sample_rate: int

cartesia/tts/requests/tts_request.py

@@ -6,6 +6,7 @@ import typing_extensions
 from ..types.supported_language import SupportedLanguage
 from .output_format import OutputFormatParams
 from ..types.model_speed import ModelSpeed
+from .generation_config import GenerationConfigParams
 
 
 class TtsRequestParams(typing_extensions.TypedDict):
@@ -25,3 +26,4 @@ class TtsRequestParams(typing_extensions.TypedDict):
     """
 
     speed: typing_extensions.NotRequired[ModelSpeed]
+    generation_config: typing_extensions.NotRequired[GenerationConfigParams]

cartesia/tts/requests/ttssse_request.py

@@ -0,0 +1,47 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from .tts_request_voice_specifier import TtsRequestVoiceSpecifierParams
+import typing_extensions
+from ..types.supported_language import SupportedLanguage
+from .sse_output_format import SseOutputFormatParams
+from ..types.model_speed import ModelSpeed
+from ..types.context_id import ContextId
+
+
+class TtssseRequestParams(typing_extensions.TypedDict):
+    model_id: str
+    """
+    The ID of the model to use for the generation. See [Models](/build-with-cartesia/models) for available models.
+    """
+
+    transcript: str
+    voice: TtsRequestVoiceSpecifierParams
+    language: typing_extensions.NotRequired[SupportedLanguage]
+    output_format: SseOutputFormatParams
+    duration: typing_extensions.NotRequired[float]
+    """
+    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.
+    """
+
+    speed: typing_extensions.NotRequired[ModelSpeed]
+    add_timestamps: typing_extensions.NotRequired[bool]
+    """
+    Whether to return word-level timestamps. If `false` (default), no word timestamps will be produced at all. If `true`, the server will return timestamp events containing word-level timing information.
+    """
+
+    add_phoneme_timestamps: typing_extensions.NotRequired[bool]
+    """
+    Whether to return phoneme-level timestamps. If `false` (default), no phoneme timestamps will be produced - if `add_timestamps` is `true`, the produced timestamps will be word timestamps instead. If `true`, the server will return timestamp events containing phoneme-level timing information.
+    """
+
+    use_normalized_timestamps: typing_extensions.NotRequired[bool]
+    """
+    Whether to use normalized timestamps (True) or original timestamps (False).
+    """
+
+    context_id: typing_extensions.NotRequired[ContextId]
+    """
+    Optional context ID for this request.
+    """

cartesia/tts/requests/web_socket_chunk_response.py

@@ -1,11 +1,8 @@
 # This file was auto-generated by Fern from our API Definition.
 
 from .web_socket_base_response import WebSocketBaseResponseParams
-import typing_extensions
-from ..types.flush_id import FlushId
 
 
 class WebSocketChunkResponseParams(WebSocketBaseResponseParams):
     data: str
     step_time: float
-    flush_id: typing_extensions.NotRequired[FlushId]

cartesia/tts/requests/web_socket_response.py

@@ -4,8 +4,8 @@ from __future__ import annotations
 import typing_extensions
 import typing
 import typing_extensions
-from ..types.flush_id import FlushId
 from ..types.context_id import ContextId
+from ..types.flush_id import FlushId
 from .word_timestamps import WordTimestampsParams
 from .phoneme_timestamps import PhonemeTimestampsParams
 
@@ -14,7 +14,6 @@ class WebSocketResponse_ChunkParams(typing_extensions.TypedDict):
     type: typing.Literal["chunk"]
     data: str
     step_time: float
-    flush_id: typing_extensions.NotRequired[FlushId]
     context_id: typing_extensions.NotRequired[ContextId]
     status_code: int
     done: bool

cartesia/tts/requests/web_socket_tts_request.py

@@ -20,8 +20,16 @@ class WebSocketTtsRequestParams(typing_extensions.TypedDict):
     duration: typing_extensions.NotRequired[int]
     language: typing_extensions.NotRequired[str]
     add_timestamps: typing_extensions.NotRequired[bool]
-    use_original_timestamps: typing_extensions.NotRequired[bool]
+    """
+    Whether to return word-level timestamps. If `false` (default), no word timestamps will be produced at all. If `true`, the server will return timestamp events containing word-level timing information.
+    """
+
     add_phoneme_timestamps: typing_extensions.NotRequired[bool]
+    """
+    Whether to return phoneme-level timestamps. If `false` (default), no phoneme timestamps will be produced - if `add_timestamps` is `true`, the produced timestamps will be word timestamps instead. If `true`, the server will return timestamp events containing phoneme-level timing information.
+    """
+
+    use_normalized_timestamps: typing_extensions.NotRequired[bool]
     continue_: typing_extensions.NotRequired[typing_extensions.Annotated[bool, FieldMetadata(alias="continue")]]
     context_id: typing_extensions.NotRequired[str]
     max_buffer_delay_ms: typing_extensions.NotRequired[int]

