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

cartesia/voices/client.py

@@ -0,0 +1,1812 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+from ..core.client_wrapper import SyncClientWrapper
+from ..core.request_options import RequestOptions
+from .types.voice import Voice
+from ..core.pydantic_utilities import parse_obj_as
+from json.decoder import JSONDecodeError
+from ..core.api_error import ApiError
+from ..embedding.types.embedding import Embedding
+from ..tts.types.supported_language import SupportedLanguage
+from .types.voice_id import VoiceId
+from ..core.jsonable_encoder import jsonable_encoder
+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 .. import core
+from .types.clone_mode import CloneMode
+from .types.voice_metadata import VoiceMetadata
+from ..core.client_wrapper import AsyncClientWrapper
+
+# this is used as the default value for optional parameters
+OMIT = typing.cast(typing.Any, ...)
+
+
+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]:
+        """
+        Parameters
+        ----------
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        typing.List[Voice]
+
+        Examples
+        --------
+        from cartesia import Cartesia
+
+        client = Cartesia(
+            api_key="YOUR_API_KEY",
+        )
+        client.voices.list()
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "voices/",
+            method="GET",
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    typing.List[Voice],
+                    parse_obj_as(
+                        type_=typing.List[Voice],  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def create(
+        self,
+        *,
+        name: str,
+        description: str,
+        embedding: Embedding,
+        language: typing.Optional[SupportedLanguage] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> Voice:
+        """
+        Parameters
+        ----------
+        name : str
+            The name of the voice.
+
+        description : str
+            The description of the voice.
+
+        embedding : Embedding
+
+        language : typing.Optional[SupportedLanguage]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        Voice
+
+        Examples
+        --------
+        from cartesia import Cartesia
+
+        client = Cartesia(
+            api_key="YOUR_API_KEY",
+        )
+        client.voices.create(
+            name="string",
+            description="string",
+            embedding=[
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+            ],
+            language="en",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "voices/",
+            method="POST",
+            json={
+                "name": name,
+                "description": description,
+                "embedding": embedding,
+                "language": language,
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    Voice,
+                    parse_obj_as(
+                        type_=Voice,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def delete(self, id: VoiceId, *, request_options: typing.Optional[RequestOptions] = None) -> None:
+        """
+        Parameters
+        ----------
+        id : VoiceId
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        None
+
+        Examples
+        --------
+        from cartesia import Cartesia
+
+        client = Cartesia(
+            api_key="YOUR_API_KEY",
+        )
+        client.voices.delete(
+            id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"voices/{jsonable_encoder(id)}",
+            method="DELETE",
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def update(
+        self, id: VoiceId, *, name: str, description: str, request_options: typing.Optional[RequestOptions] = None
+    ) -> Voice:
+        """
+        Parameters
+        ----------
+        id : VoiceId
+
+        name : str
+            The name of the voice.
+
+        description : str
+            The description of the voice.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        Voice
+
+        Examples
+        --------
+        from cartesia import Cartesia
+
+        client = Cartesia(
+            api_key="YOUR_API_KEY",
+        )
+        client.voices.update(
+            id="string",
+            name="string",
+            description="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"voices/{jsonable_encoder(id)}",
+            method="PATCH",
+            json={
+                "name": name,
+                "description": description,
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    Voice,
+                    parse_obj_as(
+                        type_=Voice,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def get(self, id: VoiceId, *, request_options: typing.Optional[RequestOptions] = None) -> Voice:
+        """
+        Parameters
+        ----------
+        id : VoiceId
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        Voice
+
+        Examples
+        --------
+        from cartesia import Cartesia
+
+        client = Cartesia(
+            api_key="YOUR_API_KEY",
+        )
+        client.voices.get(
+            id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"voices/{jsonable_encoder(id)}",
+            method="GET",
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    Voice,
+                    parse_obj_as(
+                        type_=Voice,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def localize(
+        self,
+        *,
+        embedding: Embedding,
+        language: LocalizeTargetLanguage,
+        original_speaker_gender: Gender,
+        dialect: typing.Optional[LocalizeDialectParams] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> EmbeddingResponse:
+        """
+        Parameters
+        ----------
+        embedding : Embedding
+
+        language : LocalizeTargetLanguage
+
+        original_speaker_gender : Gender
+
+        dialect : typing.Optional[LocalizeDialectParams]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        EmbeddingResponse
+
+        Examples
+        --------
+        from cartesia import Cartesia
+
+        client = Cartesia(
+            api_key="YOUR_API_KEY",
+        )
+        client.voices.localize(
+            embedding=[
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+                1.0,
+            ],
+            language="en",
+            original_speaker_gender="male",
+            dialect="au",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "voices/localize",
+            method="POST",
+            json={
+                "embedding": embedding,
+                "language": language,
+                "original_speaker_gender": original_speaker_gender,
+                "dialect": convert_and_respect_annotation_metadata(
+                    object_=dialect, annotation=LocalizeDialectParams, direction="write"
