livekit-plugins-neuphonic 0.1.0__tar.gz → 1.0.0__tar.gz

livekit_plugins_neuphonic-1.0.0/.gitignore

@@ -0,0 +1,168 @@
+**/.vscode
+**/.DS_Store
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+node_modules
+
+credentials.json
+pyrightconfig.json

{livekit_plugins_neuphonic-0.1.0 → livekit_plugins_neuphonic-1.0.0}/PKG-INFO

@@ -1,35 +1,23 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: livekit-plugins-neuphonic
-Version: 0.1.0
-Summary: LiveKit Agents Plugin for Neuphonic
-Home-page: https://github.com/livekit/agents
-License: Apache-2.0
+Version: 1.0.0
+Summary: Neuphonic inference plugin for LiveKit Agents
 Project-URL: Documentation, https://docs.livekit.io
 Project-URL: Website, https://livekit.io/
 Project-URL: Source, https://github.com/livekit/agents
-Keywords: webrtc,realtime,audio,video,livekit
+Author-email: LiveKit <hello@livekit.io>
+License-Expression: Apache-2.0
+Keywords: audio,livekit,neuphonic,realtime,webrtc
 Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Topic :: Multimedia :: Sound/Audio
-Classifier: Topic :: Multimedia :: Video
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0
+Requires-Dist: livekit-agents>=1.0.0
 Description-Content-Type: text/markdown
-Requires-Dist: livekit-agents<1.0.0,>=0.12.16
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: keywords
-Dynamic: license
-Dynamic: project-url
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
 
 # LiveKit Plugins Neuphonic
 

{livekit_plugins_neuphonic-0.1.0 → livekit_plugins_neuphonic-1.0.0}/livekit/plugins/neuphonic/tts.py

@@ -20,9 +20,9 @@ import json
 import os
 import weakref
 from dataclasses import dataclass
-from typing import Optional
 
 import aiohttp
+
 from livekit.agents import (
     APIConnectionError,
     APIConnectOptions,
@@ -31,6 +31,8 @@ from livekit.agents import (
     tts,
     utils,
 )
+from livekit.agents.types import DEFAULT_API_CONNECT_OPTIONS, NOT_GIVEN, NotGivenOr
+from livekit.agents.utils import is_given
 
 from .log import logger
 from .models import TTSEncodings, TTSLangCodes, TTSModels
@@ -49,26 +51,20 @@ class _TTSOptions:
     encoding: TTSEncodings | str
     sampling_rate: int
     speed: float
-    voice_id: str | None = None
+    voice_id: NotGivenOr[str] = NOT_GIVEN
 
     @property
     def model_params(self) -> dict:
-        """Returns a dict of all model parameters and their values."""
-        params = [
-            "voice_id",
-            "model",
-            "lang_code",
-            "encoding",
-            "sampling_rate",
-            "speed",
-        ]
-        values = {}
-
-        for param in params:
-            if hasattr(self, param) and getattr(self, param) is not None:
-                values[param] = getattr(self, param)
-
-        return values
+        """Returns a dictionary of model parameters for API requests."""
+        params = {
+            "voice_id": self.voice_id,
+            "model": self.model,
+            "lang_code": self.lang_code,
+            "encoding": self.encoding,
+            "sampling_rate": self.sampling_rate,
+            "speed": self.speed,
+        }
+        return {k: v for k, v in params.items() if is_given(v) and v is not None}
 
     def get_query_param_string(self):
         """Forms the query parameter string from all model parameters."""
@@ -97,9 +93,7 @@ def _parse_sse_message(message: str) -> dict:
     message = json.loads(value)
 
     if message.get("errors") is not None:
-        raise Exception(
-            f"Status {message.status_code} error received: {message.errors}."
-        )
+        raise Exception(f"Status {message.status_code} error received: {message.errors}.")
 
