feat: speechify.voices.list()

.gitignore

@@ -1,3 +1,4 @@
 _site/
 
 .DS_Store
+**/__pycache__/**

speechify-python-sdk/LICENSE.txt

@@ -0,0 +1,9 @@
+MIT License
+
+Copyright (c) 2024-present Irwansyah <[email protected]>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

speechify-python-sdk/README.md

@@ -0,0 +1,21 @@
+# Speechify Python SDK
+
+[![PyPI - Version](https://img.shields.io/pypi/v/speechify-python-sdk.svg)](https://pypi.org/project/speechify-python-sdk)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/speechify-python-sdk.svg)](https://pypi.org/project/speechify-python-sdk)
+
+-----
+
+## Table of Contents
+
+- [Installation](#installation)
+- [License](#license)
+
+## Installation
+
+```console
+pip install speechify-python-sdk
+```
+
+## License
+
+`speechify-python-sdk` is distributed under the terms of the [MIT](https://spdx.org/licenses/MIT.html) license.

speechify-python-sdk/pyproject.toml

@@ -0,0 +1,63 @@
+[build-system]
+requires = ["hatchling", "hatch-requirements-txt"]
+build-backend = "hatchling.build"
+
+[project]
+name = "speechify-python-sdk"
+dynamic = ["dependencies", "version"]
+description = 'Python SDK for Speechify API'
+readme = "README.md"
+requires-python = ">=3.8"
+license = "MIT"
+keywords = []
+authors = [
+  { name = "Irwansyah", email = "[email protected]" },
+]
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3.8",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: Implementation :: CPython",
+  "Programming Language :: Python :: Implementation :: PyPy",
+]
+
+[project.urls]
+Documentation = "https://github.com/Irwansyah/speechify-python-sdk#readme"
+Issues = "https://github.com/Irwansyah/speechify-python-sdk/issues"
+Source = "https://github.com/Irwansyah/speechify-python-sdk"
+
+[tool.hatch.metadata.hooks.requirements_txt]
+files = ["requirements.txt"]
+
+[tool.hatch.version]
+path = "src/speechify_python_sdk/__about__.py"
+
+[tool.hatch.envs.types]
+extra-dependencies = [
+  "mypy>=1.0.0",
+]
+[tool.hatch.envs.types.scripts]
+check = "mypy --install-types --non-interactive {args:src/speechify_python_sdk tests}"
+
+[tool.coverage.run]
+source_pkgs = ["speechify_python_sdk", "tests"]
+branch = true
+parallel = true
+omit = [
+  "src/speechify_python_sdk/__about__.py",
+]
+
+[tool.coverage.paths]
+speechify_python_sdk = ["src/speechify_python_sdk", "*/speechify-python-sdk/src/speechify_python_sdk"]
+tests = ["tests", "*/speechify-python-sdk/tests"]
+
+[tool.coverage.report]
+exclude_lines = [
+  "no cov",
+  "if __name__ == .__main__.:",
+  "if TYPE_CHECKING:",
+]

speechify-python-sdk/requirements.txt

@@ -0,0 +1,4 @@
+pydantic==2.10.4
+pytest==8.3.4
+python-dotenv==1.0.1
+Requests==2.32.3

speechify-python-sdk/src/speechify_python_sdk/__about__.py

@@ -0,0 +1,4 @@
+# SPDX-FileCopyrightText: 2024-present Irwansyah <[email protected]>
+#
+# SPDX-License-Identifier: MIT
+__version__ = "0.0.1"

speechify-python-sdk/src/speechify_python_sdk/__init__.py

@@ -0,0 +1,3 @@
+# SPDX-FileCopyrightText: 2024-present Irwansyah <[email protected]>
+#
+# SPDX-License-Identifier: MIT

