murf 1.2.0__py3-none-any.whl → 1.2.2__py3-none-any.whl

murf/text_to_speech/client.py

@@ -54,6 +54,7 @@ class TextToSpeechClient:
             The text that is to be synthesised. e.g. 'Hello there [pause 1s] friend'
 
         voice_id : str
+            Use the GET /v1/speech/voices api to find supported voiceIds.
 
         audio_duration : typing.Optional[float]
             This parameter allows specifying the duration (in seconds) for the generated audio. If the value is 0, this parameter will be ignored. Only available for Gen2 model.
@@ -72,7 +73,7 @@ class TextToSpeechClient:
 
         multi_native_locale : typing.Optional[str]
             Specifies the language for the generated audio, enabling a voice to speak in multiple languages natively. Only available in the Gen2 model.
-            Valid values: "en-US", "en-UK", "es-ES", etc. Use the GET /v1/speed/voices endpoint to retrieve the list of available voices and languages.
+            Valid values: "en-US", "en-UK", "es-ES", etc. Use the GET /v1/speech/voices endpoint to retrieve the list of available voices and languages.
 
         pitch : typing.Optional[int]
             Pitch of the voiceover
@@ -209,6 +210,157 @@ class TextToSpeechClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def stream(
+        self,
+        *,
+        text: str,
+        voice_id: str,
+        channel_type: typing.Optional[str] = OMIT,
+        format: typing.Optional[str] = OMIT,
+        multi_native_locale: typing.Optional[str] = OMIT,
+        pitch: typing.Optional[int] = OMIT,
+        rate: typing.Optional[int] = OMIT,
+        sample_rate: typing.Optional[float] = OMIT,
+        style: typing.Optional[str] = OMIT,
+        variation: typing.Optional[int] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.Iterator[bytes]:
+        """
+        Returns a streaming output of generated audio
+
+        Parameters
+        ----------
+        text : str
+            The text that is to be synthesised. e.g. 'Hello there [pause 1s] friend'
+
+        voice_id : str
+            Use the GET /v1/speech/voices api to find supported voiceIds.
+
+        channel_type : typing.Optional[str]
+            Valid values: STEREO, MONO
+
+        format : typing.Optional[str]
+            Format of the generated audio file. Valid values: MP3, WAV
+
+        multi_native_locale : typing.Optional[str]
+            Specifies the language for the generated audio, enabling a voice to speak in multiple languages natively. Only available in the Gen2 model.
+            Valid values: "en-US", "en-UK", "es-ES", etc. Use the GET /v1/speech/voices endpoint to retrieve the list of available voices and languages.
+
+        pitch : typing.Optional[int]
+            Pitch of the voiceover
+
+        rate : typing.Optional[int]
+            Speed of the voiceover
+
+        sample_rate : typing.Optional[float]
+            Valid values are 8000, 24000, 44100, 48000
+
+        style : typing.Optional[str]
+            The voice style to be used for voiceover generation.
+
+        variation : typing.Optional[int]
+            Higher values will add more variation in terms of Pause, Pitch, and Speed to the voice. Only available for Gen2 model.
+
+        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]
+            Ok
+
+        Examples
+        --------
+        from murf import Murf
+
+        client = Murf(
+            api_key="YOUR_API_KEY",
+        )
+        client.text_to_speech.stream()
+        """
+        with self._client_wrapper.httpx_client.stream(
+            "v1/speech/stream",
+            method="POST",
+            json={
+                "channelType": channel_type,
+                "format": format,
+                "multiNativeLocale": multi_native_locale,
+                "pitch": pitch,
+                "rate": rate,
+                "sampleRate": sample_rate,
+                "style": style,
+                "text": text,
+                "variation": variation,
+                "voiceId": voice_id,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            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(),
+                            ),
+                        )
+                    )
+                if _response.status_code == 503:
+                    raise ServiceUnavailableError(
+                        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 get_voices(
         self, *, token: typing.Optional[str] = None, request_options: typing.Optional[RequestOptions] = None
     ) -> typing.List[ApiVoice]:
@@ -331,6 +483,7 @@ class AsyncTextToSpeechClient:
             The text that is to be synthesised. e.g. 'Hello there [pause 1s] friend'
 
         voice_id : str
+            Use the GET /v1/speech/voices api to find supported voiceIds.
 