cartesia/tts/types/__init__.py

@@ -4,7 +4,9 @@ from .cancel_context_request import CancelContextRequest
 from .context_id import ContextId
 from .controls import Controls
 from .emotion import Emotion
+from .experimental_model_controls import ExperimentalModelControls
 from .flush_id import FlushId
+from .generation_config import GenerationConfig
 from .generation_request import GenerationRequest
 from .model_speed import ModelSpeed
 from .mp_3_output_format import Mp3OutputFormat
@@ -15,11 +17,13 @@ from .phoneme_timestamps import PhonemeTimestamps
 from .raw_encoding import RawEncoding
 from .raw_output_format import RawOutputFormat
 from .speed import Speed
+from .sse_output_format import SseOutputFormat
 from .supported_language import SupportedLanguage
 from .tts_request import TtsRequest
 from .tts_request_embedding_specifier import TtsRequestEmbeddingSpecifier
 from .tts_request_id_specifier import TtsRequestIdSpecifier
 from .tts_request_voice_specifier import TtsRequestVoiceSpecifier
+from .ttssse_request import TtssseRequest
 from .wav_output_format import WavOutputFormat
 from .web_socket_base_response import WebSocketBaseResponse
 from .web_socket_chunk_response import WebSocketChunkResponse
@@ -49,7 +53,9 @@ __all__ = [
     "ContextId",
     "Controls",
     "Emotion",
+    "ExperimentalModelControls",
     "FlushId",
+    "GenerationConfig",
     "GenerationRequest",
     "ModelSpeed",
     "Mp3OutputFormat",
@@ -63,11 +69,13 @@ __all__ = [
     "RawEncoding",
     "RawOutputFormat",
     "Speed",
+    "SseOutputFormat",
     "SupportedLanguage",
     "TtsRequest",
     "TtsRequestEmbeddingSpecifier",
     "TtsRequestIdSpecifier",
     "TtsRequestVoiceSpecifier",
+    "TtssseRequest",
     "WavOutputFormat",
     "WebSocketBaseResponse",
     "WebSocketChunkResponse",

cartesia/tts/types/experimental_model_controls.py

@@ -0,0 +1,28 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+import typing
+import pydantic
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+
+
+class ExperimentalModelControls(UniversalBaseModel):
+    """
+    These controls are **experimental** and subject to breaking changes.
+    """
+
+    accent_localization: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Toggle accent localization: 0 (disabled, default) or 1 (enabled).
+    When enabled, the voice adapts to match the transcript language's accent while preserving vocal characteristics. When disabled, maintains the original voice accent.
+    For more information, see [Localize Voices](/build-with-sonic/capabilities/localize-voices).
+    """
+
+    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/generation_config.py

@@ -0,0 +1,34 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ...core.pydantic_utilities import UniversalBaseModel
+import typing
+import pydantic
+from .experimental_model_controls import ExperimentalModelControls
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+
+
+class GenerationConfig(UniversalBaseModel):
+    """
+    Configure the various attributes of the generated speech. These controls are only available for `sonic-3-preview` and will have no effect on earlier models.
+    """
+
+    volume: typing.Optional[float] = pydantic.Field(default=None)
+    """
+    Adjust the volume of the generated speech between -1.0 (softer) and 1.0 (louder). 0.0 is the default volume.
+    """
+
+    speed: typing.Optional[float] = pydantic.Field(default=None)
+    """
+    Adjust the speed of the generated speech between -1.0 (slower) and 1.0 (faster). 0.0 is the default speed.
+    """
+
+    experimental: typing.Optional[ExperimentalModelControls] = 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/generation_request.py

@@ -59,17 +59,17 @@ class GenerationRequest(UniversalBaseModel):
 
     add_timestamps: typing.Optional[bool] = pydantic.Field(default=None)
     """
-    Whether to return word-level timestamps.
+    Whether to return word-level timestamps. If `false` (default), no word timestamps will be produced at all. If `true`, the server will return timestamp events containing word-level timing information.
     """
 
     add_phoneme_timestamps: typing.Optional[bool] = pydantic.Field(default=None)
     """
-    Whether to return phoneme-level timestamps.
+    Whether to return phoneme-level timestamps. If `false` (default), no phoneme timestamps will be produced. If `true`, the server will return timestamp events containing phoneme-level timing information.
     """
 
