livekit-plugins-inworld 1.1.4__tar.gz

livekit_plugins_inworld-1.1.4/.gitignore

@@ -0,0 +1,172 @@
+**/.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
+
+# trunk
+.trunk/
+
+# 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
+docs/

livekit_plugins_inworld-1.1.4/PKG-INFO

@@ -0,0 +1,54 @@
+Metadata-Version: 2.4
+Name: livekit-plugins-inworld
+Version: 1.1.4
+Summary: Agent Framework plugin for voice synthesis with Inworld's API.
+Project-URL: Documentation, https://docs.livekit.io
+Project-URL: Website, https://livekit.io/
+Project-URL: Source, https://github.com/livekit/agents
+Author-email: LiveKit <hello@livekit.io>
+License-Expression: Apache-2.0
+Keywords: audio,inworld,livekit,realtime,video,webrtc
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Multimedia :: Video
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9.0
+Requires-Dist: livekit-agents>=1.1.4
+Description-Content-Type: text/markdown
+
+# Inworld plugin for LiveKit Agents
+
+Support for voice synthesis with [Inworld](https://beta.docs.inworld.ai/api-reference/ttsAPI/texttospeech/synthesize-speech).
+
+See [https://docs.livekit.io/agents/integrations/tts/inworld/](https://docs.livekit.io/agents/integrations/tts/inworld/) for more information.
+
+## Installation
+
+```bash
+pip install livekit-plugins-inworld
+```
+
+## Authentication
+
+The Inworld plugin requires a [Inworld API key](https://studio.inworld.ai/login).
+
+Set `INWORLD_API_KEY` in your `.env` file.
+
+## Usage
+
+Use Inworld TTS within an `AgentSession` or as a standalone speech generator. For example,
+you can use this TTS in the [Voice AI quickstart](/agents/start/voice-ai/).
+
+```python
+from livekit.plugins import inworld
+
+session = AgentSession(
+   tts=inworld.TTS(voice="Ashley")
+   # ... llm, stt, etc.
+)
+```

livekit_plugins_inworld-1.1.4/README.md

@@ -0,0 +1,31 @@
+# Inworld plugin for LiveKit Agents
+
+Support for voice synthesis with [Inworld](https://beta.docs.inworld.ai/api-reference/ttsAPI/texttospeech/synthesize-speech).
+
+See [https://docs.livekit.io/agents/integrations/tts/inworld/](https://docs.livekit.io/agents/integrations/tts/inworld/) for more information.
+
+## Installation
+
+```bash
+pip install livekit-plugins-inworld
+```
+
+## Authentication
+
+The Inworld plugin requires a [Inworld API key](https://studio.inworld.ai/login).
+
+Set `INWORLD_API_KEY` in your `.env` file.
+
+## Usage
+
+Use Inworld TTS within an `AgentSession` or as a standalone speech generator. For example,
+you can use this TTS in the [Voice AI quickstart](/agents/start/voice-ai/).
+
+```python
+from livekit.plugins import inworld
+
+session = AgentSession(
+   tts=inworld.TTS(voice="Ashley")
+   # ... llm, stt, etc.
+)
+```

livekit_plugins_inworld-1.1.4/livekit/plugins/inworld/__init__.py

@@ -0,0 +1,47 @@
+# Copyright 2025 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.
+
+"""Inworld plugin for LiveKit Agents
+
+See https://docs.livekit.io/agents/integrations/tts/inworld/ for more information.
+"""
+
+from .tts import TTS
+from .version import __version__
+
+__all__ = [
+    "TTS",
+    "__version__",
+]
+
+from livekit.agents import Plugin
+
+from .log import logger
+
+
+class InworldPlugin(Plugin):
+    def __init__(self) -> None:
+        super().__init__(__name__, __version__, __package__, logger)
+
+
+Plugin.register_plugin(InworldPlugin())
+
+# Cleanup docs of unexported modules
+_module = dir()
+NOT_IN_ALL = [m for m in _module if m not in __all__]
+
+__pdoc__ = {}
+
+for n in NOT_IN_ALL:
+    __pdoc__[n] = False