+                ),
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    EmbeddingResponse,
+                    parse_obj_as(
+                        type_=EmbeddingResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def mix(
+        self,
+        *,
+        voices: typing.Sequence[MixVoiceSpecifierParams],
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> EmbeddingResponse:
+        """
+        Parameters
+        ----------
+        voices : typing.Sequence[MixVoiceSpecifierParams]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        EmbeddingResponse
+
+        Examples
+        --------
+        from cartesia import Cartesia
+
+        client = Cartesia(
+            api_key="YOUR_API_KEY",
+        )
+        client.voices.mix(
+            voices=[{"id": "string", "weight": 1.1}],
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "voices/mix",
+            method="POST",
+            json={
+                "voices": convert_and_respect_annotation_metadata(
+                    object_=voices, annotation=typing.Sequence[MixVoiceSpecifierParams], direction="write"
+                ),
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    EmbeddingResponse,
+                    parse_obj_as(
+                        type_=EmbeddingResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    def clone(
+        self,
+        *,
+        clip: core.File,
+        name: str,
+        language: SupportedLanguage,
+        mode: CloneMode,
+        enhance: bool,
+        description: typing.Optional[str] = OMIT,
+        transcript: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> VoiceMetadata:
+        """
+        Clone a voice from an audio clip. This endpoint has two modes, stability and similarity.
+
+        Similarity mode clones are more similar to the source clip, but may reproduce background noise. For these, use an audio clip about 5 seconds long.
+
+        Stability mode clones are more stable, but may not sound as similar to the source clip. For these, use an audio clip 10-20 seconds long.
+
+        Parameters
+        ----------
+        clip : core.File
+            See core.File for more documentation
+
+        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.
+
+
+        enhance : bool
+            Whether to enhance the clip to improve its quality before cloning. Useful if the clip has background noise.
+
+
+        description : typing.Optional[str]
+            A description for the voice.
+
+
+        transcript : typing.Optional[str]
+            Optional transcript of the words spoken in the audio clip. Only used for similarity mode.
+
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        VoiceMetadata
+
+        Examples
+        --------
+        from cartesia import Cartesia
+
+        client = Cartesia(
+            api_key="YOUR_API_KEY",
+        )
+        client.voices.clone(
+            name="A high-stability cloned voice",
+            description="Copied from Cartesia docs",
+            mode="stability",
+            language="en",
+            enhance=True,
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "voices/clone",
+            method="POST",
+            data={
+                "name": name,
+                "description": description,
+                "language": language,
+                "mode": mode,
+                "enhance": enhance,
+                "transcript": transcript,
+            },
+            files={
+                "clip": clip,
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    VoiceMetadata,
+                    parse_obj_as(
+                        type_=VoiceMetadata,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+
+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]:
+        """
+        Parameters
+        ----------
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        typing.List[Voice]
+
+        Examples
+        --------
+        import asyncio
+
+        from cartesia import AsyncCartesia
+
+        client = AsyncCartesia(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.voices.list()
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "voices/",
+            method="GET",
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    typing.List[Voice],
+                    parse_obj_as(
+                        type_=typing.List[Voice],  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def create(
+        self,
+        *,
+        name: str,
+        description: str,
+        embedding: Embedding,
+        language: typing.Optional[SupportedLanguage] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> Voice:
+        """
+        Parameters
+        ----------
+        name : str
+            The name of the voice.
+
+        description : str
+            The description of the voice.
+
+        embedding : Embedding
+
+        language : typing.Optional[SupportedLanguage]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        Voice
+
+        Examples
+        --------
+        import asyncio
+
+        from cartesia import AsyncCartesia
+
+        client = AsyncCartesia(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.voices.create(
+                name="string",
+                description="string",
+                embedding=[
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                ],
+                language="en",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "voices/",
+            method="POST",
+            json={
+                "name": name,
+                "description": description,
+                "embedding": embedding,
+                "language": language,
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    Voice,
+                    parse_obj_as(
+                        type_=Voice,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def delete(self, id: VoiceId, *, request_options: typing.Optional[RequestOptions] = None) -> None:
+        """
+        Parameters
+        ----------
+        id : VoiceId
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        None
+
+        Examples
+        --------
+        import asyncio
+
+        from cartesia import AsyncCartesia
+
+        client = AsyncCartesia(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.voices.delete(
+                id="string",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"voices/{jsonable_encoder(id)}",
+            method="DELETE",
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def update(
+        self, id: VoiceId, *, name: str, description: str, request_options: typing.Optional[RequestOptions] = None
+    ) -> Voice:
+        """
+        Parameters
+        ----------
+        id : VoiceId
+
+        name : str
+            The name of the voice.
