livekit-plugins-speechify 1.3.9__tar.gz

livekit_plugins_speechify-1.3.9/.gitignore

@@ -0,0 +1,179 @@
+**/.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/
+
+# Database files
+*.db
+
+
+# Examples for development
+examples/dev/*

livekit_plugins_speechify-1.3.9/PKG-INFO

@@ -0,0 +1,38 @@
+Metadata-Version: 2.4
+Name: livekit-plugins-speechify
+Version: 1.3.9
+Summary: Agent Framework plugin for voice synthesis with Speechify'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,livekit,realtime,speechify,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[codecs]>=1.3.9
+Description-Content-Type: text/markdown
+
+# Speechify TTS plugin for LiveKit Agents
+
+Support for voice synthesis with the [Speechify](https://www.speechify.ai/) API.
+
+See [https://docs.livekit.io/agents/integrations/tts/speechify/](https://docs.livekit.io/agents/integrations/tts/speechify/) for more information.
+
+## Installation
+
+```bash
+pip install livekit-plugins-speechify
+```
+
+## Pre-requisites
+
+You'll need an API key from Speechify. It can be set as an environment variable: `SPEECHIFY_API_KEY`

livekit_plugins_speechify-1.3.9/README.md

@@ -0,0 +1,15 @@
+# Speechify TTS plugin for LiveKit Agents
+
+Support for voice synthesis with the [Speechify](https://www.speechify.ai/) API.
+
+See [https://docs.livekit.io/agents/integrations/tts/speechify/](https://docs.livekit.io/agents/integrations/tts/speechify/) for more information.
+
+## Installation
+
+```bash
+pip install livekit-plugins-speechify
+```
+
+## Pre-requisites
+
+You'll need an API key from Speechify. It can be set as an environment variable: `SPEECHIFY_API_KEY`

livekit_plugins_speechify-1.3.9/livekit/plugins/speechify/__init__.py

@@ -0,0 +1,52 @@
+# 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.
+
+"""Speechify plugin for LiveKit Agents
+
+See https://docs.livekit.io/agents/integrations/tts/speechify/ for more information.
+"""
+
+from .models import TTSEncoding, TTSModels
+from .tts import DEFAULT_VOICE_ID, TTS, Voice
+from .version import __version__
+
+__all__ = [
+    "TTS",
+    "Voice",
+    "TTSEncoding",
+    "TTSModels",
+    "DEFAULT_VOICE_ID",
+    "__version__",
+]
+
+from livekit.agents import Plugin
+
+from .log import logger
+
+
+class SpeechifyPlugin(Plugin):
+    def __init__(self) -> None:
+        super().__init__(__name__, __version__, __package__, logger)
+
+
+Plugin.register_plugin(SpeechifyPlugin())
+
+# 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_speechify-1.3.9/livekit/plugins/speechify/log.py

@@ -0,0 +1,17 @@
+# Copyright 2024 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 logging
+
+logger = logging.getLogger("livekit.plugins.speechify")

livekit_plugins_speechify-1.3.9/livekit/plugins/speechify/models.py

@@ -0,0 +1,29 @@
+# Copyright 2024 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 typing import Literal
+
+TTSModels = Literal[
+    "simba-english",
+    "simba-multilingual",
+]
+
+TTSEncoding = Literal[
+    "mp3_24000",
+    "wav_48000",
+    "ogg_24000",
+    "aac_24000",
+]
+
+VoiceType = Literal["shared", "personal"]
+Gender = Literal["male", "female", "neutral"]