speechify-python-sdk/src/speechify_python_sdk/lib/config.py

@@ -0,0 +1,27 @@
+import os
+
+from speechify_python_sdk import __about__
+from speechify_python_sdk.lib.speechify_requests import SpeechifyRequests
+
+
+class Config:
+    SPEECHIFY_API_KEY = os.environ.get("SPEECHIFY_API_KEY", "")
+
+    @classmethod
+    def sdk_version(cls):
+        return __about__.__version__
+
+    @classmethod
+    def __setup_requests_base_config__(cls):
+        SpeechifyRequests.api_key = Config.SPEECHIFY_API_KEY
+        SpeechifyRequests.sdk_version = Config.sdk_version()
+
+    @classmethod
+    def use_prod(cls):
+        cls.__setup_requests_base_config__()
+        SpeechifyRequests.use_prod()
+
+    @classmethod
+    def use_dev(cls):
+        cls.__setup_requests_base_config__()
+        SpeechifyRequests.use_dev

speechify-python-sdk/src/speechify_python_sdk/lib/speechify_audio.py

@@ -0,0 +1,36 @@
+from typing import Generator
+
+from speechify_python_sdk.models.generate_audio_request import GenerateAudioRequest
+from speechify_python_sdk.models.generate_audio_response import GenerateAudioResponse
+
+
+class SpeechifyTTS:
+
+    def text_to_speech(self, request: GenerateAudioRequest) -> GenerateAudioResponse:
+        """
+        Gets the speech data for the given input
+
+        Arguments:
+            request: The request parameters
+
+        Returns:
+            A GenerateAudioResponse
+
+        Raises:
+            HTTPError:
+
+                - 400 Invalid request parameters
+                - 402 Insufficient credits
+                - 403 Access Denied
+                - 500 Internal Server Error
+        """
+        pass
+
+    def stream(self, request: GenerateAudioRequest):
+        """
+        Gets the stream speech for the given input
+
+        Returns:
+            Base64 encoded of the the audio data
+        """
+        pass

speechify-python-sdk/src/speechify_python_sdk/lib/speechify_auth.py

@@ -0,0 +1,17 @@
+from speechify_python_sdk.models.generate_oauth_token_request import (
+    GenerateOAuthTokenRequest,
+)
+
+
+class SpeechifyAuth:
+    def generate_oauth_token(self, request: GenerateOAuthTokenRequest):
+        """
+        Create a new API token for the logged in user
+
+        Arguments:
+            request: The request parameters
+
+        Returns:
+            A GenerateOAuthTokenResponse
+        """
+        pass

speechify-python-sdk/src/speechify_python_sdk/lib/speechify_requests.py

@@ -0,0 +1,46 @@
+import requests
+
+
+class SpeechifyRequests:
+    """
+    Responsible to do all HTTP requests to Speechify REST API
+    """
+
+    api_url = "https://api.sws.speechify.com"
+    api_key = ""
+    sdk_version = ""
+
+    @classmethod
+    def use_prod(cls):
+        cls.api_url = "https://api.sws.speechify.com"
+
+    @classmethod
+    def use_dev(cls):
+        cls.api_url = "https://api.sws.speechify.dev"
+
+    @classmethod
+    def set_api_key(cls, new_api_key: str):
+        cls.api_key = new_api_key
+
+    @classmethod
+    def set_config(cls, api_key: str, sdk_version: str, is_use_prod: bool):
+        cls.api_key = api_key
+        cls.sdk_version = sdk_version
+        cls.use_prod() if is_use_prod else cls.use_dev()
+
+    def __get_headers__(self):
+        headers = {
+            "Authorization": f"Bearer {SpeechifyRequests.api_key}",
+            "X-Speechify-SDK": "python",
+            "X-Speechify-SDK-Version": SpeechifyRequests.sdk_version,
+        }
+
+        return headers
+
+    def fetch_json(self, path: str):
+        headers = self.__get_headers__()
+
+        response = requests.get(f"{SpeechifyRequests.api_url}{path}", headers=headers)
+        response.raise_for_status()
+
+        return response.json()

speechify-python-sdk/src/speechify_python_sdk/lib/speechify_voices.py

@@ -0,0 +1,49 @@
+from typing import List
+
+from speechify_python_sdk.lib.speechify_requests import SpeechifyRequests
+from speechify_python_sdk.models.voices_response import VoicesResponse
+
+
+class SpeechifyVoices:
+
+    def __init__(self, requests: SpeechifyRequests):
+        self.requests = requests
+
+    def list(self) -> List[VoicesResponse]:
+        """
+        Gets the list of voices available for the user
+
+        Returns:
+            An empty array if no voices found or
+            list of VoicesResponse
+
+        Raises:
+            - 500 Internal Server Error
+
+        """
+        data = self.requests.fetch_json("/v1/voices")
+
+        return list(
+            map(
+                lambda item: VoicesResponse.model_validate(item),
+                data,
+            )
+        )
+
+    def create(self):
+        """
+        Create a personal (cloned) voice for the user
+
+        Raises:
+            - 400 Invalid request params
+            - 402 Current billing plan does not have access to voice cloning
+            - 500 Internal Server Error
+
+        Returns:
+            A CreateVoiceResponse
+
+        """
+        pass
+
+    def delete(self):
+        pass

