cartesia 2.0.0b2__py3-none-any.whl → 2.0.0b8__py3-none-any.whl

cartesia/tts/types/web_socket_tts_output.py

@@ -7,11 +7,13 @@ import pydantic
 from ...core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
 from .context_id import ContextId
 from .flush_id import FlushId
+from .phoneme_timestamps import PhonemeTimestamps
 from .word_timestamps import WordTimestamps
 
 
 class WebSocketTtsOutput(UniversalBaseModel):
     word_timestamps: typing.Optional[WordTimestamps] = None
+    phoneme_timestamps: typing.Optional[PhonemeTimestamps] = None
     audio: typing.Optional[bytes] = None
     context_id: typing.Optional[ContextId] = None
     flush_id: typing.Optional[FlushId] = None

cartesia/tts/types/web_socket_tts_request.py

@@ -22,6 +22,7 @@ class WebSocketTtsRequest(UniversalBaseModel):
     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
     continue_: typing_extensions.Annotated[typing.Optional[bool], FieldMetadata(alias="continue")] = None
     context_id: typing.Optional[str] = None

cartesia/tts/utils/constants.py

@@ -1,5 +1,5 @@
-DEFAULT_MODEL_ID = "sonic-english"  # latest default model
-MULTILINGUAL_MODEL_ID = "sonic-multilingual"  # latest multilingual model
+DEFAULT_MODEL_ID = "sonic-2"  # latest default model
+MULTILINGUAL_MODEL_ID = "sonic-2"  # latest multilingual model
 DEFAULT_BASE_URL = "api.cartesia.ai"
 DEFAULT_CARTESIA_VERSION = "2024-06-10"  # latest version
 DEFAULT_OUTPUT_FORMAT = "raw_pcm_f32le_44100"

cartesia/voice_changer/requests/streaming_response.py

@@ -4,6 +4,7 @@ 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
 
 
@@ -11,6 +12,7 @@ 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

@@ -3,6 +3,7 @@
 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
@@ -12,6 +13,7 @@ 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/__init__.py

@@ -7,9 +7,12 @@ from .types import (
     EmbeddingResponse,
     EmbeddingSpecifier,
     Gender,
+    GenderPresentation,
+    GetVoicesResponse,
     IdSpecifier,
     LocalizeDialect,
     LocalizeEnglishDialect,
+    LocalizeFrenchDialect,
     LocalizePortugueseDialect,
     LocalizeSpanishDialect,
     LocalizeTargetLanguage,
@@ -18,6 +21,7 @@ from .types import (
     MixVoicesRequest,
     UpdateVoiceRequest,
     Voice,
+    VoiceExpandOptions,
     VoiceId,
     VoiceMetadata,
     Weight,
@@ -26,6 +30,7 @@ from .requests import (
     CreateVoiceRequestParams,
     EmbeddingResponseParams,
     EmbeddingSpecifierParams,
+    GetVoicesResponseParams,
     IdSpecifierParams,
     LocalizeDialectParams,
     LocalizeVoiceRequestParams,
@@ -46,11 +51,15 @@ __all__ = [
     "EmbeddingSpecifier",
     "EmbeddingSpecifierParams",
     "Gender",
+    "GenderPresentation",
+    "GetVoicesResponse",
+    "GetVoicesResponseParams",
     "IdSpecifier",
     "IdSpecifierParams",
     "LocalizeDialect",
     "LocalizeDialectParams",
     "LocalizeEnglishDialect",
+    "LocalizeFrenchDialect",
     "LocalizePortugueseDialect",
     "LocalizeSpanishDialect",
     "LocalizeTargetLanguage",
@@ -63,6 +72,7 @@ __all__ = [
     "UpdateVoiceRequest",
     "UpdateVoiceRequestParams",
     "Voice",
+    "VoiceExpandOptions",
     "VoiceId",
     "VoiceMetadata",
     "VoiceMetadataParams",