     return message
 
@@ -109,12 +103,12 @@ class TTS(tts.TTS):
         self,
         *,
         model: TTSModels | str = "neu_hq",
-        voice_id: str | None = None,
+        voice_id: NotGivenOr[str] = NOT_GIVEN,
         lang_code: TTSLangCodes | str = "en",
         encoding: TTSEncodings | str = "pcm_linear",
         speed: float = 1.0,
         sample_rate: int = 22050,
-        api_key: str | None = None,
+        api_key: NotGivenOr[str] = NOT_GIVEN,
         http_session: aiohttp.ClientSession | None = None,
         base_url: str = API_BASE_URL,
     ) -> None:
@@ -133,17 +127,16 @@ class TTS(tts.TTS):
             api_key (str | None, optional): The Neuphonic API key. If not provided, it will be read from the NEUPHONIC_API_TOKEN environment variable.
             http_session (aiohttp.ClientSession | None, optional): An existing aiohttp ClientSession to use. If not provided, a new session will be created.
             base_url (str, optional): The base URL for the Neuphonic API. Defaults to "api.neuphonic.com".
-        """
+        """  # noqa: E501
         super().__init__(
             capabilities=tts.TTSCapabilities(streaming=True),
             sample_rate=sample_rate,
             num_channels=NUM_CHANNELS,
         )
 
-        api_key = api_key or os.environ.get("NEUPHONIC_API_TOKEN")
-
-        if not api_key:
-            raise ValueError("NEUPHONIC_API_TOKEN must be set")
+        neuphonic_api_key = api_key if is_given(api_key) else os.environ.get("NEUPHONIC_API_TOKEN")
+        if not neuphonic_api_key:
+            raise ValueError("API key must be provided or set in NEUPHONIC_API_TOKEN")
 
         self._opts = _TTSOptions(
             model=model,
@@ -152,7 +145,7 @@ class TTS(tts.TTS):
             encoding=encoding,
             speed=speed,
             sampling_rate=sample_rate,
-            api_key=api_key,
+            api_key=neuphonic_api_key,
             base_url=base_url,
         )
 
@@ -189,12 +182,12 @@ class TTS(tts.TTS):
     def update_options(
         self,
         *,
-        model: TTSModels | str = None,
-        voice_id: str | None = None,
-        lang_code: TTSLangCodes | str | None = None,
-        encoding: TTSEncodings | str | None = None,
-        speed: float | None = None,
-        sample_rate: int | None = None,
+        model: NotGivenOr[TTSModels] = NOT_GIVEN,
+        voice_id: NotGivenOr[str] = NOT_GIVEN,
+        lang_code: NotGivenOr[TTSLangCodes] = NOT_GIVEN,
+        encoding: NotGivenOr[TTSEncodings] = NOT_GIVEN,
+        speed: NotGivenOr[float] = NOT_GIVEN,
+        sample_rate: NotGivenOr[int] = NOT_GIVEN,
     ) -> None:
         """
         Update the Text-to-Speech (TTS) configuration options.
@@ -210,20 +203,26 @@ class TTS(tts.TTS):
             encoding (TTSEncodings | str, optional): The audio encoding format.
             speed (float, optional): The audio playback speed.
             sample_rate (int, optional): The audio sample rate in Hz.
-        """
-        self._opts.model = model or self._opts.model
-        self._opts.voice_id = voice_id or self._opts.voice_id
-        self._opts.lang_code = lang_code or self._opts.lang_code
-        self._opts.encoding = encoding or self._opts.encoding
-        self._opts.speed = speed or self._opts.speed
-        self._opts.sampling_rate = sample_rate or self._opts.sampling_rate
+        """  # noqa: E501
+        if is_given(model):
+            self._opts.model = model
+        if is_given(voice_id):
+            self._opts.voice_id = voice_id
+        if is_given(lang_code):
+            self._opts.lang_code = lang_code
+        if is_given(encoding):
+            self._opts.encoding = encoding
+        if is_given(speed):
+            self._opts.speed = speed
+        if is_given(sample_rate):
+            self._opts.sampling_rate = sample_rate
         self._pool.invalidate()
 
     def synthesize(
         self,
         text: str,
         *,
-        conn_options: Optional[APIConnectOptions] = None,
+        conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS,
     ) -> ChunkedStream:
         return ChunkedStream(
             tts=self,
@@ -234,7 +233,7 @@ class TTS(tts.TTS):
         )
 
     def stream(
-        self, *, conn_options: Optional[APIConnectOptions] = None
+        self, *, conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS
     ) -> SynthesizeStream:
         stream = SynthesizeStream(
             tts=self,
@@ -262,7 +261,7 @@ class ChunkedStream(tts.ChunkedStream):
         input_text: str,
         opts: _TTSOptions,
         session: aiohttp.ClientSession,
-        conn_options: Optional[APIConnectOptions] = None,
+        conn_options: APIConnectOptions,
     ) -> None:
         super().__init__(tts=tts, input_text=input_text, conn_options=conn_options)
         self._opts, self._session = opts, session
@@ -310,9 +309,7 @@ class ChunkedStream(tts.ChunkedStream):
                             parsed_message is not None
                             and parsed_message.get("data", {}).get("audio") is not None
                         ):
-                            audio_bytes = base64.b64decode(
-                                parsed_message["data"]["audio"]
-                            )
+                            audio_bytes = base64.b64decode(parsed_message["data"]["audio"])
 
