speechify-api 0.0.145__py3-none-any.whl

speechifyinc/tts/__init__.py

@@ -0,0 +1,78 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .types import (
+    AccessToken,
+    AccessTokenScope,
+    ApiKey,
+    CreateVoiceLanguage,
+    CreateVoiceModel,
+    CreateVoiceModelName,
+    CreatedVoice,
+    CreatedVoiceGender,
+    CreatedVoiceType,
+    ExperimentalStreamRequest,
+    ExperimentalStreamRequestModel,
+    ExperimentalStreamResponse,
+    GetSpeechOptionsRequest,
+    GetSpeechResponse,
+    GetSpeechResponseAudioFormat,
+    GetStreamOptionsRequest,
+    GetVoice,
+    GetVoiceGender,
+    GetVoiceLanguage,
+    GetVoiceType,
+    GetVoicesModel,
+    GetVoicesModelName,
+    NestedChunk,
+    OAuthError,
+    OAuthErrorError,
+    SpeechMarks,
+)
+from .errors import BadRequestError, ForbiddenError, InternalServerError, NotFoundError, PaymentRequiredError
+from . import audio, auth, voices
+from .audio import AudioStreamRequestAccept, GetSpeechRequestAudioFormat, GetSpeechRequestModel, GetStreamRequestModel
+from .auth import CreateAccessTokenRequestScope
+from .voices import VoicesCreateRequestGender
+
+__all__ = [
+    "AccessToken",
+    "AccessTokenScope",
+    "ApiKey",
+    "AudioStreamRequestAccept",
+    "BadRequestError",
+    "CreateAccessTokenRequestScope",
+    "CreateVoiceLanguage",
+    "CreateVoiceModel",
+    "CreateVoiceModelName",
+    "CreatedVoice",
+    "CreatedVoiceGender",
+    "CreatedVoiceType",
+    "ExperimentalStreamRequest",
+    "ExperimentalStreamRequestModel",
+    "ExperimentalStreamResponse",
+    "ForbiddenError",
+    "GetSpeechOptionsRequest",
+    "GetSpeechRequestAudioFormat",
+    "GetSpeechRequestModel",
+    "GetSpeechResponse",
+    "GetSpeechResponseAudioFormat",
+    "GetStreamOptionsRequest",
+    "GetStreamRequestModel",
+    "GetVoice",
+    "GetVoiceGender",
+    "GetVoiceLanguage",
+    "GetVoiceType",
+    "GetVoicesModel",
+    "GetVoicesModelName",
+    "InternalServerError",
+    "NestedChunk",
+    "NotFoundError",
+    "OAuthError",
+    "OAuthErrorError",
+    "PaymentRequiredError",
+    "SpeechMarks",
+    "VoicesCreateRequestGender",
+    "audio",
+    "auth",
+    "voices",
+]

speechifyinc/tts/audio/__init__.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .types import AudioStreamRequestAccept, GetSpeechRequestAudioFormat, GetSpeechRequestModel, GetStreamRequestModel
+
+__all__ = ["AudioStreamRequestAccept", "GetSpeechRequestAudioFormat", "GetSpeechRequestModel", "GetStreamRequestModel"]