livekit_plugins_speechify-1.3.9/livekit/plugins/speechify/tts.py

@@ -0,0 +1,293 @@
+# 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.
+
+from __future__ import annotations
+
+import asyncio
+import os
+from dataclasses import dataclass, replace
+from typing import cast
+
+import aiohttp
+
+from livekit.agents import (
+    APIConnectionError,
+    APIConnectOptions,
+    APIError,
+    APIStatusError,
+    APITimeoutError,
+    tts,
+    utils,
+)
+from livekit.agents.types import (
+    DEFAULT_API_CONNECT_OPTIONS,
+    NOT_GIVEN,
+    NotGivenOr,
+)
+from livekit.agents.utils import is_given
+
+from .models import Gender, TTSEncoding, TTSModels, VoiceType
+
+_DefaultEncoding: TTSEncoding = "ogg_24000"
+
+
+def _sample_rate_from_encoding(output_encoding: TTSEncoding) -> int:
+    split = output_encoding.split("_")
+    return int(split[1])
+
+
+def _audio_format_from_encoding(encoding: TTSEncoding) -> str:
+    split = encoding.split("_")
+    return split[0]
+
+
+DEFAULT_VOICE_ID = "jack"
+API_BASE_URL_V1 = "https://api.sws.speechify.com/v1"
+AUTHORIZATION_HEADER = "Authorization"
+CALLER_HEADER = "x-caller"
+
+
+@dataclass
+class Voice:
+    id: str
+    type: VoiceType
+    display_name: str
+    gender: Gender
+    avatar_image: str | None
+    models: list[TTSModels]
+    locale: str
+
+
+@dataclass
+class _TTSOptions:
+    base_url: NotGivenOr[str]
+    token: str
+    voice_id: str
+    encoding: TTSEncoding
+    language: NotGivenOr[str]
+    model: NotGivenOr[TTSModels]
+    loudness_normalization: NotGivenOr[bool]
+    text_normalization: NotGivenOr[bool]
+    follow_redirects: bool
+    sample_rate: int
+
+
+class TTS(tts.TTS):
+    def __init__(
+        self,
+        *,
+        voice_id: NotGivenOr[str] = DEFAULT_VOICE_ID,
+        encoding: NotGivenOr[TTSEncoding] = NOT_GIVEN,
+        model: NotGivenOr[TTSModels] = NOT_GIVEN,
+        base_url: NotGivenOr[str] = NOT_GIVEN,
+        api_key: NotGivenOr[str] = NOT_GIVEN,
+        language: NotGivenOr[str] = NOT_GIVEN,
+        loudness_normalization: NotGivenOr[bool] = NOT_GIVEN,
+        text_normalization: NotGivenOr[bool] = NOT_GIVEN,
+        http_session: aiohttp.ClientSession | None = None,
+        follow_redirects: bool = True,
+    ) -> None:
+        """
+        Create a new instance of Speechify TTS.
+
+        Args:
+            voice_id (NotGivenOr[str]): Voice ID. Defaults to `cliff`.
+            encoding (NotGivenOr[TTSEncoding]): Audio encoding to use. Optional. Defaults to `wav_48000`.
+            model (NotGivenOr[TTSModels]): TTS model to use. Optional.
+            base_url (NotGivenOr[str]): Custom base URL for the API. Optional.
+            api_key (NotGivenOr[str]): Speechify API key. Can be set via argument or `SPEECHIFY_API_KEY` environment variable
+            language (NotGivenOr[str]): Language code for the TTS model. Optional.
+            loudness_normalization (NotGivenOr[bool]): Whether to normalize the loudness of the audio. Optional.
+            text_normalization (NotGivenOr[bool]): Whether to normalize the text. Optional.
+            http_session (aiohttp.ClientSession | None): Custom HTTP session for API requests. Optional.
+            follow_redirects (bool): Whether to follow redirects in HTTP requests. Defaults to True.
+        """  # noqa: E501
+
+        if not is_given(encoding):
+            encoding = _DefaultEncoding
+
+        super().__init__(
+            capabilities=tts.TTSCapabilities(
+                streaming=False,
+            ),
+            sample_rate=_sample_rate_from_encoding(encoding),
+            num_channels=1,
+        )
+
+        speechify_token = api_key if is_given(api_key) else os.environ.get("SPEECHIFY_API_KEY")
+        if not (speechify_token):
+            raise ValueError(
+                "Speechify API key is required, either as argument or set SPEECHIFY_API_KEY environment variable"  # noqa: E501
+            )
+
+        self._opts = _TTSOptions(
+            model=model,
+            voice_id=voice_id or DEFAULT_VOICE_ID,
+            language=language,
+            base_url=base_url if is_given(base_url) else API_BASE_URL_V1,
+            token=speechify_token,
+            follow_redirects=follow_redirects,
+            encoding=encoding,
+            sample_rate=_sample_rate_from_encoding(encoding),
+            loudness_normalization=loudness_normalization,
+            text_normalization=text_normalization,
+        )
+        self._session = http_session
+
+    @property
+    def model(self) -> str:
+        return self._opts.model if is_given(self._opts.model) else "unknown"
+
+    @property
+    def provider(self) -> str:
+        return "Speechify"
+
+    def _ensure_session(self) -> aiohttp.ClientSession:
+        if not self._session:
+            self._session = utils.http_context.http_session()
+
+        return self._session
+
+    async def list_voices(self) -> list[Voice]:
+        async with self._ensure_session().get(
+            f"{self._opts.base_url}/voices", headers=_get_headers(self._opts.token)
+        ) as resp:
+            return await resp.json()  # type: ignore