cartesia/voices/client.py

@@ -2,8 +2,12 @@
 
 import typing
 from ..core.client_wrapper import SyncClientWrapper
+from .types.gender_presentation import GenderPresentation
+from .types.voice_expand_options import VoiceExpandOptions
 from ..core.request_options import RequestOptions
+from ..core.pagination import SyncPager
 from .types.voice import Voice
+from .types.get_voices_response import GetVoicesResponse
 from ..core.pydantic_utilities import parse_obj_as
 from json.decoder import JSONDecodeError
 from ..core.api_error import ApiError
@@ -13,15 +17,16 @@ from .types.clone_mode import CloneMode
 from .types.voice_metadata import VoiceMetadata
 from .types.voice_id import VoiceId
 from ..core.jsonable_encoder import jsonable_encoder
-from ..embedding.types.embedding import Embedding
 from .types.localize_target_language import LocalizeTargetLanguage
 from .types.gender import Gender
 from .requests.localize_dialect import LocalizeDialectParams
-from .types.embedding_response import EmbeddingResponse
 from ..core.serialization import convert_and_respect_annotation_metadata
 from .requests.mix_voice_specifier import MixVoiceSpecifierParams
+from .types.embedding_response import EmbeddingResponse
+from ..embedding.types.embedding import Embedding
 from .types.base_voice_id import BaseVoiceId
 from ..core.client_wrapper import AsyncClientWrapper
+from ..core.pagination import AsyncPager
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -31,16 +36,54 @@ class VoicesClient:
     def __init__(self, *, client_wrapper: SyncClientWrapper):
         self._client_wrapper = client_wrapper
 
-    def list(self, *, request_options: typing.Optional[RequestOptions] = None) -> typing.List[Voice]:
+    def list(
+        self,
+        *,
+        limit: typing.Optional[int] = None,
+        starting_after: typing.Optional[str] = None,
+        ending_before: typing.Optional[str] = None,
+        is_owner: typing.Optional[bool] = None,
+        is_starred: typing.Optional[bool] = None,
+        gender: typing.Optional[GenderPresentation] = None,
+        expand: typing.Optional[typing.Sequence[VoiceExpandOptions]] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> SyncPager[Voice]:
         """
         Parameters
         ----------
+        limit : typing.Optional[int]
+            The number of Voices to return per page, ranging between 1 and 100.
+
+        starting_after : typing.Optional[str]
+            A cursor to use in pagination. `starting_after` is a Voice ID that defines your
+            place in the list. For example, if you make a /voices request and receive 100
+            objects, ending with `voice_abc123`, your subsequent call can include
+            `starting_after=voice_abc123` to fetch the next page of the list.
+
+        ending_before : typing.Optional[str]
+            A cursor to use in pagination. `ending_before` is a Voice ID that defines your
+            place in the list. For example, if you make a /voices request and receive 100
+            objects, starting with `voice_abc123`, your subsequent call can include
+            `ending_before=voice_abc123` to fetch the previous page of the list.
+
+        is_owner : typing.Optional[bool]
+            Whether to only return voices owned by the current user.
+
+        is_starred : typing.Optional[bool]
+            Whether to only return starred voices.
+
+        gender : typing.Optional[GenderPresentation]
+            The gender presentation of the voices to return.
+
+        expand : typing.Optional[typing.Sequence[VoiceExpandOptions]]
+            Additional fields to include in the response.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
         Returns
         -------
-        typing.List[Voice]
+        SyncPager[Voice]
 
         Examples
         --------
@@ -49,22 +92,50 @@ class VoicesClient:
         client = Cartesia(
             api_key="YOUR_API_KEY",
         )
-        client.voices.list()
+        response = client.voices.list()
+        for item in response:
+            yield item
+        # alternatively, you can paginate page-by-page
+        for page in response.iter_pages():
+            yield page
         """
         _response = self._client_wrapper.httpx_client.request(
             "voices/",
             method="GET",
+            params={
+                "limit": limit,
+                "starting_after": starting_after,
+                "ending_before": ending_before,
+                "is_owner": is_owner,
+                "is_starred": is_starred,
+                "gender": gender,
+                "expand[]": expand,
+            },
             request_options=request_options,
         )
         try:
             if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    typing.List[Voice],
+                _parsed_response = typing.cast(
+                    GetVoicesResponse,
                     parse_obj_as(
-                        type_=typing.List[Voice],  # type: ignore
+                        type_=GetVoicesResponse,  # type: ignore
                         object_=_response.json(),
                     ),
                 )
+                _parsed_next = _parsed_response.next_page
+                _has_next = _parsed_next is not None and _parsed_next != ""
+                _get_next = lambda: self.list(
+                    limit=limit,
+                    starting_after=_parsed_next,
+                    ending_before=ending_before,
+                    is_owner=is_owner,
+                    is_starred=is_starred,
+                    gender=gender,
+                    expand=expand,
+                    request_options=request_options,
+                )
+                _items = _parsed_response.data
+                return SyncPager(has_next=_has_next, items=_items, get_next=_get_next)
             _response_json = _response.json()
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
@@ -312,16 +383,27 @@ class VoicesClient:
     def localize(
         self,
         *,
-        embedding: Embedding,
+        voice_id: str,
+        name: str,
+        description: str,
         language: LocalizeTargetLanguage,
         original_speaker_gender: Gender,
         dialect: typing.Optional[LocalizeDialectParams] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
-    ) -> EmbeddingResponse:
+    ) -> VoiceMetadata:
         """
+        Create a new voice from an existing voice localized to a new language and dialect.
+
         Parameters
         ----------
-        embedding : Embedding
+        voice_id : str
+            The ID of the voice to localize.
+
+        name : str
+            The name of the new localized voice.
+
+        description : str
+            The description of the new localized voice.
 