speechifyinc/tts/audio/client.py

@@ -0,0 +1,544 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+from ...core.client_wrapper import SyncClientWrapper
+from .types.get_speech_request_audio_format import GetSpeechRequestAudioFormat
+from .types.get_speech_request_model import GetSpeechRequestModel
+from ..types.get_speech_options_request import GetSpeechOptionsRequest
+from ...core.request_options import RequestOptions
+from ..types.get_speech_response import GetSpeechResponse
+from ...core.serialization import convert_and_respect_annotation_metadata
+from ...core.pydantic_utilities import parse_obj_as
+from ..errors.bad_request_error import BadRequestError
+from ..errors.payment_required_error import PaymentRequiredError
+from ..errors.forbidden_error import ForbiddenError
+from ..errors.internal_server_error import InternalServerError
+from json.decoder import JSONDecodeError
+from ...core.api_error import ApiError
+from .types.audio_stream_request_accept import AudioStreamRequestAccept
+from .types.get_stream_request_model import GetStreamRequestModel
+from ..types.get_stream_options_request import GetStreamOptionsRequest
+from ...core.client_wrapper import AsyncClientWrapper
+
+# this is used as the default value for optional parameters
+OMIT = typing.cast(typing.Any, ...)
+
+
+class AudioClient:
+    def __init__(self, *, client_wrapper: SyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    def speech(
+        self,
+        *,
+        input: str,
+        voice_id: str,
+        audio_format: typing.Optional[GetSpeechRequestAudioFormat] = OMIT,
+        language: typing.Optional[str] = OMIT,
+        model: typing.Optional[GetSpeechRequestModel] = OMIT,
+        options: typing.Optional[GetSpeechOptionsRequest] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> GetSpeechResponse:
+        """
+        Gets the speech data for the given input
+
+        Parameters
+        ----------
+        input : str
+            Plain text or SSML to be synthesized to speech.
+            Refer to https://docs.sws.speechify.com/docs/api-limits for the input size limits.
+            Emotion, Pitch and Speed Rate are configured in the ssml input, please refer to the ssml documentation for more information: https://docs.sws.speechify.com/docs/ssml#prosody
+
+        voice_id : str
+            Id of the voice to be used for synthesizing speech. Refer to /v1/voices endpoint for available voices
+
+        audio_format : typing.Optional[GetSpeechRequestAudioFormat]
+            The format for the output audio. Note, that the current default is "wav", but there's no guarantee it will not change in the future. We recommend always passing the specific param you expect.
+
+        language : typing.Optional[str]
+            Language of the input. Follow the format of an ISO 639-1 language code and an ISO 3166-1 region code, separated by a hyphen, e.g. en-US.
+            Please refer to the list of the supported languages and recommendations regarding this parameter: https://docs.sws.speechify.com/docs/language-support.
+
+        model : typing.Optional[GetSpeechRequestModel]
+            Model used for audio synthesis
+            simba-base ModelBase  ModelBase is deprecated. Use simba-english or simba-multilingual instead.  @deprecated
+            simba-english ModelEnglish
+            simba-multilingual ModelMultilingual
+            simba-turbo ModelTurbo
+
+        options : typing.Optional[GetSpeechOptionsRequest]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        GetSpeechResponse
+
+
+        Examples
+        --------
+        from speechifyinc import Speechify
+
+        client = Speechify(
+            token="YOUR_TOKEN",
+        )
+        client.tts.audio.speech(
+            input="input",
+            voice_id="voice_id",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "v1/audio/speech",
+            method="POST",
+            json={
+                "audio_format": audio_format,
+                "input": input,
+                "language": language,
+                "model": model,
+                "options": convert_and_respect_annotation_metadata(
+                    object_=options, annotation=GetSpeechOptionsRequest, direction="write"
+                ),
+                "voice_id": voice_id,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    GetSpeechResponse,
+                    parse_obj_as(
+                        type_=GetSpeechResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            if _response.status_code == 402:
+                raise PaymentRequiredError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            if _response.status_code == 403:
+                raise ForbiddenError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            if _response.status_code == 500:
+                raise InternalServerError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # 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 stream(
+        self,
+        *,
+        accept: AudioStreamRequestAccept,
+        input: str,
+        voice_id: str,
+        language: typing.Optional[str] = OMIT,
+        model: typing.Optional[GetStreamRequestModel] = OMIT,
+        options: typing.Optional[GetStreamOptionsRequest] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.Iterator[bytes]:
+        """
+        Gets the stream speech for the given input
+
+        Parameters
+        ----------
+        accept : AudioStreamRequestAccept
+
+        input : str
+            Plain text or SSML to be synthesized to speech.
+            Refer to https://docs.sws.speechify.com/docs/api-limits for the input size limits.
+            Emotion, Pitch and Speed Rate are configured in the ssml input, please refer to the ssml documentation for more information: https://docs.sws.speechify.com/docs/ssml#prosody
+
+        voice_id : str
+            Id of the voice to be used for synthesizing speech. Refer to /v1/voices endpoint for available voices
+
+        language : typing.Optional[str]
+            Language of the input. Follow the format of an ISO 639-1 language code and an ISO 3166-1 region code, separated by a hyphen, e.g. en-US.
+            Please refer to the list of the supported languages and recommendations regarding this parameter: https://docs.sws.speechify.com/docs/language-support.
+
+        model : typing.Optional[GetStreamRequestModel]
+            Model used for audio synthesis
+            simba-base ModelBase  ModelBase is deprecated. Use simba-english or simba-multilingual instead.  @deprecated
+            simba-english ModelEnglish
+            simba-multilingual ModelMultilingual
+            simba-turbo ModelTurbo
+
+        options : typing.Optional[GetStreamOptionsRequest]
+
+        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]
+
+        """
+        with self._client_wrapper.httpx_client.stream(
+            "v1/audio/stream",
+            method="POST",
+            json={
+                "input": input,
+                "language": language,
+                "model": model,
+                "options": convert_and_respect_annotation_metadata(
+                    object_=options, annotation=GetStreamOptionsRequest, direction="write"
+                ),
+                "voice_id": voice_id,
+            },
+            headers={
+                "content-type": "application/json",
+                "Accept": str(accept) if accept is not None else None,
+            },
+            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()
+                if _response.status_code == 400:
+                    raise BadRequestError(
+                        typing.cast(
+                            typing.Optional[typing.Any],
+                            parse_obj_as(
+                                type_=typing.Optional[typing.Any],  # type: ignore
+                                object_=_response.json(),
+                            ),
+                        )
+                    )
+                if _response.status_code == 402:
+                    raise PaymentRequiredError(
+                        typing.cast(
+                            typing.Optional[typing.Any],
+                            parse_obj_as(
+                                type_=typing.Optional[typing.Any],  # type: ignore
+                                object_=_response.json(),
+                            ),
+                        )
+                    )
+                if _response.status_code == 403:
+                    raise ForbiddenError(
+                        typing.cast(
+                            typing.Optional[typing.Any],
+                            parse_obj_as(
+                                type_=typing.Optional[typing.Any],  # type: ignore
+                                object_=_response.json(),