+
+    def update_options(
+        self,
+        *,
+        voice_id: NotGivenOr[str] = NOT_GIVEN,
+        model: NotGivenOr[TTSModels] = NOT_GIVEN,
+        language: NotGivenOr[str] = NOT_GIVEN,
+        loudness_normalization: NotGivenOr[bool] = NOT_GIVEN,
+        text_normalization: NotGivenOr[bool] = NOT_GIVEN,
+    ) -> None:
+        """
+        Args:
+            voice_id (NotGivenOr[str]): Voice ID.
+            model (NotGivenOr[TTSModels | str]): TTS model to use.
+            language (NotGivenOr[str]): Language code for the TTS model.
+        """
+        if is_given(model):
+            self._opts.model = cast(TTSModels, model)
+        if is_given(voice_id):
+            self._opts.voice_id = voice_id
+        if is_given(language):
+            self._opts.language = language
+        if is_given(loudness_normalization):
+            self._opts.loudness_normalization = loudness_normalization
+        if is_given(text_normalization):
+            self._opts.text_normalization = text_normalization
+
+    def synthesize(
+        self,
+        text: str,
+        *,
+        conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS,
+    ) -> ChunkedStream:
+        return ChunkedStream(tts=self, input_text=text, conn_options=conn_options)
+
+
+class ChunkedStream(tts.ChunkedStream):
+    """Synthesize using the chunked api endpoint"""
+
+    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:
+        data = {
+            "input": self._input_text,
+            "voice_id": self._opts.voice_id,
+            "language": self._opts.language if is_given(self._opts.language) else None,
+            "model": self._opts.model if is_given(self._opts.model) else None,
+            "audio_format": _audio_format_from_encoding(self._opts.encoding),
+            "options": {
+                "loudness_normalization": self._opts.loudness_normalization
+                if is_given(self._opts.loudness_normalization)
+                else None,
+                "text_normalization": self._opts.text_normalization
+                if is_given(self._opts.text_normalization)
+                else None,
+            },
+        }
+
+        try:
+            async with self._tts._ensure_session().post(
+                _synthesize_url(self._opts),
+                headers=_get_headers(self._opts.token, encoding=self._opts.encoding),
+                json=data,
+                timeout=aiohttp.ClientTimeout(connect=self._conn_options.timeout, total=30),
+            ) as resp:
+                resp.raise_for_status()
+
+                if not resp.content_type.startswith("audio/"):
+                    content = await resp.text()
+                    raise APIError(message="Speechify returned non-audio data", body=content)
+
+                output_emitter.initialize(
+                    request_id=utils.shortuuid(),
+                    sample_rate=self._opts.sample_rate,
+                    num_channels=1,
+                    mime_type=f"audio/{_audio_format_from_encoding(self._opts.encoding)}",
+                )
+
+                async for chunk, _ in resp.content.iter_chunks():
+                    output_emitter.push(chunk)
+
+                output_emitter.flush()
+
+        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
+
+
+def _synthesize_url(opts: _TTSOptions) -> str:
+    """Construct the Speechify stream URL."""
+    return f"{opts.base_url}/audio/stream"
+
+
+def _get_headers(token: str, *, encoding: TTSEncoding | None = None) -> dict[str, str]:
+    """Construct the headers for the Speechify API."""
+    headers = {
+        AUTHORIZATION_HEADER: f"Bearer {token}" if not token.startswith("Bearer ") else token
+    }
+
+    if encoding:
+        accept = ""
+        format = _audio_format_from_encoding(encoding)
+        if format == "ogg":
+            accept = "audio/ogg"
+        elif format == "mp3":
+            accept = "audio/mpeg"
+        elif format == "aac":
+            accept = "audio/aac"
+
+        # docs does not specify mime type for wav
+        # https://docs.sws.speechify.com/v1/api-reference/api-reference/tts/audio/stream
+
+        if accept:
+            headers["Accept"] = accept
+    headers[CALLER_HEADER] = "livekit"
+    return headers

livekit_plugins_speechify-1.3.9/livekit/plugins/speechify/version.py

@@ -0,0 +1,15 @@
+# Copyright 2024 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__ = "1.3.9"

livekit_plugins_speechify-1.3.9/pyproject.toml

@@ -0,0 +1,39 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "livekit-plugins-speechify"
+dynamic = ["version"]
+description = "Agent Framework plugin for voice synthesis with Speechify'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", "speechify"]
+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[codecs]>=1.3.9"]
+
+[project.urls]
+Documentation = "https://docs.livekit.io"
+Website = "https://livekit.io/"
+Source = "https://github.com/livekit/agents"
+
+[tool.hatch.version]
+path = "livekit/plugins/speechify/version.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["livekit"]
+
+[tool.hatch.build.targets.sdist]
+include = ["/livekit"]