         language : LocalizeTargetLanguage
 
@@ -334,7 +416,7 @@ class VoicesClient:
 
         Returns
         -------
-        EmbeddingResponse
+        VoiceMetadata
 
         Examples
         --------
@@ -344,16 +426,21 @@ class VoicesClient:
             api_key="YOUR_API_KEY",
         )
         client.voices.localize(
-            embedding=[1.1, 1.1],
-            language="en",
-            original_speaker_gender="male",
+            voice_id="694f9389-aac1-45b6-b726-9d9369183238",
+            name="Sarah Peninsular Spanish",
+            description="Sarah Voice in Peninsular Spanish",
+            language="es",
+            original_speaker_gender="female",
+            dialect="pe",
         )
         """
         _response = self._client_wrapper.httpx_client.request(
             "voices/localize",
             method="POST",
             json={
-                "embedding": embedding,
+                "voice_id": voice_id,
+                "name": name,
+                "description": description,
                 "language": language,
                 "original_speaker_gender": original_speaker_gender,
                 "dialect": convert_and_respect_annotation_metadata(
@@ -366,9 +453,9 @@ class VoicesClient:
         try:
             if 200 <= _response.status_code < 300:
                 return typing.cast(
-                    EmbeddingResponse,
+                    VoiceMetadata,
                     parse_obj_as(
-                        type_=EmbeddingResponse,  # type: ignore
+                        type_=VoiceMetadata,  # type: ignore
                         object_=_response.json(),
                     ),
                 )
@@ -473,11 +560,9 @@ class VoicesClient:
             api_key="YOUR_API_KEY",
         )
         client.voices.create(
-            name="My Custom Voice",
-            description="A custom voice created through the API",
-            embedding=[],
-            language="en",
-            base_voice_id="123e4567-e89b-12d3-a456-426614174000",
+            name="name",
+            description="description",
+            embedding=[1.1, 1.1],
         )
         """
         _response = self._client_wrapper.httpx_client.request(
@@ -512,16 +597,54 @@ class AsyncVoicesClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
         self._client_wrapper = client_wrapper
 
-    async def list(self, *, request_options: typing.Optional[RequestOptions] = None) -> typing.List[Voice]:
+    async def list(
+        self,
+        *,
+        limit: typing.Optional[int] = None,
+        starting_after: typing.Optional[str] = None,
+        ending_before: typing.Optional[str] = None,
+        is_owner: typing.Optional[bool] = None,
+        is_starred: typing.Optional[bool] = None,
+        gender: typing.Optional[GenderPresentation] = None,
+        expand: typing.Optional[typing.Sequence[VoiceExpandOptions]] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncPager[Voice]:
         """
         Parameters
         ----------
+        limit : typing.Optional[int]
+            The number of Voices to return per page, ranging between 1 and 100.
+
+        starting_after : typing.Optional[str]
+            A cursor to use in pagination. `starting_after` is a Voice ID that defines your
+            place in the list. For example, if you make a /voices request and receive 100
+            objects, ending with `voice_abc123`, your subsequent call can include
+            `starting_after=voice_abc123` to fetch the next page of the list.
+
+        ending_before : typing.Optional[str]
+            A cursor to use in pagination. `ending_before` is a Voice ID that defines your
+            place in the list. For example, if you make a /voices request and receive 100
+            objects, starting with `voice_abc123`, your subsequent call can include
+            `ending_before=voice_abc123` to fetch the previous page of the list.
+
+        is_owner : typing.Optional[bool]
+            Whether to only return voices owned by the current user.
+
+        is_starred : typing.Optional[bool]
+            Whether to only return starred voices.
+
+        gender : typing.Optional[GenderPresentation]
+            The gender presentation of the voices to return.
+
+        expand : typing.Optional[typing.Sequence[VoiceExpandOptions]]
+            Additional fields to include in the response.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
         Returns
         -------
-        typing.List[Voice]
+        AsyncPager[Voice]
 