+                            ),
+                        )
+                    )
+                if _response.status_code == 500:
+                    raise InternalServerError(
+                        typing.cast(
+                            typing.Optional[typing.Any],
+                            parse_obj_as(
+                                type_=typing.Optional[typing.Any],  # 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 AsyncAudioClient:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    async def speech(
+        self,
+        *,
+        input: str,
+        voice_id: str,
+        audio_format: typing.Optional[GetSpeechRequestAudioFormat] = OMIT,
+        language: typing.Optional[str] = OMIT,
+        model: typing.Optional[GetSpeechRequestModel] = OMIT,
+        options: typing.Optional[GetSpeechOptionsRequest] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> GetSpeechResponse:
+        """
+        Gets the speech data for the given input
+
+        Parameters
+        ----------
+        input : str
+            Plain text or SSML to be synthesized to speech.
+            Refer to https://docs.sws.speechify.com/docs/api-limits for the input size limits.
+            Emotion, Pitch and Speed Rate are configured in the ssml input, please refer to the ssml documentation for more information: https://docs.sws.speechify.com/docs/ssml#prosody
+
+        voice_id : str
+            Id of the voice to be used for synthesizing speech. Refer to /v1/voices endpoint for available voices
+
+        audio_format : typing.Optional[GetSpeechRequestAudioFormat]
+            The format for the output audio. Note, that the current default is "wav", but there's no guarantee it will not change in the future. We recommend always passing the specific param you expect.
+
+        language : typing.Optional[str]
+            Language of the input. Follow the format of an ISO 639-1 language code and an ISO 3166-1 region code, separated by a hyphen, e.g. en-US.
+            Please refer to the list of the supported languages and recommendations regarding this parameter: https://docs.sws.speechify.com/docs/language-support.
+
+        model : typing.Optional[GetSpeechRequestModel]
+            Model used for audio synthesis
+            simba-base ModelBase  ModelBase is deprecated. Use simba-english or simba-multilingual instead.  @deprecated
+            simba-english ModelEnglish
+            simba-multilingual ModelMultilingual
+            simba-turbo ModelTurbo
+
+        options : typing.Optional[GetSpeechOptionsRequest]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        GetSpeechResponse
+
+
+        Examples
+        --------
+        import asyncio
+
+        from speechifyinc import AsyncSpeechify
+
+        client = AsyncSpeechify(
+            token="YOUR_TOKEN",
+        )
+
+
+        async def main() -> None:
+            await client.tts.audio.speech(
+                input="input",
+                voice_id="voice_id",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "v1/audio/speech",
+            method="POST",
+            json={
+                "audio_format": audio_format,
+                "input": input,
+                "language": language,
+                "model": model,
+                "options": convert_and_respect_annotation_metadata(
+                    object_=options, annotation=GetSpeechOptionsRequest, direction="write"
+                ),
+                "voice_id": voice_id,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return typing.cast(
+                    GetSpeechResponse,
+                    parse_obj_as(
+                        type_=GetSpeechResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+            if _response.status_code == 400:
+                raise BadRequestError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            if _response.status_code == 402:
+                raise PaymentRequiredError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            if _response.status_code == 403:
+                raise ForbiddenError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    )
+                )
+            if _response.status_code == 500:
+                raise InternalServerError(
+                    typing.cast(
+                        typing.Optional[typing.Any],
+                        parse_obj_as(
+                            type_=typing.Optional[typing.Any],  # 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 stream(
+        self,
+        *,
+        accept: AudioStreamRequestAccept,
+        input: str,
+        voice_id: str,
+        language: typing.Optional[str] = OMIT,
+        model: typing.Optional[GetStreamRequestModel] = OMIT,
+        options: typing.Optional[GetStreamOptionsRequest] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.AsyncIterator[bytes]:
+        """
+        Gets the stream speech for the given input
+
+        Parameters
+        ----------
+        accept : AudioStreamRequestAccept
+
+        input : str
+            Plain text or SSML to be synthesized to speech.
+            Refer to https://docs.sws.speechify.com/docs/api-limits for the input size limits.
+            Emotion, Pitch and Speed Rate are configured in the ssml input, please refer to the ssml documentation for more information: https://docs.sws.speechify.com/docs/ssml#prosody
+
+        voice_id : str
+            Id of the voice to be used for synthesizing speech. Refer to /v1/voices endpoint for available voices
+
+        language : typing.Optional[str]
+            Language of the input. Follow the format of an ISO 639-1 language code and an ISO 3166-1 region code, separated by a hyphen, e.g. en-US.
+            Please refer to the list of the supported languages and recommendations regarding this parameter: https://docs.sws.speechify.com/docs/language-support.
+
+        model : typing.Optional[GetStreamRequestModel]
+            Model used for audio synthesis
+            simba-base ModelBase  ModelBase is deprecated. Use simba-english or simba-multilingual instead.  @deprecated
+            simba-english ModelEnglish
+            simba-multilingual ModelMultilingual
+            simba-turbo ModelTurbo
+
+        options : typing.Optional[GetStreamOptionsRequest]
+
+        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]
+
+        """
+        async with self._client_wrapper.httpx_client.stream(
+            "v1/audio/stream",
+            method="POST",
+            json={
+                "input": input,
+                "language": language,
+                "model": model,
+                "options": convert_and_respect_annotation_metadata(
+                    object_=options, annotation=GetStreamOptionsRequest, direction="write"
+                ),
+                "voice_id": voice_id,
+            },
+            headers={
+                "content-type": "application/json",
+                "Accept": str(accept) if accept is not None else None,
+            },
+            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()
+                if _response.status_code == 400:
+                    raise BadRequestError(
+                        typing.cast(
+                            typing.Optional[typing.Any],
+                            parse_obj_as(
+                                type_=typing.Optional[typing.Any],  # type: ignore
+                                object_=_response.json(),
+                            ),
+                        )
+                    )
+                if _response.status_code == 402:
+                    raise PaymentRequiredError(
+                        typing.cast(
+                            typing.Optional[typing.Any],
+                            parse_obj_as(
+                                type_=typing.Optional[typing.Any],  # type: ignore
+                                object_=_response.json(),
+                            ),
+                        )
+                    )
+                if _response.status_code == 403:
+                    raise ForbiddenError(
+                        typing.cast(
+                            typing.Optional[typing.Any],
+                            parse_obj_as(
+                                type_=typing.Optional[typing.Any],  # type: ignore
+                                object_=_response.json(),
+                            ),
+                        )
+                    )
+                if _response.status_code == 500:
+                    raise InternalServerError(
+                        typing.cast(
+                            typing.Optional[typing.Any],
+                            parse_obj_as(
+                                type_=typing.Optional[typing.Any],  # 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)