livekit_plugins_inworld-1.1.4/livekit/plugins/inworld/log.py

@@ -0,0 +1,3 @@
+import logging
+
+logger = logging.getLogger("livekit.plugins.inworld")

livekit_plugins_inworld-1.1.4/livekit/plugins/inworld/tts.py

@@ -0,0 +1,263 @@
+# Copyright 2025 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.
+
+from __future__ import annotations
+
+import asyncio
+import base64
+import json
+import os
+from dataclasses import dataclass, replace
+from typing import Any, Literal, Union
+from urllib.parse import urljoin
+
+import aiohttp
+
+from livekit.agents import tts, utils
+from livekit.agents._exceptions import (
+    APIConnectionError,
+    APIStatusError,
+    APITimeoutError,
+)
+from livekit.agents.types import (
+    DEFAULT_API_CONNECT_OPTIONS,
+    NOT_GIVEN,
+    APIConnectOptions,
+    NotGivenOr,
+)
+
+DEFAULT_BIT_RATE = 64000
+DEFAULT_ENCODING = "OGG_OPUS"
+DEFAULT_MODEL = "inworld-tts-1"
+DEFAULT_SAMPLE_RATE = 48000
+DEFAULT_URL = "https://api.inworld.ai/"
+DEFAULT_VOICE = "Ashley"
+NUM_CHANNELS = 1
+
+Encoding = Union[Literal["LINEAR16", "MP3", "OGG_OPUS"], str]
+
+
+@dataclass
+class _TTSOptions:
+    model: str
+    encoding: Encoding
+    voice: str
+    sample_rate: int
+    bit_rate: NotGivenOr[int] = NOT_GIVEN
+    pitch: NotGivenOr[float] = NOT_GIVEN
+    speaking_rate: NotGivenOr[float] = NOT_GIVEN
+    temperature: NotGivenOr[float] = NOT_GIVEN
+
+    @property
+    def mime_type(self) -> str:
+        if self.encoding == "MP3":
+            return "audio/mpeg"
+        elif self.encoding == "OGG_OPUS":
+            return "audio/ogg"
+        else:
+            return "audio/wav"
+
+
+class TTS(tts.TTS):
+    def __init__(
+        self,
+        *,
+        api_key: NotGivenOr[str] = NOT_GIVEN,
+        voice: NotGivenOr[str] = NOT_GIVEN,
+        model: NotGivenOr[str] = NOT_GIVEN,
+        encoding: NotGivenOr[Encoding] = NOT_GIVEN,
+        bit_rate: NotGivenOr[int] = NOT_GIVEN,
+        sample_rate: NotGivenOr[int] = NOT_GIVEN,
+        pitch: NotGivenOr[float] = NOT_GIVEN,
+        speaking_rate: NotGivenOr[float] = NOT_GIVEN,
+        temperature: NotGivenOr[float] = NOT_GIVEN,
+        base_url: str = DEFAULT_URL,
+        http_session: aiohttp.ClientSession | None = None,
+    ) -> None:
+        """
+        Create a new instance of Inworld TTS.
+
+        Args:
+            api_key (str, optional): The Inworld API key.
+                If not provided, it will be read from the INWORLD_API_KEY environment variable.
+            voice (str, optional): The voice to use. Defaults to "Ashley".
+            model (str, optional): The Inworld model to use. Defaults to "inworld-tts-1".
+            encoding (str, optional): The encoding to use. Defaults to "MP3".
+            bit_rate (int, optional): Bits per second of the audio. Defaults to 64000.
+            sample_rate (int, optional): The audio sample rate in Hz. Defaults to 24000.
+            pitch (float, optional): The pitch of the voice. Defaults to 0.0.
+            speaking_rate (float, optional): The speed of the voice. Defaults to 1.0.
+            temperature (float, optional): Determines the degree of randomness when sampling audio
+                tokens to generate the response. Defaults to 0.8.
+            base_url (str, optional): The base URL for the Inworld TTS API.
+                Defaults to "https://api.inworld.ai/".
+            http_session (aiohttp.ClientSession, optional): The HTTP session to use.
+        """
+        if not utils.is_given(sample_rate):
+            sample_rate = DEFAULT_SAMPLE_RATE
+        super().__init__(
+            capabilities=tts.TTSCapabilities(streaming=False),
+            sample_rate=sample_rate,
+            num_channels=NUM_CHANNELS,
+        )
+