                             for frame in bstream.write(audio_bytes):
                                 emitter.push(frame)
@@ -346,26 +343,6 @@ class SynthesizeStream(tts.SynthesizeStream):
 
     async def _run(self) -> None:
         request_id = utils.shortuuid()
-        request_data = {request_id: {"sent": "", "recv": ""}}
-
-        def _is_all_audio_recv():
-            """Check whether all audio has been recieved."""
-            recv_text = (
-                request_data[request_id]["recv"]
-                .lower()
-                .replace(" ", "")
-                .replace("\n", "")
-                .replace("<stop>", "")
-            )
-            sent_text = (
-                request_data[request_id]["sent"]
-                .lower()
-                .replace(" ", "")
-                .replace("\n", "")
-                .replace("<stop>", "")
-            )
-
-            return sent_text == recv_text
 
         async def _send_task(ws: aiohttp.ClientWebSocketResponse):
             """Stream text to the websocket."""
@@ -376,7 +353,6 @@ class SynthesizeStream(tts.SynthesizeStream):
                     await ws.send_str(json.dumps({"text": "<STOP>"}))
                     continue
 
-                request_data[request_id]["sent"] += data
                 await ws.send_str(json.dumps({"text": data}))
 
         async def _recv_task(ws: aiohttp.ClientWebSocketResponse):
@@ -409,20 +385,17 @@ class SynthesizeStream(tts.SynthesizeStream):
 
                 if data.get("data"):
                     b64data = base64.b64decode(data["data"]["audio"])
-                    recv_text = data["data"]["text"]
                     for frame in audio_bstream.write(b64data):
                         emitter.push(frame)
 
-                    request_data[request_id]["recv"] += recv_text
+                    if data["data"].get("stop"):  # A bool flag, is True when audio reaches "<STOP>"
+                        for frame in audio_bstream.flush():
+                            emitter.push(frame)
+                        emitter.flush()
+                        break  # we are not going to receive any more audio
                 else:
                     logger.error("Unexpected Neuphonic message %s", data)
 
-                if _is_all_audio_recv():
-                    for frame in audio_bstream.flush():
-                        emitter.push(frame)
-                    emitter.flush()
-                    break  # we are not going to receive any more audio
-
         async with self._pool.connection() as ws:
             tasks = [
                 asyncio.create_task(_send_task(ws)),

{livekit_plugins_neuphonic-0.1.0 → livekit_plugins_neuphonic-1.0.0}/livekit/plugins/neuphonic/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.1.0"
+__version__ = "1.0.0"

livekit_plugins_neuphonic-1.0.0/pyproject.toml

@@ -0,0 +1,37 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "livekit-plugins-neuphonic"
+dynamic = ["version"]
+description = "Neuphonic inference plugin for LiveKit Agents"
+readme = "README.md"
+license = "Apache-2.0"
+requires-python = ">=3.9.0"
+authors = [{ name = "LiveKit", email = "hello@livekit.io" }]
+keywords = ["webrtc", "realtime", "audio", "livekit", "neuphonic"]
+classifiers = [
+    "Intended Audience :: Developers",
+    "Topic :: Multimedia :: Sound/Audio",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3 :: Only",
+]
+dependencies = ["livekit-agents>=1.0.0"]
+
+[project.urls]
+Documentation = "https://docs.livekit.io"
+Website = "https://livekit.io/"
+Source = "https://github.com/livekit/agents"
+
+[tool.hatch.version]
+path = "livekit/plugins/neuphonic/version.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["livekit"]
+
+[tool.hatch.build.targets.sdist]
+include = ["/livekit"]