speechifyinc/tts/audio/types/__init__.py

@@ -0,0 +1,8 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .audio_stream_request_accept import AudioStreamRequestAccept
+from .get_speech_request_audio_format import GetSpeechRequestAudioFormat
+from .get_speech_request_model import GetSpeechRequestModel
+from .get_stream_request_model import GetStreamRequestModel
+
+__all__ = ["AudioStreamRequestAccept", "GetSpeechRequestAudioFormat", "GetSpeechRequestModel", "GetStreamRequestModel"]

speechifyinc/tts/audio/types/audio_stream_request_accept.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+AudioStreamRequestAccept = typing.Union[typing.Literal["audio/mpeg", "audio/ogg", "audio/aac"], typing.Any]

speechifyinc/tts/audio/types/get_speech_request_audio_format.py

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

speechifyinc/tts/audio/types/get_speech_request_model.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+GetSpeechRequestModel = typing.Union[
+    typing.Literal["simba-base", "simba-english", "simba-multilingual", "simba-turbo"], typing.Any
+]

speechifyinc/tts/audio/types/get_stream_request_model.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+GetStreamRequestModel = typing.Union[
+    typing.Literal["simba-base", "simba-english", "simba-multilingual", "simba-turbo"], typing.Any
+]

speechifyinc/tts/auth/__init__.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from .types import CreateAccessTokenRequestScope
+
+__all__ = ["CreateAccessTokenRequestScope"]