cartesia 1.4.0__py3-none-any.whl → 2.0.0__py3-none-any.whl

cartesia/voice_changer/client.py

@@ -0,0 +1,395 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+from ..core.client_wrapper import SyncClientWrapper
+from .. import core
+from .types.output_format_container import OutputFormatContainer
+from ..tts.types.raw_encoding import RawEncoding
+from ..core.request_options import RequestOptions
+from json.decoder import JSONDecodeError
+from ..core.api_error import ApiError
+from .types.streaming_response import StreamingResponse
+from ..core.pydantic_utilities import parse_obj_as
+import json
+from ..core.client_wrapper import AsyncClientWrapper
+
+# this is used as the default value for optional parameters
+OMIT = typing.cast(typing.Any, ...)
+
+
+class VoiceChangerClient:
+    def __init__(self, *, client_wrapper: SyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    def bytes(
+        self,
+        *,
+        clip: core.File,
+        voice_id: str,
+        output_format_container: OutputFormatContainer,
+        output_format_sample_rate: int,
+        output_format_encoding: typing.Optional[RawEncoding] = OMIT,
+        output_format_bit_rate: typing.Optional[int] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.Iterator[bytes]:
+        """
+        Takes an audio file of speech, and returns an audio file of speech spoken with the same intonation, but with a different voice.
+
+        This endpoint is priced at 15 characters per second of input audio.
+
+        Parameters
+        ----------
+        clip : core.File
+            See core.File for more documentation
+
+        voice_id : str
+
+        output_format_container : OutputFormatContainer
+
+        output_format_sample_rate : int
+
+        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.
+
+        Yields
+        ------
+        typing.Iterator[bytes]
+
+        Examples
+        --------
+        from cartesia import Cartesia
+
+        client = Cartesia(
+            api_key="YOUR_API_KEY",
+        )
+        client.voice_changer.bytes(
+            voice_id="694f9389-aac1-45b6-b726-9d9369183238",
+            output_format_container="mp3",
+            output_format_sample_rate=44100,
+            output_format_bit_rate=128000,
+        )
+        """
+        with self._client_wrapper.httpx_client.stream(
+            "voice-changer/bytes",
+            method="POST",
+            data={
+                "voice[id]": voice_id,
+                "output_format[container]": output_format_container,
+                "output_format[sample_rate]": output_format_sample_rate,
+                "output_format[encoding]": output_format_encoding,
+                "output_format[bit_rate]": output_format_bit_rate,
+            },
+            files={
+                "clip": clip,
+            },
+            request_options=request_options,
+            omit=OMIT,
+        ) as _response:
+            try:
+                if 200 <= _response.status_code < 300:
+                    _chunk_size = request_options.get("chunk_size", None) if request_options is not None else None
+                    for _chunk in _response.iter_bytes(chunk_size=_chunk_size):
+                        yield _chunk
+                    return
+                _response.read()
+                _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 sse(
+        self,
+        *,
+        clip: core.File,
+        voice_id: str,
+        output_format_container: OutputFormatContainer,
+        output_format_sample_rate: int,
+        output_format_encoding: typing.Optional[RawEncoding] = OMIT,
+        output_format_bit_rate: typing.Optional[int] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.Iterator[StreamingResponse]:
+        """
+        Parameters
+        ----------
+        clip : core.File
+            See core.File for more documentation
+
+        voice_id : str
+
+        output_format_container : OutputFormatContainer
+
+        output_format_sample_rate : int
+
+        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.
+
+        Yields
+        ------
+        typing.Iterator[StreamingResponse]
+
+        Examples
+        --------
+        from cartesia import Cartesia
+
+        client = Cartesia(
+            api_key="YOUR_API_KEY",
+        )
+        response = client.voice_changer.sse(
+            voice_id="694f9389-aac1-45b6-b726-9d9369183238",
+            output_format_container="mp3",
+            output_format_sample_rate=44100,
+            output_format_bit_rate=128000,
+        )
+        for chunk in response:
+            yield chunk
+        """
+        with self._client_wrapper.httpx_client.stream(
+            "voice-changer/sse",
+            method="POST",
+            data={
+                "voice[id]": voice_id,
+                "output_format[container]": output_format_container,
+                "output_format[sample_rate]": output_format_sample_rate,
+                "output_format[encoding]": output_format_encoding,
+                "output_format[bit_rate]": output_format_bit_rate,
+            },
+            files={
+                "clip": clip,
+            },
+            request_options=request_options,
+            omit=OMIT,
+        ) as _response:
+            try:
+                if 200 <= _response.status_code < 300:
+                    for _text in _response.iter_lines():
+                        try:
+                            if len(_text) == 0:
+                                continue
+                            yield typing.cast(
+                                StreamingResponse,
+                                parse_obj_as(
+                                    type_=StreamingResponse,  # type: ignore
+                                    object_=json.loads(_text),