speechify-python-sdk/src/speechify_python_sdk/models/create_voice_request.py

@@ -0,0 +1,5 @@
+from pydantic import BaseModel
+
+
+class CreateVoiceRequest(BaseModel):
+    pass

speechify-python-sdk/src/speechify_python_sdk/models/create_voice_response.py

@@ -0,0 +1,11 @@
+from typing import List
+from pydantic import BaseModel
+
+from speechify_python_sdk.models.voice_model import VoiceModel
+
+
+class CreateVoiceResponse(BaseModel):
+    id: str
+    display_name: str
+    type: str
+    models: List[VoiceModel]

speechify-python-sdk/src/speechify_python_sdk/models/generate_audio_request.py

@@ -0,0 +1,51 @@
+from typing import Literal, Optional
+from pydantic import BaseModel
+
+
+class GenerateAudioRequest(BaseModel):
+    """
+    Wrap the request parameters to generate an audio for an input text.
+    """
+
+    def __init__(
+        self,
+        input: str,
+        voice_id: str,
+        audio_format: Optional[Literal["wav", "mp3", "ogg", "aac"]] = None,
+        language: Optional[str] = None,
+        model: Optional[
+            Literal["simba-english", "simba-multilingual", "simba-turbo"]
+        ] = None,
+        loudness_normalization=Optional[bool],
+    ):
+        """
+        Create the parameters wrapper.
+
+        Args:
+          input: Plain text or SSML to be synthesized to speech. Refer to https://docs.sws.speechify.com/docs/api-limits for the input size limits.
+          voice_id: Id of the voice to be used for synthesizing speech. Refer to :func:`~speechify_sdk.lib.speechify_voices.SpeechifyVoices.list` for available voices.
+          audio_format: 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: 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: Model used for audio synthesis. Defaults to simba-base. It could be:
+
+                        - simba-base ModelBase ModelBase is deprecated. Use simba-english or simba-multilingual instead. @deprecated
+                        - simba-english ModelEnglish
+                        - simba-multilingual ModelMultilingual
+                        - simba-turbo ModelTurbo
+
+          loudness_normalization: Determines whether to normalize the audio loudness to a standard level. When enabled, loudness normalization aligns the audio output to the following standards:
+
+                        - Integrated loudness: -14 LUFS
+                        - True peak: -2 dBTP
+                        - Loudness range: 7 LU
+                        If disabled, the audio loudness will match the original loudness of the selected voice, which may vary significantly and be either too quiet or too loud. Enabling loudness normalization can increase latency due to additional processing required for audio level adjustments.
+
+        Returns:
+          A  new instance of the request model containing all the parameters.
+        """
+        self.input = input
+        self.voice_id = voice_id
+        self.audio_format = audio_format
+        self.language = language
+        self.model = model
+        self.loudness_normalization = loudness_normalization

speechify-python-sdk/src/speechify_python_sdk/models/generate_audio_response.py

@@ -0,0 +1,28 @@
+from typing import List, Literal
+from pydantic import BaseModel
+
+
+class SpeechMarkChunk(BaseModel):
+    end: int
+    end_time: float
+    start: int
+    start_time: float
+    type: str
+    value: str
+
+
+class SpeechMarks(SpeechMarkChunk):
+    end: int
+    end_time: float
+    start: int
+    start_time: float
+    type: str
+    value: str
+    chunks: List[SpeechMarkChunk]
+
+
+class GenerateAudioResponse(BaseModel):
+    audio_data: str
+    audio_format: Literal["wav", "mp3", "ogg", "aac"]
+    billable_characters_count: int
+    speech_marks: SpeechMarks