         Examples
         --------
@@ -535,7 +658,12 @@ class AsyncVoicesClient:
 
 
         async def main() -> None:
-            await client.voices.list()
+            response = await client.voices.list()
+            async for item in response:
+                yield item
+            # alternatively, you can paginate page-by-page
+            async for page in response.iter_pages():
+                yield page
 
 
         asyncio.run(main())
@@ -543,17 +671,40 @@ class AsyncVoicesClient:
         _response = await self._client_wrapper.httpx_client.request(
             "voices/",
             method="GET",
+            params={
+                "limit": limit,
+                "starting_after": starting_after,
+                "ending_before": ending_before,
+                "is_owner": is_owner,
+                "is_starred": is_starred,
+                "gender": gender,
+                "expand[]": expand,
+            },
             request_options=request_options,
         )
         try:
             if 200 <= _response.status_code < 300:
-                return typing.cast(
-                    typing.List[Voice],
+                _parsed_response = typing.cast(
+                    GetVoicesResponse,
                     parse_obj_as(
-                        type_=typing.List[Voice],  # type: ignore
+                        type_=GetVoicesResponse,  # type: ignore
                         object_=_response.json(),
                     ),
                 )
+                _parsed_next = _parsed_response.next_page
+                _has_next = _parsed_next is not None and _parsed_next != ""
+                _get_next = lambda: self.list(
+                    limit=limit,
+                    starting_after=_parsed_next,
+                    ending_before=ending_before,
+                    is_owner=is_owner,
+                    is_starred=is_starred,
+                    gender=gender,
+                    expand=expand,
+                    request_options=request_options,
+                )
+                _items = _parsed_response.data
+                return AsyncPager(has_next=_has_next, items=_items, get_next=_get_next)
             _response_json = _response.json()
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
@@ -833,16 +984,27 @@ class AsyncVoicesClient:
     async def localize(
         self,
         *,
-        embedding: Embedding,
+        voice_id: str,
+        name: str,
+        description: str,
         language: LocalizeTargetLanguage,
         original_speaker_gender: Gender,
         dialect: typing.Optional[LocalizeDialectParams] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
-    ) -> EmbeddingResponse:
+    ) -> VoiceMetadata:
         """
+        Create a new voice from an existing voice localized to a new language and dialect.
+
         Parameters
         ----------
-        embedding : Embedding
+        voice_id : str
+            The ID of the voice to localize.
+
+        name : str
+            The name of the new localized voice.
+
+        description : str
+            The description of the new localized voice.
 
         language : LocalizeTargetLanguage
 
@@ -855,7 +1017,7 @@ class AsyncVoicesClient:
 
         Returns
         -------
-        EmbeddingResponse
+        VoiceMetadata
 
         Examples
         --------
@@ -870,9 +1032,12 @@ class AsyncVoicesClient:
 
         async def main() -> None:
             await client.voices.localize(
-                embedding=[1.1, 1.1],
-                language="en",
-                original_speaker_gender="male",
+                voice_id="694f9389-aac1-45b6-b726-9d9369183238",
+                name="Sarah Peninsular Spanish",
+                description="Sarah Voice in Peninsular Spanish",
+                language="es",
+                original_speaker_gender="female",
+                dialect="pe",
             )
 
 
@@ -882,7 +1047,9 @@ class AsyncVoicesClient:
             "voices/localize",
             method="POST",
             json={
-                "embedding": embedding,
+                "voice_id": voice_id,
+                "name": name,
+                "description": description,
                 "language": language,
                 "original_speaker_gender": original_speaker_gender,
                 "dialect": convert_and_respect_annotation_metadata(
@@ -895,9 +1062,9 @@ class AsyncVoicesClient:
         try:
             if 200 <= _response.status_code < 300:
                 return typing.cast(
-                    EmbeddingResponse,
+                    VoiceMetadata,
                     parse_obj_as(
-                        type_=EmbeddingResponse,  # type: ignore
+                        type_=VoiceMetadata,  # type: ignore
                         object_=_response.json(),
                     ),
                 )
@@ -1015,11 +1182,9 @@ class AsyncVoicesClient:
 
         async def main() -> None:
             await client.voices.create(
-                name="My Custom Voice",
-                description="A custom voice created through the API",
-                embedding=[],
-                language="en",
-                base_voice_id="123e4567-e89b-12d3-a456-426614174000",
+                name="name",
+                description="description",
+                embedding=[1.1, 1.1],
             )
 