+        api_key = api_key or os.getenv("INWORLD_API_KEY", "")
+        if not api_key:
+            raise ValueError("Inworld API key required. Set INWORLD_API_KEY or provide api_key.")
+
+        self._authorization = f"Basic {api_key}"
+        self._base_url = base_url
+        self._session = http_session
+
+        self._opts = _TTSOptions(
+            voice=voice if utils.is_given(voice) else DEFAULT_VOICE,
+            model=model if utils.is_given(model) else DEFAULT_MODEL,
+            encoding=encoding if utils.is_given(encoding) else DEFAULT_ENCODING,
+            bit_rate=bit_rate if utils.is_given(bit_rate) else DEFAULT_BIT_RATE,
+            sample_rate=sample_rate if utils.is_given(sample_rate) else DEFAULT_SAMPLE_RATE,
+            pitch=pitch,
+            speaking_rate=speaking_rate,
+            temperature=temperature,
+        )
+
+    def update_options(
+        self,
+        *,
+        voice: NotGivenOr[str] = NOT_GIVEN,
+        model: NotGivenOr[str] = NOT_GIVEN,
+        encoding: NotGivenOr[Encoding] = NOT_GIVEN,
+        bit_rate: NotGivenOr[int] = NOT_GIVEN,
+        sample_rate: NotGivenOr[int] = NOT_GIVEN,
+        pitch: NotGivenOr[float] = NOT_GIVEN,
+        speaking_rate: NotGivenOr[float] = NOT_GIVEN,
+        temperature: NotGivenOr[float] = NOT_GIVEN,
+    ) -> None:
+        """
+        Update the TTS configuration options.
+
+        Args:
+            voice (str, optional): The voice to use.
+            model (str, optional): The Inworld model to use.
+            encoding (str, optional): The encoding to use.
+            bit_rate (int, optional): Bits per second of the audio.
+            sample_rate (int, optional): The audio sample rate in Hz.
+            pitch (float, optional): The pitch of the voice.
+            speaking_rate (float, optional): The speed of the voice.
+            temperature (float, optional): Determines the degree of randomness when sampling audio
+                tokens to generate the response. Defaults to 0.8.
+        """
+        if utils.is_given(voice):
+            self._opts.voice = voice
+        if utils.is_given(model):
+            self._opts.model = model
+        if utils.is_given(encoding):
+            self._opts.encoding = encoding
+        if utils.is_given(bit_rate):
+            self._opts.bit_rate = bit_rate
+        if utils.is_given(sample_rate):
+            self._opts.sample_rate = sample_rate
+        if utils.is_given(pitch):
+            self._opts.pitch = pitch
+        if utils.is_given(speaking_rate):
+            self._opts.speaking_rate = speaking_rate
+        if utils.is_given(temperature):
+            self._opts.temperature = temperature
+
+    def _ensure_session(self) -> aiohttp.ClientSession:
+        if not self._session:
+            self._session = utils.http_context.http_session()
+
+        return self._session
+
+    def synthesize(
+        self,
+        text: str,
+        *,
+        conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS,
+    ) -> tts.ChunkedStream:
+        return ChunkedStream(tts=self, input_text=text, conn_options=conn_options)
+
+
+class ChunkedStream(tts.ChunkedStream):
+    def __init__(self, *, tts: TTS, input_text: str, conn_options: APIConnectOptions) -> None:
+        super().__init__(tts=tts, input_text=input_text, conn_options=conn_options)
+        self._tts: TTS = tts
+        self._opts = replace(tts._opts)
+
+    async def _run(self, output_emitter: tts.AudioEmitter) -> None:
+        try:
+            audio_config: dict[str, Any] = {
+                "audioEncoding": self._opts.encoding,
+            }
+            if utils.is_given(self._opts.bit_rate):
+                audio_config["bitrate"] = self._opts.bit_rate
+            if utils.is_given(self._opts.sample_rate):
