livekit-plugins-gladia 1.0.0__tar.gz

livekit_plugins_gladia-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_gladia-1.0.0/PKG-INFO

@@ -0,0 +1,101 @@
+Metadata-Version: 2.4
+Name: livekit-plugins-gladia
+Version: 1.0.0
+Summary: Agent Framework plugin for services using Gladia'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 <support@livekit.io>
+License-Expression: Apache-2.0
+Keywords: audio,gladia,livekit,realtime,speech-to-text,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: aiohttp>=3.8.0
+Requires-Dist: livekit-agents[codecs]>=1.0.0
+Requires-Dist: numpy>=1.26
+Description-Content-Type: text/markdown
+
+# Gladia plugin for LiveKit
+
+Agent Framework plugin for speech-to-text with [Gladia](https://gladia.io/)'s API. Currently supports streaming speech-to-text with optional translation.
+
+## Installation
+
+```bash
+pip install livekit-plugins-gladia
+```
+
+## Pre-requisites
+
+You'll need an API key from Gladia. It can be set as an environment variable: `GLADIA_API_KEY`
+
+## Features
+
+- Streaming speech-to-text
+- Multi-language support
+- Code-switching between languages
+- Interim results (partial transcriptions)
+- Voice activity detection with energy filtering
+- Optional real-time translation
+- Customizable audio parameters (sample rate, bit depth, channels, encoding)
+
+## Example Usage
+
+```python
+from livekit.stt import STT
+from livekit.plugins.gladia.stt import STT as GladiaSTT
+
+# Basic initialization
+stt = GladiaSTT(
+    api_key="your-api-key-here",  # or use GLADIA_API_KEY env var
+    interim_results=True
+)
+
+# With more options
+stt = GladiaSTT(
+    languages=["en", "fr"],  # Specify languages or let Gladia auto-detect
+    code_switching=True,     # Allow switching between languages during recognition
+    sample_rate=16000,       # Audio sample rate in Hz
+    bit_depth=16,            # Audio bit depth
+    channels=1,              # Number of audio channels
+    encoding="wav/pcm",      # Audio encoding format
+    energy_filter=True,      # Enable voice activity detection
+    translation_enabled=True,
+    translation_target_languages=["en"],
+    translation_model="base",
+    translation_match_original_utterances=True
+)
+
+# Update options after initialization
+stt.update_options(
+    languages=["ja", "en"],
+    translation_enabled=True,
+    translation_target_languages=["fr"]
+)
+```
+
+## Using with LiveKit Agents Framework
+
+```python
+from livekit.agents import Agent
+from livekit.plugins.gladia.stt import STT as GladiaSTT
+
+agent = Agent(
+    stt=GladiaSTT(
+        api_key="your-api-key-here",
+        languages=["en"],
+        translation_enabled=True,
+        translation_target_languages=["es"]
+    )
+)
+
+# Rest of your agent setup...
+```

livekit_plugins_gladia-1.0.0/README.md

@@ -0,0 +1,76 @@
+# Gladia plugin for LiveKit
+
+Agent Framework plugin for speech-to-text with [Gladia](https://gladia.io/)'s API. Currently supports streaming speech-to-text with optional translation.
+
+## Installation
+
+```bash
+pip install livekit-plugins-gladia
+```
+
+## Pre-requisites
+
+You'll need an API key from Gladia. It can be set as an environment variable: `GLADIA_API_KEY`
+
+## Features
+
+- Streaming speech-to-text
+- Multi-language support
+- Code-switching between languages
+- Interim results (partial transcriptions)
+- Voice activity detection with energy filtering
+- Optional real-time translation
+- Customizable audio parameters (sample rate, bit depth, channels, encoding)
+
+## Example Usage
+
+```python
+from livekit.stt import STT
+from livekit.plugins.gladia.stt import STT as GladiaSTT
+
+# Basic initialization
+stt = GladiaSTT(
+    api_key="your-api-key-here",  # or use GLADIA_API_KEY env var
+    interim_results=True
+)
+
+# With more options
+stt = GladiaSTT(
+    languages=["en", "fr"],  # Specify languages or let Gladia auto-detect
+    code_switching=True,     # Allow switching between languages during recognition
+    sample_rate=16000,       # Audio sample rate in Hz
+    bit_depth=16,            # Audio bit depth
+    channels=1,              # Number of audio channels
+    encoding="wav/pcm",      # Audio encoding format
+    energy_filter=True,      # Enable voice activity detection
+    translation_enabled=True,
+    translation_target_languages=["en"],
+    translation_model="base",
+    translation_match_original_utterances=True
+)
+
+# Update options after initialization
+stt.update_options(
+    languages=["ja", "en"],
+    translation_enabled=True,
+    translation_target_languages=["fr"]
+)
+```
+
+## Using with LiveKit Agents Framework
+
+```python
+from livekit.agents import Agent
+from livekit.plugins.gladia.stt import STT as GladiaSTT
+
+agent = Agent(
+    stt=GladiaSTT(
+        api_key="your-api-key-here",
+        languages=["en"],
+        translation_enabled=True,
+        translation_target_languages=["es"]
+    )
+)
+
+# Rest of your agent setup...
+```

