livekit-plugins-zoom-ai 1.8.11__tar.gz

livekit_plugins_zoom_ai-1.8.11/.gitignore

@@ -0,0 +1,180 @@
+**/.vscode
+**/.DS_Store
+.env
+
+# 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_zoom_ai-1.8.11/PKG-INFO

@@ -0,0 +1,114 @@
+Metadata-Version: 2.5
+Name: livekit-plugins-zoom-ai
+Version: 1.8.11
+Summary: Agent Framework plugin for speech-to-text with Zoom Scribe.
+Project-URL: Documentation, https://docs.livekit.io
+Project-URL: Website, https://livekit.io/
+Project-URL: Source, https://github.com/livekit/agents
+Author: Zoom
+License-Expression: Apache-2.0
+Keywords: audio,livekit,realtime,scribe,speech-to-text,stt,webrtc,zoom
+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 :: 3.10
+Classifier: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10.0
+Requires-Dist: livekit-agents>=1.8.11
+Description-Content-Type: text/markdown
+
+# Zoom AI plugin for LiveKit Agents
+
+Support for [Zoom Scribe](https://developers.zoom.us/docs/ai-services/scribe/) speech-to-text, in two modes:
+
+- **Live** ([docs](https://developers.zoom.us/docs/ai-services/scribe/live-mode/)): streaming over WebSocket. Scribe's own VAD ends each speech turn and returns its final transcript.
+- **Fast** ([docs](https://developers.zoom.us/docs/ai-services/scribe/fast-mode/)): one HTTP request per utterance. Not streaming, so `AgentSession` pairs it with a VAD.
+
+See [zoom.ai](https://www.zoom.ai/) for all Zoom AI Services APIs and features.
+
+## Installation
+
+```bash
+pip install livekit-plugins-zoom-ai
+```
+
+Or install with the LiveKit Agents extra:
+
+```bash
+uv add "livekit-agents[zoom-ai]"
+```
+
+## Pre-requisites
+
+The plugin needs a Zoom AI Services API key. Create one in [Zoom Platform Studio](https://platform.zoom.us/) under Credentials → API Keys, with the Scribe permissions.
+
+Set it in your `.env` file:
+
+```
+ZOOM_AI_API_KEY=<your_zoom_api_key>
+```
+
+## Usage
+
+### Scribe Live (streaming)
+
+Scribe detects the end of each turn, so let the STT drive turn detection:
+
+```python
+from livekit.agents import AgentSession
+from livekit.plugins import zoom_ai
+
+session = AgentSession(
+    stt=zoom_ai.STT(language="en-US"),
+    turn_handling={"turn_detection": "stt"},
+    # ... llm, tts, etc.
+)
+```
+
+### Scribe Fast (per utterance)
+
+```python
+from livekit.agents import AgentSession
+from livekit.plugins import silero, zoom_ai
+
+session = AgentSession(
+    stt=zoom_ai.STT(mode="fast"),
+    vad=silero.VAD.load(),  # cuts the audio into utterances
+    # ... llm, tts, etc.
+)
+```
+
+### Without an agent
+
+Both modes also work on their own, for example for transcription. Outside an agent job, pass an `aiohttp` session:
+
+```python
+stt = zoom_ai.STT(http_session=session, silence_duration_ms=600)  # Live
+stream = stt.stream()  # push_frame() audio, then iterate the stream for SpeechEvents
+
+event = await zoom_ai.STT(mode="fast", http_session=session).recognize(frames)  # Fast
+```
+
+For transcription, a longer `silence_duration_ms` (such as 600) keeps sentences with pauses together and can improve accuracy; the 350 ms default is tuned for voice agents.
+
+## Options
+
+Options map to the Scribe API fields of the same name; see the [Scribe docs](https://developers.zoom.us/docs/ai-services/scribe/) for what each one does and its availability. For a Scribe feature without an option here, pass its fields in `extra_kwargs`.
+
+| Option | Default | Description |
+|---|---|---|
+| `mode` | `"live"` | `"live"` (streaming) or `"fast"` (one request per utterance) |
+| `api_key` | `$ZOOM_AI_API_KEY` | Zoom AI Services API key |
+| `language` | `"en-US"` | Recognition language ([supported languages](https://developers.zoom.us/docs/ai-services/scribe/speech-understanding/)); a regional variant Scribe doesn't list uses its base language's locale (`en-GB` → `en-US`) |
+| `model` | `None` | Recognition model; `None` uses Scribe's default |
+| `language_detection` | `None` | Language detection mode (Live supports `"continuous"`); the language Scribe detects is in `SpeechData.language`. With `zoom-scribe-multilingual` in Live, set it to get each final's language |
+| `silence_duration_ms` | `350` | Live: silence (ms) that ends a turn; `None` uses Scribe's default |
+| `diarization` | `False` | Speaker labels: `SpeechData.speaker_id`, or `metadata["speaker_segments"]` when several people speak in one final |
+| `word_time_offsets` | `False` | Fast: word timings in `SpeechData.words` |
+| `channel_separation` | `False` | Fast: recognize each stereo channel separately; channels in `metadata["channel_segments"]` |
+| `vocabulary` | `None` | Words and phrases to recognize, such as names and product terms |
+| `text_polishing` | `False` | Polished text as the transcript, with the original in `metadata["transcript"]`; if polishing fails, the original text. `en-US` only |
+| `extra_kwargs` | `None` | Other Scribe request fields, e.g. `{"config": {"language_detection": {"candidate_languages": ["en-US", "fr-FR"]}}}` to restrict language detection |
+| `base_url` | `https://api.zoom.us/v2/aiservices/scribe` | Scribe API base URL |