         audio_duration : typing.Optional[float]
             This parameter allows specifying the duration (in seconds) for the generated audio. If the value is 0, this parameter will be ignored. Only available for Gen2 model.
@@ -349,7 +502,7 @@ class AsyncTextToSpeechClient:
 
         multi_native_locale : typing.Optional[str]
             Specifies the language for the generated audio, enabling a voice to speak in multiple languages natively. Only available in the Gen2 model.
-            Valid values: "en-US", "en-UK", "es-ES", etc. Use the GET /v1/speed/voices endpoint to retrieve the list of available voices and languages.
+            Valid values: "en-US", "en-UK", "es-ES", etc. Use the GET /v1/speech/voices endpoint to retrieve the list of available voices and languages.
 
         pitch : typing.Optional[int]
             Pitch of the voiceover
@@ -494,6 +647,165 @@ class AsyncTextToSpeechClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def stream(
+        self,
+        *,
+        text: str,
+        voice_id: str,
+        channel_type: typing.Optional[str] = OMIT,
+        format: typing.Optional[str] = OMIT,
+        multi_native_locale: typing.Optional[str] = OMIT,
+        pitch: typing.Optional[int] = OMIT,
+        rate: typing.Optional[int] = OMIT,
+        sample_rate: typing.Optional[float] = OMIT,
+        style: typing.Optional[str] = OMIT,
+        variation: typing.Optional[int] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.AsyncIterator[bytes]:
+        """
+        Returns a streaming output of generated audio
+
+        Parameters
+        ----------
+        text : str
+            The text that is to be synthesised. e.g. 'Hello there [pause 1s] friend'
+
+        voice_id : str
+            Use the GET /v1/speech/voices api to find supported voiceIds.
+
+        channel_type : typing.Optional[str]
+            Valid values: STEREO, MONO
+
+        format : typing.Optional[str]
+            Format of the generated audio file. Valid values: MP3, WAV
+
+        multi_native_locale : typing.Optional[str]
+            Specifies the language for the generated audio, enabling a voice to speak in multiple languages natively. Only available in the Gen2 model.
+            Valid values: "en-US", "en-UK", "es-ES", etc. Use the GET /v1/speech/voices endpoint to retrieve the list of available voices and languages.
+
+        pitch : typing.Optional[int]
+            Pitch of the voiceover
+
+        rate : typing.Optional[int]
+            Speed of the voiceover
+
+        sample_rate : typing.Optional[float]
+            Valid values are 8000, 24000, 44100, 48000
+
+        style : typing.Optional[str]
+            The voice style to be used for voiceover generation.
+
+        variation : typing.Optional[int]
+            Higher values will add more variation in terms of Pause, Pitch, and Speed to the voice. Only available for Gen2 model.
+
+        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]
+            Ok
+
+        Examples
+        --------
+        import asyncio
+
+        from murf import AsyncMurf
+
+        client = AsyncMurf(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.text_to_speech.stream()
+
+
+        asyncio.run(main())
+        """
+        async with self._client_wrapper.httpx_client.stream(
+            "v1/speech/stream",
+            method="POST",
+            json={
+                "channelType": channel_type,
+                "format": format,
+                "multiNativeLocale": multi_native_locale,
+                "pitch": pitch,
+                "rate": rate,
+                "sampleRate": sample_rate,
+                "style": style,
+                "text": text,
+                "variation": variation,
+                "voiceId": voice_id,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            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(),
+                            ),
+                        )
+                    )
+                if _response.status_code == 503:
+                    raise ServiceUnavailableError(
+                        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 get_voices(
         self, *, token: typing.Optional[str] = None, request_options: typing.Optional[RequestOptions] = None
     ) -> typing.List[ApiVoice]:

murf/types/__init__.py

@@ -8,6 +8,7 @@ from .api_project_response_dubbing_type import ApiProjectResponseDubbingType
 from .api_voice import ApiVoice
 from .api_voice_gender import ApiVoiceGender
 from .auth_token_response import AuthTokenResponse
+from .character_count import CharacterCount
 from .dub_api_detail_response import DubApiDetailResponse
 from .dub_job_status_response import DubJobStatusResponse
 from .form_data_content_disposition import FormDataContentDisposition
@@ -15,11 +16,15 @@ from .generate_speech_response import GenerateSpeechResponse
 from .group_api_project_response import GroupApiProjectResponse
 from .locale_response import LocaleResponse
 from .locale_response_supports_item import LocaleResponseSupportsItem
+from .metadata import Metadata
+from .murf_api_translation_response import MurfApiTranslationResponse
 from .pronunciation_detail import PronunciationDetail
 from .pronunciation_detail_type import PronunciationDetailType
 from .source_locale_response import SourceLocaleResponse
+from .speech_to_speech_response import SpeechToSpeechResponse
 from .style_details import StyleDetails
-from .word_duration import WordDuration
+from .translation import Translation
+from .word_duration_response import WordDurationResponse
 
 __all__ = [
     "ApiJobResponse",
@@ -30,6 +35,7 @@ __all__ = [
     "ApiVoice",
     "ApiVoiceGender",
     "AuthTokenResponse",
+    "CharacterCount",
     "DubApiDetailResponse",
     "DubJobStatusResponse",
     "FormDataContentDisposition",
@@ -37,9 +43,13 @@ __all__ = [
     "GroupApiProjectResponse",
     "LocaleResponse",
     "LocaleResponseSupportsItem",
+    "Metadata",
+    "MurfApiTranslationResponse",
     "PronunciationDetail",
     "PronunciationDetailType",
     "SourceLocaleResponse",
+    "SpeechToSpeechResponse",
     "StyleDetails",
-    "WordDuration",
+    "Translation",
+    "WordDurationResponse",
 ]

murf/types/character_count.py

@@ -0,0 +1,20 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ..core.pydantic_utilities import UniversalBaseModel
+import typing
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class CharacterCount(UniversalBaseModel):
+    total_source_text_length: typing.Optional[int] = None
+    total_translated_text_length: typing.Optional[int] = None
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

murf/types/generate_speech_response.py

@@ -2,37 +2,33 @@
 
 from ..core.pydantic_utilities import UniversalBaseModel
 import typing_extensions
-import typing
 from ..core.serialization import FieldMetadata
 import pydantic
-from .word_duration import WordDuration
+import typing
+from .word_duration_response import WordDurationResponse
 from ..core.pydantic_utilities import IS_PYDANTIC_V2
 
 
 class GenerateSpeechResponse(UniversalBaseModel):
-    audio_file: typing_extensions.Annotated[typing.Optional[str], FieldMetadata(alias="audioFile")] = None
-    audio_length_in_seconds: typing_extensions.Annotated[
-        typing.Optional[float], FieldMetadata(alias="audioLengthInSeconds")
-    ] = None
-    consumed_character_count: typing_extensions.Annotated[
-        typing.Optional[int], FieldMetadata(alias="consumedCharacterCount")
-    ] = pydantic.Field(default=None)
+    audio_file: typing_extensions.Annotated[str, FieldMetadata(alias="audioFile")]
+    audio_length_in_seconds: typing_extensions.Annotated[float, FieldMetadata(alias="audioLengthInSeconds")]
+    consumed_character_count: typing_extensions.Annotated[int, FieldMetadata(alias="consumedCharacterCount")] = (
+        pydantic.Field()
+    )
     """
     Number of characters consumed so far in the current billing cycle.
     """
 
     encoded_audio: typing_extensions.Annotated[typing.Optional[str], FieldMetadata(alias="encodedAudio")] = None
-    remaining_character_count: typing_extensions.Annotated[
-        typing.Optional[int], FieldMetadata(alias="remainingCharacterCount")
-    ] = pydantic.Field(default=None)
+    remaining_character_count: typing_extensions.Annotated[int, FieldMetadata(alias="remainingCharacterCount")] = (
+        pydantic.Field()
+    )
     """
     Remaining number of characters available for synthesis in the current billing cycle.
     """
 
     warning: typing.Optional[str] = None
-    word_durations: typing_extensions.Annotated[
-        typing.Optional[typing.List[WordDuration]], FieldMetadata(alias="wordDurations")
-    ] = None
+    word_durations: typing_extensions.Annotated[typing.List[WordDurationResponse], FieldMetadata(alias="wordDurations")]
 