+
+        description : str
+            The description of the voice.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        Voice
+
+        Examples
+        --------
+        import asyncio
+
+        from cartesia import AsyncCartesia
+
+        client = AsyncCartesia(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.voices.update(
+                id="string",
+                name="string",
+                description="string",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"voices/{jsonable_encoder(id)}",
+            method="PATCH",
+            json={
+                "name": name,
+                "description": description,
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    Voice,
+                    parse_obj_as(
+                        type_=Voice,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def get(self, id: VoiceId, *, request_options: typing.Optional[RequestOptions] = None) -> Voice:
+        """
+        Parameters
+        ----------
+        id : VoiceId
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        Voice
+
+        Examples
+        --------
+        import asyncio
+
+        from cartesia import AsyncCartesia
+
+        client = AsyncCartesia(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.voices.get(
+                id="string",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"voices/{jsonable_encoder(id)}",
+            method="GET",
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    Voice,
+                    parse_obj_as(
+                        type_=Voice,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def localize(
+        self,
+        *,
+        embedding: Embedding,
+        language: LocalizeTargetLanguage,
+        original_speaker_gender: Gender,
+        dialect: typing.Optional[LocalizeDialectParams] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> EmbeddingResponse:
+        """
+        Parameters
+        ----------
+        embedding : Embedding
+
+        language : LocalizeTargetLanguage
+
+        original_speaker_gender : Gender
+
+        dialect : typing.Optional[LocalizeDialectParams]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        EmbeddingResponse
+
+        Examples
+        --------
+        import asyncio
+
+        from cartesia import AsyncCartesia
+
+        client = AsyncCartesia(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.voices.localize(
+                embedding=[
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                    1.0,
+                ],
+                language="en",
+                original_speaker_gender="male",
+                dialect="au",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "voices/localize",
+            method="POST",
+            json={
+                "embedding": embedding,
+                "language": language,
+                "original_speaker_gender": original_speaker_gender,
+                "dialect": convert_and_respect_annotation_metadata(
+                    object_=dialect, annotation=LocalizeDialectParams, direction="write"
+                ),
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    EmbeddingResponse,
+                    parse_obj_as(
+                        type_=EmbeddingResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def mix(
+        self,
+        *,
+        voices: typing.Sequence[MixVoiceSpecifierParams],
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> EmbeddingResponse:
+        """
+        Parameters
+        ----------
+        voices : typing.Sequence[MixVoiceSpecifierParams]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        EmbeddingResponse
+
+        Examples
+        --------
+        import asyncio
+
+        from cartesia import AsyncCartesia
+
+        client = AsyncCartesia(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.voices.mix(
+                voices=[{"id": "string", "weight": 1.1}],
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "voices/mix",
+            method="POST",
+            json={
+                "voices": convert_and_respect_annotation_metadata(
+                    object_=voices, annotation=typing.Sequence[MixVoiceSpecifierParams], direction="write"
+                ),
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    EmbeddingResponse,
+                    parse_obj_as(
+                        type_=EmbeddingResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def clone(
+        self,
+        *,
+        clip: core.File,
+        name: str,
+        language: SupportedLanguage,
+        mode: CloneMode,
+        enhance: bool,
+        description: typing.Optional[str] = OMIT,
+        transcript: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> VoiceMetadata:
+        """
+        Clone a voice from an audio clip. This endpoint has two modes, stability and similarity.
+
+        Similarity mode clones are more similar to the source clip, but may reproduce background noise. For these, use an audio clip about 5 seconds long.
+
+        Stability mode clones are more stable, but may not sound as similar to the source clip. For these, use an audio clip 10-20 seconds long.
+
+        Parameters
+        ----------
+        clip : core.File
+            See core.File for more documentation
+
+        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.
+
+
+        enhance : bool
+            Whether to enhance the clip to improve its quality before cloning. Useful if the clip has background noise.
+
+
+        description : typing.Optional[str]
+            A description for the voice.
+
+
+        transcript : typing.Optional[str]
+            Optional transcript of the words spoken in the audio clip. Only used for similarity mode.
+
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        VoiceMetadata
+
+        Examples
+        --------
+        import asyncio
+
+        from cartesia import AsyncCartesia
+
+        client = AsyncCartesia(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.voices.clone(
+                name="A high-stability cloned voice",
+                description="Copied from Cartesia docs",
+                mode="stability",
+                language="en",
+                enhance=True,
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "voices/clone",
+            method="POST",
+            data={
+                "name": name,
+                "description": description,
+                "language": language,
+                "mode": mode,
+                "enhance": enhance,
+                "transcript": transcript,
+            },
+            files={
+                "clip": clip,
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    VoiceMetadata,
+                    parse_obj_as(
+                        type_=VoiceMetadata,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)