-    use_original_timestamps: typing.Optional[bool] = pydantic.Field(default=None)
+    use_normalized_timestamps: typing.Optional[bool] = pydantic.Field(default=None)
     """
-    Whether to use the original transcript for timestamps.
+    Whether to use normalized timestamps (True) or original timestamps (False).
     """
 
     if IS_PYDANTIC_V2:

cartesia/tts/types/sse_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 SseOutputFormat(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/tts_request.py

@@ -7,6 +7,7 @@ import typing
 from .supported_language import SupportedLanguage
 from .output_format import OutputFormat
 from .model_speed import ModelSpeed
+from .generation_config import GenerationConfig
 from ...core.pydantic_utilities import IS_PYDANTIC_V2
 
 
@@ -27,6 +28,7 @@ class TtsRequest(UniversalBaseModel):
     """
 
     speed: typing.Optional[ModelSpeed] = None
+    generation_config: typing.Optional[GenerationConfig] = None
 
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2

cartesia/tts/types/ttssse_request.py

@@ -0,0 +1,58 @@
+# 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 .sse_output_format import SseOutputFormat
+from .model_speed import ModelSpeed
+from .context_id import ContextId
+from ...core.pydantic_utilities import IS_PYDANTIC_V2
+
+
+class TtssseRequest(UniversalBaseModel):
+    model_id: str = pydantic.Field()
+    """
+    The ID of the model to use for the generation. See [Models](/build-with-cartesia/models) for available models.
+    """
+
+    transcript: str
+    voice: TtsRequestVoiceSpecifier
+    language: typing.Optional[SupportedLanguage] = None
+    output_format: SseOutputFormat
+    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.
+    """
+
+    speed: typing.Optional[ModelSpeed] = None
+    add_timestamps: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Whether to return word-level timestamps. If `false` (default), no word timestamps will be produced at all. If `true`, the server will return timestamp events containing word-level timing information.
+    """
+
+    add_phoneme_timestamps: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Whether to return phoneme-level timestamps. If `false` (default), no phoneme timestamps will be produced - if `add_timestamps` is `true`, the produced timestamps will be word timestamps instead. If `true`, the server will return timestamp events containing phoneme-level timing information.
+    """
+
+    use_normalized_timestamps: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Whether to use normalized timestamps (True) or original timestamps (False).
+    """
+
+    context_id: typing.Optional[ContextId] = pydantic.Field(default=None)
+    """
+    Optional context ID for this request.
+    """
+
+    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

@@ -1,16 +1,14 @@
 # This file was auto-generated by Fern from our API Definition.
 
 from .web_socket_base_response import WebSocketBaseResponse
-import typing
-from .flush_id import FlushId
 from ...core.pydantic_utilities import IS_PYDANTIC_V2
+import typing
 import pydantic
 
 
 class WebSocketChunkResponse(WebSocketBaseResponse):
     data: str
     step_time: float
-    flush_id: typing.Optional[FlushId] = None
 
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2

cartesia/tts/types/web_socket_response.py

@@ -3,10 +3,10 @@
 from __future__ import annotations
 from ...core.pydantic_utilities import UniversalBaseModel
 import typing
-from .flush_id import FlushId
 from .context_id import ContextId
 from ...core.pydantic_utilities import IS_PYDANTIC_V2
 import pydantic
+from .flush_id import FlushId
 from .word_timestamps import WordTimestamps
 from .phoneme_timestamps import PhonemeTimestamps
 
@@ -15,7 +15,6 @@ class WebSocketResponse_Chunk(UniversalBaseModel):
     type: typing.Literal["chunk"] = "chunk"
     data: str
     step_time: float
-    flush_id: typing.Optional[FlushId] = None
     context_id: typing.Optional[ContextId] = None
     status_code: int
     done: bool

cartesia/tts/types/web_socket_tts_request.py

@@ -22,9 +22,17 @@ class WebSocketTtsRequest(UniversalBaseModel):
     voice: TtsRequestVoiceSpecifier
     duration: typing.Optional[int] = None
     language: typing.Optional[str] = None
-    add_timestamps: typing.Optional[bool] = None
-    use_original_timestamps: typing.Optional[bool] = None
-    add_phoneme_timestamps: typing.Optional[bool] = None
+    add_timestamps: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Whether to return word-level timestamps. If `false` (default), no word timestamps will be produced at all. If `true`, the server will return timestamp events containing word-level timing information.
+    """
+
+    add_phoneme_timestamps: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Whether to return phoneme-level timestamps. If `false` (default), no phoneme timestamps will be produced - if `add_timestamps` is `true`, the produced timestamps will be word timestamps instead. If `true`, the server will return timestamp events containing phoneme-level timing information.
+    """
+
+    use_normalized_timestamps: typing.Optional[bool] = None
     continue_: typing_extensions.Annotated[typing.Optional[bool], FieldMetadata(alias="continue")] = None
     context_id: typing.Optional[str] = None
     max_buffer_delay_ms: typing.Optional[int] = None