+                                ),
+                            )
+                        except:
+                            pass
+                    return
+                _response.read()
+                _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 AsyncVoiceChangerClient:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    async def bytes(
+        self,
+        *,
+        clip: core.File,
+        voice_id: str,
+        output_format_container: OutputFormatContainer,
+        output_format_sample_rate: int,
+        output_format_encoding: typing.Optional[RawEncoding] = OMIT,
+        output_format_bit_rate: typing.Optional[int] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.AsyncIterator[bytes]:
+        """
+        Takes an audio file of speech, and returns an audio file of speech spoken with the same intonation, but with a different voice.
+
+        This endpoint is priced at 15 characters per second of input audio.
+
+        Parameters
+        ----------
+        clip : core.File
+            See core.File for more documentation
+
+        voice_id : str
+
+        output_format_container : OutputFormatContainer
+
+        output_format_sample_rate : int
+
+        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.
+
+        Yields
+        ------
+        typing.AsyncIterator[bytes]
+
+        Examples
+        --------
+        import asyncio
+
+        from cartesia import AsyncCartesia
+
+        client = AsyncCartesia(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.voice_changer.bytes(
+                voice_id="694f9389-aac1-45b6-b726-9d9369183238",
+                output_format_container="mp3",
+                output_format_sample_rate=44100,
+                output_format_bit_rate=128000,
+            )
+
+
+        asyncio.run(main())
+        """
+        async with self._client_wrapper.httpx_client.stream(
+            "voice-changer/bytes",
+            method="POST",
+            data={
+                "voice[id]": voice_id,
+                "output_format[container]": output_format_container,
+                "output_format[sample_rate]": output_format_sample_rate,
+                "output_format[encoding]": output_format_encoding,
+                "output_format[bit_rate]": output_format_bit_rate,
+            },
+            files={
+                "clip": clip,
+            },
+            request_options=request_options,
+            omit=OMIT,
+        ) as _response:
+            try:
+                if 200 <= _response.status_code < 300:
+                    _chunk_size = request_options.get("chunk_size", None) if request_options is not None else None
+                    async for _chunk in _response.aiter_bytes(chunk_size=_chunk_size):
+                        yield _chunk
+                    return
+                await _response.aread()
+                _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 sse(
+        self,
+        *,
+        clip: core.File,
+        voice_id: str,
+        output_format_container: OutputFormatContainer,
+        output_format_sample_rate: int,
+        output_format_encoding: typing.Optional[RawEncoding] = OMIT,
+        output_format_bit_rate: typing.Optional[int] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.AsyncIterator[StreamingResponse]:
+        """
+        Parameters
+        ----------
+        clip : core.File
+            See core.File for more documentation
+
+        voice_id : str
+
+        output_format_container : OutputFormatContainer
+
+        output_format_sample_rate : int
+
+        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.
+
+        Yields
+        ------
+        typing.AsyncIterator[StreamingResponse]
+
+        Examples
+        --------
+        import asyncio
+
+        from cartesia import AsyncCartesia
+
+        client = AsyncCartesia(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            response = await client.voice_changer.sse(
+                voice_id="694f9389-aac1-45b6-b726-9d9369183238",
+                output_format_container="mp3",
+                output_format_sample_rate=44100,
+                output_format_bit_rate=128000,
+            )
+            async for chunk in response:
+                yield chunk
+
+
+        asyncio.run(main())
+        """
+        async with self._client_wrapper.httpx_client.stream(
+            "voice-changer/sse",
+            method="POST",
+            data={
+                "voice[id]": voice_id,
+                "output_format[container]": output_format_container,
+                "output_format[sample_rate]": output_format_sample_rate,
+                "output_format[encoding]": output_format_encoding,
+                "output_format[bit_rate]": output_format_bit_rate,
+            },
+            files={
+                "clip": clip,
+            },
+            request_options=request_options,
+            omit=OMIT,
+        ) as _response:
+            try:
+                if 200 <= _response.status_code < 300:
+                    async for _text in _response.aiter_lines():
+                        try:
+                            if len(_text) == 0:
+                                continue
+                            yield typing.cast(
+                                StreamingResponse,
+                                parse_obj_as(
+                                    type_=StreamingResponse,  # type: ignore
+                                    object_=json.loads(_text),
+                                ),
+                            )
+                        except:
+                            pass
+                    return
+                await _response.aread()
+                _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)