 

cartesia/voices/requests/__init__.py

@@ -3,6 +3,7 @@
 from .create_voice_request import CreateVoiceRequestParams
 from .embedding_response import EmbeddingResponseParams
 from .embedding_specifier import EmbeddingSpecifierParams
+from .get_voices_response import GetVoicesResponseParams
 from .id_specifier import IdSpecifierParams
 from .localize_dialect import LocalizeDialectParams
 from .localize_voice_request import LocalizeVoiceRequestParams
@@ -16,6 +17,7 @@ __all__ = [
     "CreateVoiceRequestParams",
     "EmbeddingResponseParams",
     "EmbeddingSpecifierParams",
+    "GetVoicesResponseParams",
     "IdSpecifierParams",
     "LocalizeDialectParams",
     "LocalizeVoiceRequestParams",

cartesia/voices/requests/get_voices_response.py

@@ -0,0 +1,24 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+import typing
+from .voice import VoiceParams
+import typing_extensions
+from ..types.voice_id import VoiceId
+
+
+class GetVoicesResponseParams(typing_extensions.TypedDict):
+    data: typing.Sequence[VoiceParams]
+    """
+    The paginated list of Voices.
+    """
+
+    has_more: bool
+    """
+    Whether there are more Voices to fetch (using `starting_after=id`, where id is the ID of the last Voice in the current response).
+    """
+
+    next_page: typing_extensions.NotRequired[VoiceId]
+    """
+    (Deprecated - use the id of the last Voice in the current response instead.) An ID that can be passed as `starting_after` to get the next page of Voices.
+    """

cartesia/voices/requests/localize_dialect.py

@@ -4,5 +4,8 @@ import typing
 from ..types.localize_english_dialect import LocalizeEnglishDialect
 from ..types.localize_spanish_dialect import LocalizeSpanishDialect
 from ..types.localize_portuguese_dialect import LocalizePortugueseDialect
+from ..types.localize_french_dialect import LocalizeFrenchDialect
 
-LocalizeDialectParams = typing.Union[LocalizeEnglishDialect, LocalizeSpanishDialect, LocalizePortugueseDialect]
+LocalizeDialectParams = typing.Union[
+    LocalizeEnglishDialect, LocalizeSpanishDialect, LocalizePortugueseDialect, LocalizeFrenchDialect
+]

cartesia/voices/requests/localize_voice_request.py

@@ -1,7 +1,6 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing_extensions
-from ...embedding.types.embedding import Embedding
 from ..types.localize_target_language import LocalizeTargetLanguage
 from ..types.gender import Gender
 import typing_extensions
@@ -9,7 +8,21 @@ from .localize_dialect import LocalizeDialectParams
 
 
 class LocalizeVoiceRequestParams(typing_extensions.TypedDict):
-    embedding: Embedding
+    voice_id: str
+    """
+    The ID of the voice to localize.
+    """
+
+    name: str
+    """
+    The name of the new localized voice.
+    """
+
+    description: str
+    """
+    The description of the new localized voice.
+    """
+
     language: LocalizeTargetLanguage
     original_speaker_gender: Gender
     dialect: typing_extensions.NotRequired[LocalizeDialectParams]

cartesia/voices/requests/voice.py

@@ -2,22 +2,17 @@
 
 import typing_extensions
 from ..types.voice_id import VoiceId
-import typing_extensions
 import datetime as dt
+import typing_extensions
 from ...embedding.types.embedding import Embedding
 from ...tts.types.supported_language import SupportedLanguage
 
 
 class VoiceParams(typing_extensions.TypedDict):
     id: VoiceId
-    user_id: typing_extensions.NotRequired[str]
-    """
-    The ID of the user who owns the voice.
+    is_owner: bool
     """
-
-    is_public: bool
-    """
-    Whether the voice is publicly accessible.
+    Whether the current user is the owner of the voice.
     """
 
     name: str
@@ -35,5 +30,14 @@ class VoiceParams(typing_extensions.TypedDict):
     The date and time the voice was created.
     """
 
-    embedding: Embedding
+    embedding: typing_extensions.NotRequired[Embedding]
+    """
+    The vector embedding of the voice. Only included when `expand` includes `embedding`.
+    """
+
+    is_starred: typing_extensions.NotRequired[bool]
+    """
+    Whether the current user has starred the voice. Only included when `expand` includes `is_starred`.
+    """
+
     language: SupportedLanguage