+                audio_config["sampleRateHertz"] = self._opts.sample_rate
+            if utils.is_given(self._opts.pitch):
+                audio_config["pitch"] = self._opts.pitch
+            if utils.is_given(self._opts.temperature):
+                audio_config["temperature"] = self._opts.temperature
+            if utils.is_given(self._opts.speaking_rate):
+                audio_config["speakingRate"] = self._opts.speaking_rate
+
+            body_params: dict[str, Any] = {
+                "text": self._input_text,
+                "voiceId": self._opts.voice,
+                "modelId": self._opts.model,
+                "audioConfig": audio_config,
+            }
+            if utils.is_given(self._opts.temperature):
+                body_params["temperature"] = self._opts.temperature
+
+            async with self._tts._ensure_session().post(
+                urljoin(self._tts._base_url, "/tts/v1/voice:stream"),
+                headers={
+                    "Authorization": self._tts._authorization,
+                },
+                json=body_params,
+                timeout=aiohttp.ClientTimeout(sock_connect=self._conn_options.timeout),
+            ) as resp:
+                resp.raise_for_status()
+
+                request_id = utils.shortuuid()
+                output_emitter.initialize(
+                    request_id=request_id,
+                    sample_rate=self._opts.sample_rate,
+                    num_channels=NUM_CHANNELS,
+                    mime_type=self._opts.mime_type,
+                )
+
+                async for line in resp.content:
+                    if not line:
+                        break
+                    data = json.loads(line)
+                    if result := data.get("result"):
+                        if audio_content := result.get("audioContent"):
+                            output_emitter.push(base64.b64decode(audio_content))
+                            output_emitter.flush()
+                    elif error := data.get("error"):
+                        raise APIStatusError(
+                            message=error.get("message"),
+                            status_code=error.get("code"),
+                            request_id=request_id,
+                            body=None,
+                        )
+        except asyncio.TimeoutError:
+            raise APITimeoutError() from None
+        except aiohttp.ClientResponseError as e:
+            raise APIStatusError(
+                message=e.message, status_code=e.status, request_id=None, body=None
+            ) from None
+        except Exception as e:
+            raise APIConnectionError() from e

livekit_plugins_inworld-1.1.4/livekit/plugins/inworld/version.py

@@ -0,0 +1,15 @@
+# Copyright 2025 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.
+
+__version__ = "1.1.4"

livekit_plugins_inworld-1.1.4/pyproject.toml

@@ -0,0 +1,41 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "livekit-plugins-inworld"
+dynamic = ["version"]
+description = "Agent Framework plugin for voice synthesis with Inworld's API."
+readme = "README.md"
+license = "Apache-2.0"
+requires-python = ">=3.9.0"
+authors = [{ name = "LiveKit", email = "hello@livekit.io" }]
+keywords = ["webrtc", "realtime", "audio", "video", "livekit", "inworld"]
+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",
+]
+dependencies = [
+    "livekit-agents>=1.1.4",
+]
+
+[project.urls]
+Documentation = "https://docs.livekit.io"
+Website = "https://livekit.io/"
+Source = "https://github.com/livekit/agents"
+
+[tool.hatch.version]
+path = "livekit/plugins/inworld/version.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["livekit"]
+
+[tool.hatch.build.targets.sdist]
+include = ["/livekit"]