cartesia/voice_changer/requests/__init__.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .streaming_response import (
+    StreamingResponseParams,
+    StreamingResponse_ChunkParams,
+    StreamingResponse_DoneParams,
+    StreamingResponse_ErrorParams,
+)
+
+__all__ = [
+    "StreamingResponseParams",
+    "StreamingResponse_ChunkParams",
+    "StreamingResponse_DoneParams",
+    "StreamingResponse_ErrorParams",
+]

cartesia/voice_changer/requests/streaming_response.py

@@ -0,0 +1,38 @@
+# This file was auto-generated by Fern from our API Definition.
+
+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
+
+
+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
+
+
+class StreamingResponse_DoneParams(typing_extensions.TypedDict):
+    type: typing.Literal["done"]
+    context_id: typing_extensions.NotRequired[ContextId]
+    status_code: int
+    done: bool
+
+
+class StreamingResponse_ErrorParams(typing_extensions.TypedDict):
+    type: typing.Literal["error"]
+    error: str
+    context_id: typing_extensions.NotRequired[ContextId]
+    status_code: int
+    done: bool
+
+
+StreamingResponseParams = typing.Union[
+    StreamingResponse_ChunkParams, StreamingResponse_DoneParams, StreamingResponse_ErrorParams
+]

cartesia/voice_changer/types/__init__.py

@@ -0,0 +1,17 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .output_format_container import OutputFormatContainer
+from .streaming_response import (
+    StreamingResponse,
+    StreamingResponse_Chunk,
+    StreamingResponse_Done,
+    StreamingResponse_Error,
+)
+
+__all__ = [
+    "OutputFormatContainer",
+    "StreamingResponse",
+    "StreamingResponse_Chunk",
+    "StreamingResponse_Done",
+    "StreamingResponse_Error",
+]

cartesia/voice_changer/types/output_format_container.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+OutputFormatContainer = typing.Union[typing.Literal["raw", "wav", "mp3"], typing.Any]

cartesia/voice_changer/types/streaming_response.py

@@ -0,0 +1,64 @@
+# This file was auto-generated by Fern from our API Definition.
+
+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
+
+
+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
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow
+
+
+class StreamingResponse_Done(UniversalBaseModel):
+    type: typing.Literal["done"] = "done"
+    context_id: typing.Optional[ContextId] = None
+    status_code: int
+    done: bool
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow
+
+
+class StreamingResponse_Error(UniversalBaseModel):
+    type: typing.Literal["error"] = "error"
+    error: str
+    context_id: typing.Optional[ContextId] = None
+    status_code: int
+    done: bool
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow
+
+
+StreamingResponse = typing.Union[StreamingResponse_Chunk, StreamingResponse_Done, StreamingResponse_Error]

cartesia/voices/__init__.py

@@ -0,0 +1,81 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .types import (
+    BaseVoiceId,
+    CloneMode,
+    CreateVoiceRequest,
+    EmbeddingResponse,
+    EmbeddingSpecifier,
+    Gender,
+    GenderPresentation,
+    GetVoicesResponse,
+    IdSpecifier,
+    LocalizeDialect,
+    LocalizeEnglishDialect,
+    LocalizeFrenchDialect,
+    LocalizePortugueseDialect,
+    LocalizeSpanishDialect,
+    LocalizeTargetLanguage,
+    LocalizeVoiceRequest,
+    MixVoiceSpecifier,
+    MixVoicesRequest,
+    UpdateVoiceRequest,
+    Voice,
+    VoiceExpandOptions,
+    VoiceId,
+    VoiceMetadata,
+    Weight,
+)
+from .requests import (
+    CreateVoiceRequestParams,
+    EmbeddingResponseParams,
+    EmbeddingSpecifierParams,
+    GetVoicesResponseParams,
+    IdSpecifierParams,
+    LocalizeDialectParams,
+    LocalizeVoiceRequestParams,
+    MixVoiceSpecifierParams,
+    MixVoicesRequestParams,
+    UpdateVoiceRequestParams,
+    VoiceMetadataParams,
+    VoiceParams,
+)
+
+__all__ = [
+    "BaseVoiceId",
+    "CloneMode",
+    "CreateVoiceRequest",
+    "CreateVoiceRequestParams",
+    "EmbeddingResponse",
+    "EmbeddingResponseParams",
+    "EmbeddingSpecifier",
+    "EmbeddingSpecifierParams",
+    "Gender",
+    "GenderPresentation",
+    "GetVoicesResponse",
+    "GetVoicesResponseParams",
+    "IdSpecifier",
+    "IdSpecifierParams",
+    "LocalizeDialect",
+    "LocalizeDialectParams",
+    "LocalizeEnglishDialect",
+    "LocalizeFrenchDialect",
+    "LocalizePortugueseDialect",
+    "LocalizeSpanishDialect",
+    "LocalizeTargetLanguage",
+    "LocalizeVoiceRequest",
+    "LocalizeVoiceRequestParams",
+    "MixVoiceSpecifier",
+    "MixVoiceSpecifierParams",
+    "MixVoicesRequest",
+    "MixVoicesRequestParams",
+    "UpdateVoiceRequest",
+    "UpdateVoiceRequestParams",
+    "Voice",
+    "VoiceExpandOptions",
+    "VoiceId",
+    "VoiceMetadata",
+    "VoiceMetadataParams",
+    "VoiceParams",
+    "Weight",
+]