livekit_plugins_neuphonic-0.1.0/livekit_plugins_neuphonic.egg-info/PKG-INFO

@@ -1,46 +0,0 @@
-Metadata-Version: 2.2
-Name: livekit-plugins-neuphonic
-Version: 0.1.0
-Summary: LiveKit Agents Plugin for Neuphonic
-Home-page: https://github.com/livekit/agents
-License: Apache-2.0
-Project-URL: Documentation, https://docs.livekit.io
-Project-URL: Website, https://livekit.io/
-Project-URL: Source, https://github.com/livekit/agents
-Keywords: webrtc,realtime,audio,video,livekit
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Topic :: Multimedia :: Sound/Audio
-Classifier: Topic :: Multimedia :: Video
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3 :: Only
-Requires-Python: >=3.9.0
-Description-Content-Type: text/markdown
-Requires-Dist: livekit-agents<1.0.0,>=0.12.16
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: keywords
-Dynamic: license
-Dynamic: project-url
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
-# LiveKit Plugins Neuphonic
-
-Agent Framework plugin for voice synthesis with [Neuphonic](https://neuphonic.com) API.
-
-## Installation
-
-```bash
-pip install livekit-plugins-neuphonic
-```
-
-## Pre-requisites
-
-You'll need an API key from Neuphonic. It can be set as an environment variable: `NEUPHONIC_API_TOKEN`

livekit_plugins_neuphonic-0.1.0/livekit_plugins_neuphonic.egg-info/SOURCES.txt

@@ -1,14 +0,0 @@
-README.md
-pyproject.toml
-setup.py
-livekit/plugins/neuphonic/__init__.py
-livekit/plugins/neuphonic/log.py
-livekit/plugins/neuphonic/models.py
-livekit/plugins/neuphonic/py.typed
-livekit/plugins/neuphonic/tts.py
-livekit/plugins/neuphonic/version.py
-livekit_plugins_neuphonic.egg-info/PKG-INFO
-livekit_plugins_neuphonic.egg-info/SOURCES.txt
-livekit_plugins_neuphonic.egg-info/dependency_links.txt
-livekit_plugins_neuphonic.egg-info/requires.txt
-livekit_plugins_neuphonic.egg-info/top_level.txt

livekit_plugins_neuphonic-0.1.0/livekit_plugins_neuphonic.egg-info/dependency_links.txt

@@ -1 +0,0 @@
-

livekit_plugins_neuphonic-0.1.0/livekit_plugins_neuphonic.egg-info/requires.txt

@@ -1 +0,0 @@
-livekit-agents<1.0.0,>=0.12.16

livekit_plugins_neuphonic-0.1.0/livekit_plugins_neuphonic.egg-info/top_level.txt

@@ -1 +0,0 @@
-livekit

livekit_plugins_neuphonic-0.1.0/pyproject.toml

@@ -1,3 +0,0 @@
-[build-system]
-requires = ["setuptools>=61.0"]
-build-backend = "setuptools.build_meta"

livekit_plugins_neuphonic-0.1.0/setup.cfg

@@ -1,4 +0,0 @@
-[egg_info]
-tag_build = 
-tag_date = 0
-

livekit_plugins_neuphonic-0.1.0/setup.py

@@ -1,58 +0,0 @@
-# Copyright 2023 LiveKit, Inc.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-import os
-import pathlib
-
-import setuptools
-import setuptools.command.build_py
-
-here = pathlib.Path(__file__).parent.resolve()
-about = {}
-with open(
-    os.path.join(here, "livekit", "plugins", "neuphonic", "version.py"), "r"
-) as f:
-    exec(f.read(), about)
-
-
-setuptools.setup(
-    name="livekit-plugins-neuphonic",
-    version=about["__version__"],
-    description="LiveKit Agents Plugin for Neuphonic",
-    long_description=(here / "README.md").read_text(encoding="utf-8"),
-    long_description_content_type="text/markdown",
-    url="https://github.com/livekit/agents",
-    cmdclass={},
-    classifiers=[
-        "Intended Audience :: Developers",
-        "License :: OSI Approved :: Apache Software License",
-        "Topic :: Multimedia :: Sound/Audio",
-        "Topic :: Multimedia :: Video",
-        "Topic :: Scientific/Engineering :: Artificial Intelligence",
-        "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.10",
-        "Programming Language :: Python :: 3 :: Only",
-    ],
-    keywords=["webrtc", "realtime", "audio", "video", "livekit"],
-    license="Apache-2.0",
-    packages=setuptools.find_namespace_packages(include=["livekit.*"]),
-    python_requires=">=3.9.0",
-    install_requires=["livekit-agents>=0.12.16,<1.0.0"],
-    project_urls={
-        "Documentation": "https://docs.livekit.io",
-        "Website": "https://livekit.io/",
-        "Source": "https://github.com/livekit/agents",
-    },
-)