livekit_plugins_zoom_ai-1.8.11/README.md

@@ -0,0 +1,93 @@
+# Zoom AI plugin for LiveKit Agents
+
+Support for [Zoom Scribe](https://developers.zoom.us/docs/ai-services/scribe/) speech-to-text, in two modes:
+
+- **Live** ([docs](https://developers.zoom.us/docs/ai-services/scribe/live-mode/)): streaming over WebSocket. Scribe's own VAD ends each speech turn and returns its final transcript.
+- **Fast** ([docs](https://developers.zoom.us/docs/ai-services/scribe/fast-mode/)): one HTTP request per utterance. Not streaming, so `AgentSession` pairs it with a VAD.
+
+See [zoom.ai](https://www.zoom.ai/) for all Zoom AI Services APIs and features.
+
+## Installation
+
+```bash
+pip install livekit-plugins-zoom-ai
+```
+
+Or install with the LiveKit Agents extra:
+
+```bash
+uv add "livekit-agents[zoom-ai]"
+```
+
+## Pre-requisites
+
+The plugin needs a Zoom AI Services API key. Create one in [Zoom Platform Studio](https://platform.zoom.us/) under Credentials → API Keys, with the Scribe permissions.
+
+Set it in your `.env` file:
+
+```
+ZOOM_AI_API_KEY=<your_zoom_api_key>
+```
+
+## Usage
+
+### Scribe Live (streaming)
+
+Scribe detects the end of each turn, so let the STT drive turn detection:
+
+```python
+from livekit.agents import AgentSession
+from livekit.plugins import zoom_ai
+
+session = AgentSession(
+    stt=zoom_ai.STT(language="en-US"),
+    turn_handling={"turn_detection": "stt"},
+    # ... llm, tts, etc.
+)
+```
+
+### Scribe Fast (per utterance)
+
+```python
+from livekit.agents import AgentSession
+from livekit.plugins import silero, zoom_ai
+
+session = AgentSession(
+    stt=zoom_ai.STT(mode="fast"),
+    vad=silero.VAD.load(),  # cuts the audio into utterances
+    # ... llm, tts, etc.
+)
+```
+
+### Without an agent
+
+Both modes also work on their own, for example for transcription. Outside an agent job, pass an `aiohttp` session:
+
+```python
+stt = zoom_ai.STT(http_session=session, silence_duration_ms=600)  # Live
+stream = stt.stream()  # push_frame() audio, then iterate the stream for SpeechEvents
+
+event = await zoom_ai.STT(mode="fast", http_session=session).recognize(frames)  # Fast
+```
+
+For transcription, a longer `silence_duration_ms` (such as 600) keeps sentences with pauses together and can improve accuracy; the 350 ms default is tuned for voice agents.
+
+## Options
+
+Options map to the Scribe API fields of the same name; see the [Scribe docs](https://developers.zoom.us/docs/ai-services/scribe/) for what each one does and its availability. For a Scribe feature without an option here, pass its fields in `extra_kwargs`.
+
+| Option | Default | Description |
+|---|---|---|
+| `mode` | `"live"` | `"live"` (streaming) or `"fast"` (one request per utterance) |
+| `api_key` | `$ZOOM_AI_API_KEY` | Zoom AI Services API key |
+| `language` | `"en-US"` | Recognition language ([supported languages](https://developers.zoom.us/docs/ai-services/scribe/speech-understanding/)); a regional variant Scribe doesn't list uses its base language's locale (`en-GB` → `en-US`) |
+| `model` | `None` | Recognition model; `None` uses Scribe's default |
+| `language_detection` | `None` | Language detection mode (Live supports `"continuous"`); the language Scribe detects is in `SpeechData.language`. With `zoom-scribe-multilingual` in Live, set it to get each final's language |
+| `silence_duration_ms` | `350` | Live: silence (ms) that ends a turn; `None` uses Scribe's default |
+| `diarization` | `False` | Speaker labels: `SpeechData.speaker_id`, or `metadata["speaker_segments"]` when several people speak in one final |
+| `word_time_offsets` | `False` | Fast: word timings in `SpeechData.words` |
+| `channel_separation` | `False` | Fast: recognize each stereo channel separately; channels in `metadata["channel_segments"]` |
+| `vocabulary` | `None` | Words and phrases to recognize, such as names and product terms |
+| `text_polishing` | `False` | Polished text as the transcript, with the original in `metadata["transcript"]`; if polishing fails, the original text. `en-US` only |
+| `extra_kwargs` | `None` | Other Scribe request fields, e.g. `{"config": {"language_detection": {"candidate_languages": ["en-US", "fr-FR"]}}}` to restrict language detection |
+| `base_url` | `https://api.zoom.us/v2/aiservices/scribe` | Scribe API base URL |

livekit_plugins_zoom_ai-1.8.11/livekit/plugins/zoom_ai/__init__.py

@@ -0,0 +1,47 @@
+# Copyright 2026 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.
+
+"""Zoom AI plugin for LiveKit Agents.
+
+Speech-to-text with Zoom Scribe: ``STT()`` streams over Scribe Live and
+``STT(mode="fast")`` transcribes one utterance per request with Scribe Fast.
+
+See https://developers.zoom.us/docs/ai-services/scribe/ for more information.
+"""
+
+from .stt import STT, SpeechStream
+from .version import __version__
+
+__all__ = ["STT", "SpeechStream", "__version__"]
+
+from livekit.agents import Plugin
+
+from .log import logger
+
+
+class ZoomAIPlugin(Plugin):
+    def __init__(self) -> None:
+        super().__init__(__name__, __version__, __package__, logger)
+
+
+Plugin.register_plugin(ZoomAIPlugin())
+
+# 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_zoom_ai-1.8.11/livekit/plugins/zoom_ai/log.py

@@ -0,0 +1,17 @@
+# Copyright 2026 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.zoom_ai")