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2

murf/types/metadata.py

@@ -0,0 +1,22 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ..core.pydantic_utilities import UniversalBaseModel
+import typing
+from .character_count import CharacterCount
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class Metadata(UniversalBaseModel):
+    character_count: typing.Optional[CharacterCount] = None
+    credits_used: typing.Optional[float] = None
+    target_language: typing.Optional[str] = None
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

murf/types/murf_api_translation_response.py

@@ -0,0 +1,22 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ..core.pydantic_utilities import UniversalBaseModel
+import typing
+from .metadata import Metadata
+from .translation import Translation
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class MurfApiTranslationResponse(UniversalBaseModel):
+    metadata: typing.Optional[Metadata] = None
+    translations: typing.Optional[typing.List[Translation]] = None
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

murf/types/speech_to_speech_response.py

@@ -0,0 +1,47 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ..core.pydantic_utilities import UniversalBaseModel
+import pydantic
+import typing
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
+
+
+class SpeechToSpeechResponse(UniversalBaseModel):
+    audio_file: str = pydantic.Field()
+    """
+    The URL or path of the generated audio file.
+    """
+
+    audio_length_in_seconds: float = pydantic.Field()
+    """
+    Length of the generated audio in seconds.
+    """
+
+    encoded_audio: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Base64 encoded string of the generated audio. Used when audio is returned directly in the response.
+    """
+
+    remaining_character_count: int = pydantic.Field()
+    """
+    Remaining number of characters available for synthesis in the current billing cycle.
+    """
+
+    transcription: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Transcript of the generated audio, if transcription was requested.
+    """
+
+    warning: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Any warning or informational message related to the audio generation process.
+    """
+
+    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

murf/types/translation.py

@@ -0,0 +1,20 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from ..core.pydantic_utilities import UniversalBaseModel
+import typing
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
+import pydantic
+
+
+class Translation(UniversalBaseModel):
+    source_text: typing.Optional[str] = None
+    translated_text: typing.Optional[str] = None
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

murf/types/{word_duration.py → word_duration_response.py}

@@ -4,19 +4,33 @@ from ..core.pydantic_utilities import UniversalBaseModel
 import typing_extensions
 import typing
 from ..core.serialization import FieldMetadata
-from ..core.pydantic_utilities import IS_PYDANTIC_V2
 import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2
 
 
-class WordDuration(UniversalBaseModel):
+class WordDurationResponse(UniversalBaseModel):
     end_ms: typing_extensions.Annotated[typing.Optional[int], FieldMetadata(alias="endMs")] = None
     pitch_scale_maximum: typing_extensions.Annotated[
         typing.Optional[float], FieldMetadata(alias="pitchScaleMaximum")
-    ] = None
+    ] = pydantic.Field(default=None)
+    """
+    This field has been deprecated.
+    """
+
     pitch_scale_minimum: typing_extensions.Annotated[
         typing.Optional[float], FieldMetadata(alias="pitchScaleMinimum")
-    ] = None
-    source_word_index: typing_extensions.Annotated[typing.Optional[int], FieldMetadata(alias="sourceWordIndex")] = None
+    ] = pydantic.Field(default=None)
+    """
+    This field has been deprecated.
+    """
+
+    source_word_index: typing_extensions.Annotated[typing.Optional[int], FieldMetadata(alias="sourceWordIndex")] = (
+        pydantic.Field(default=None)
+    )
+    """
+    This field has been deprecated.
+    """
+
     start_ms: typing_extensions.Annotated[typing.Optional[int], FieldMetadata(alias="startMs")] = None
     word: typing.Optional[str] = None
 

murf/voice_changer/__init__.py

@@ -0,0 +1,2 @@
+# This file was auto-generated by Fern from our API Definition.
+