livekit_plugins_gladia-1.0.0/livekit/plugins/gladia/__init__.py

@@ -0,0 +1,25 @@
+from .stt import STT, AudioEnergyFilter, SpeechStream
+from .version import __version__
+
+__all__ = ["STT", "SpeechStream", "AudioEnergyFilter", "__version__"]
+
+
+from livekit.agents import Plugin
+
+from .log import logger
+
+
+class GladiaPlugin(Plugin):
+    def __init__(self):
+        super().__init__(__name__, __version__, __package__, logger)
+
+
+Plugin.register_plugin(GladiaPlugin())
+
+_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_gladia-1.0.0/livekit/plugins/gladia/_utils.py

@@ -0,0 +1,36 @@
+import time
+from typing import Callable, Generic, Optional, TypeVar
+
+T = TypeVar("T")
+
+
+class PeriodicCollector(Generic[T]):
+    def __init__(self, callback: Callable[[T], None], *, duration: float) -> None:
+        """
+        Create a new periodic collector that accumulates values and calls the callback
+        after the specified duration if there are values to report.
+
+        Args:
+            duration: Time in seconds between callback invocations
+            callback: Function to call with accumulated value when duration expires
+        """
+        self._duration = duration
+        self._callback = callback
+        self._last_flush_time = time.monotonic()
+        self._total: Optional[T] = None
+
+    def push(self, value: T) -> None:
+        """Add a value to the accumulator"""
+        if self._total is None:
+            self._total = value
+        else:
+            self._total += value
+        if time.monotonic() - self._last_flush_time >= self._duration:
+            self.flush()
+
+    def flush(self) -> None:
+        """Force callback to be called with current total if non-zero"""
+        if self._total is not None:
+            self._callback(self._total)
+            self._total = None
+        self._last_flush_time = time.monotonic()

livekit_plugins_gladia-1.0.0/livekit/plugins/gladia/log.py

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

livekit_plugins_gladia-1.0.0/livekit/plugins/gladia/models.py

@@ -0,0 +1,121 @@
+from typing import Literal
+
+GladiaModels = Literal["base"]
+
+GladiaLanguages = Literal[
+    "af",
+    "sq",
+    "am",
+    "ar",
+    "hy",
+    "as",
+    "ast",
+    "az",
+    "ba",
+    "eu",
+    "be",
+    "bn",
+    "bs",
+    "br",
+    "bg",
+    "my",
+    "es",
+    "ca",
+    "ceb",
+    "zh",
+    "hr",
+    "cs",
+    "da",
+    "nl",
+    "en",
+    "et",
+    "fo",
+    "fi",
+    "fr",
+    "fy",
+    "ff",
+    "gd",
+    "gl",
+    "lg",
+    "ka",
+    "de",
+    "el",
+    "gu",
+    "ht",
+    "ha",
+    "haw",
+    "he",
+    "hi",
+    "hu",
+    "is",
+    "ig",
+    "ilo",
+    "id",
+    "ga",
+    "it",
+    "ja",
+    "jv",
+    "kn",
+    "kk",
+    "km",
+    "ko",
+    "lo",
+    "la",
+    "lv",
+    "lb",
+    "ln",
+    "lt",
+    "mk",
+    "mg",
+    "ms",
+    "ml",
+    "mt",
+    "mi",
+    "mr",
+    "mo",
+    "mn",
+    "ne",
+    "no",
+    "nn",
+    "oc",
+    "or",
+    "pa",
+    "ps",
+    "fa",
+    "pl",
+    "pt",
+    "ro",
+    "ru",
+    "sa",
+    "sr",
+    "sn",
+    "sd",
+    "si",
+    "sk",
+    "sl",
+    "so",
+    "su",
+    "sw",
+    "ss",
+    "sv",
+    "tl",
+    "tg",
+    "ta",
+    "tt",
+    "te",
+    "th",
+    "bo",
+    "tn",
+    "tr",
+    "tk",
+    "uk",
+    "ur",
+    "uz",
+    "vi",
+    "cy",
+    "wo",
+    "xh",
+    "yi",
+    "yo",
+    "zu",
+]