cartesia/voice_changer/client.py

@@ -51,11 +51,9 @@ class VoiceChangerClient:
         output_format_encoding : typing.Optional[RawEncoding]
             Required for `raw` and `wav` containers.
 
-
         output_format_bit_rate : typing.Optional[int]
             Required for `mp3` containers.
 
-
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response.
 
@@ -131,11 +129,9 @@ class VoiceChangerClient:
         output_format_encoding : typing.Optional[RawEncoding]
             Required for `raw` and `wav` containers.
 
-
         output_format_bit_rate : typing.Optional[int]
             Required for `mp3` containers.
 
-
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -232,11 +228,9 @@ class AsyncVoiceChangerClient:
         output_format_encoding : typing.Optional[RawEncoding]
             Required for `raw` and `wav` containers.
 
-
         output_format_bit_rate : typing.Optional[int]
             Required for `mp3` containers.
 
-
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response.
 
@@ -320,11 +314,9 @@ class AsyncVoiceChangerClient:
         output_format_encoding : typing.Optional[RawEncoding]
             Required for `raw` and `wav` containers.
 
-
         output_format_bit_rate : typing.Optional[int]
             Required for `mp3` containers.
 
-
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 

cartesia/voice_changer/requests/streaming_response.py

@@ -4,7 +4,6 @@ from __future__ import annotations
 import typing_extensions
 import typing
 import typing_extensions
-from ...tts.types.flush_id import FlushId
 from ...tts.types.context_id import ContextId
 
 
@@ -12,7 +11,6 @@ class StreamingResponse_ChunkParams(typing_extensions.TypedDict):
     type: typing.Literal["chunk"]
     data: str
     step_time: float
-    flush_id: typing_extensions.NotRequired[FlushId]
     context_id: typing_extensions.NotRequired[ContextId]
     status_code: int
     done: bool

cartesia/voice_changer/types/streaming_response.py

@@ -3,7 +3,6 @@
 from __future__ import annotations
 from ...core.pydantic_utilities import UniversalBaseModel
 import typing
-from ...tts.types.flush_id import FlushId
 from ...tts.types.context_id import ContextId
 from ...core.pydantic_utilities import IS_PYDANTIC_V2
 import pydantic
@@ -13,7 +12,6 @@ class StreamingResponse_Chunk(UniversalBaseModel):
     type: typing.Literal["chunk"] = "chunk"
     data: str
     step_time: float
-    flush_id: typing.Optional[FlushId] = None
     context_id: typing.Optional[ContextId] = None
     status_code: int
     done: bool

cartesia/voices/client.py

@@ -168,27 +168,21 @@ class VoicesClient:
         name : str
             The name of the voice.
 
-
         language : SupportedLanguage
             The language of the voice.
 
-
         mode : CloneMode
             Tradeoff between similarity and stability. Similarity clones sound more like the source clip, but may reproduce background noise. Stability clones always sound like a studio recording, but may not sound as similar to the source clip.
 
-
         description : typing.Optional[str]
             A description for the voice.
 
-
         enhance : typing.Optional[bool]
             Whether to apply AI enhancements to the clip to reduce background noise. This leads to cleaner generated speech at the cost of reduced similarity to the source clip.
 
-
         base_voice_id : typing.Optional[VoiceId]
             Optional base voice ID that the cloned voice is derived from.
 
-
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -736,27 +730,21 @@ class AsyncVoicesClient:
         name : str
             The name of the voice.
 
-
         language : SupportedLanguage
             The language of the voice.
 
-
         mode : CloneMode
             Tradeoff between similarity and stability. Similarity clones sound more like the source clip, but may reproduce background noise. Stability clones always sound like a studio recording, but may not sound as similar to the source clip.
 
-
         description : typing.Optional[str]
             A description for the voice.
 
-
         enhance : typing.Optional[bool]
             Whether to apply AI enhancements to the clip to reduce background noise. This leads to cleaner generated speech at the cost of reduced similarity to the source clip.
 
-
         base_voice_id : typing.Optional[VoiceId]
             Optional base voice ID that the cloned voice is derived from.
 
-
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.