pipecat-alkove 0.2.0__tar.gz

pipecat_alkove-0.2.0/.gitignore

@@ -0,0 +1,3 @@
+__pycache__/
+*.egg-info/
+dist/

pipecat_alkove-0.2.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   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.

pipecat_alkove-0.2.0/NOTICE

@@ -0,0 +1,27 @@
+Alkove
+Copyright 2026 Eddy Bordi
+
+This product includes software developed by third parties:
+
+- alkove-focus-1-preview is derived from GTCRN
+  (https://github.com/Xiaobin-Rong/gtcrn), under the MIT License:
+
+  Copyright (c) 2024 Rong Xiaobin
+
+  Permission is hereby granted, free of charge, to any person obtaining a copy
+  of this software and associated documentation files (the "Software"), to deal
+  in the Software without restriction, including without limitation the rights
+  to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+  copies of the Software, and to permit persons to whom the Software is
+  furnished to do so, subject to the following conditions:
+
+  The above copyright notice and this permission notice shall be included in all
+  copies or substantial portions of the Software.
+
+  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+  IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+  AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+  SOFTWARE.

pipecat_alkove-0.2.0/PKG-INFO

@@ -0,0 +1,56 @@
+Metadata-Version: 2.5
+Name: pipecat-alkove
+Version: 0.2.0
+Summary: Alkove for Pipecat: AlkoveFilter keeps the user's voice, AlkoveVADAnalyzer finds speech, on the bot's CPU
+Project-URL: Homepage, https://alkove.ai
+Project-URL: Repository, https://github.com/alkove-ai/alkove
+Author: Eddy Bordi
+License-Expression: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
+Keywords: noise-cancellation,on-device,pipecat,vad,voice,voice-agent,voice-isolation
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Requires-Python: >=3.10
+Requires-Dist: alkove<0.3,>=0.2
+Requires-Dist: numpy>=1.21
+Requires-Dist: pipecat-ai<2,>=1.0
+Description-Content-Type: text/markdown
+
+# pipecat-alkove
+
+[Alkove](https://alkove.ai) for [Pipecat](https://github.com/pipecat-ai/pipecat): `AlkoveFilter` keeps the user's voice and removes the others and the noise (Focus), `AlkoveVADAnalyzer` finds where they speak (Cue). Both run on the bot's CPU, with no server and no key, with the chain of Alkove's web SDK; where speech starts and ends is Pipecat's `VADParams`.
+
+Maintained by Alkove, not by the Pipecat team.
+
+## Install
+
+```sh
+pip install pipecat-alkove
+```
+
+The models (Focus 1.1 MB, Cue 1.1 MB) are downloaded once into the cache and checked by their sha256: the analyzer loads them when it is created, as Silero's does, the filter when the transport starts. Pass `models=alkove.Models.load(["focus", "cue"], dir=...)` to read them from your own folder.
+
+## Use
+
+```python
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.transports.base_transport import TransportParams
+from pipecat_alkove import AlkoveFilter, AlkoveVADAnalyzer
+
+params = TransportParams(audio_in_enabled=True, audio_in_filter=AlkoveFilter())
+vad = AlkoveVADAnalyzer()  # VADParams(confidence=0.5) unless you pass params
+```
+
+Give the analyzer to your user aggregator (`LLMUserAggregatorParams(vad_analyzer=vad)`) or to a `VADProcessor`, as you would Silero's.
+
+- **`AlkoveFilter`** keeps the closest voice, or with `voiceprint=` the voice of that print; `strength=` and `normalize=` work as in the web SDK. It works at the transport's input rate. `FilterEnableFrame(False)` gives the raw microphone back at the same delay; `FilterUpdateSettingsFrame(settings={"strength": 0.5})` and `{"voiceprint": ...}` change it while it runs. It returns the samples that are ready: a little less than the input at the start (Focus's 16 ms), then about the input's size.
+- **`AlkoveVADAnalyzer`** gives Cue's speech probability every 30 ms, at any input rate. Cue was tuned with a confidence of 0.5, so that is its default. Behind `AlkoveFilter`, it hears only the user.
+
+`example.py` runs both on your microphone and prints when you speak.
+
+Tested with pipecat-ai 1.13.0.
+
+## License
+
+Apache-2.0. See [NOTICE](./NOTICE).

pipecat_alkove-0.2.0/README.md

@@ -0,0 +1,37 @@
+# pipecat-alkove
+
+[Alkove](https://alkove.ai) for [Pipecat](https://github.com/pipecat-ai/pipecat): `AlkoveFilter` keeps the user's voice and removes the others and the noise (Focus), `AlkoveVADAnalyzer` finds where they speak (Cue). Both run on the bot's CPU, with no server and no key, with the chain of Alkove's web SDK; where speech starts and ends is Pipecat's `VADParams`.
+
+Maintained by Alkove, not by the Pipecat team.
+
+## Install
+
+```sh
+pip install pipecat-alkove
+```
+
+The models (Focus 1.1 MB, Cue 1.1 MB) are downloaded once into the cache and checked by their sha256: the analyzer loads them when it is created, as Silero's does, the filter when the transport starts. Pass `models=alkove.Models.load(["focus", "cue"], dir=...)` to read them from your own folder.
+
+## Use
+
+```python
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.transports.base_transport import TransportParams
+from pipecat_alkove import AlkoveFilter, AlkoveVADAnalyzer
+
+params = TransportParams(audio_in_enabled=True, audio_in_filter=AlkoveFilter())
+vad = AlkoveVADAnalyzer()  # VADParams(confidence=0.5) unless you pass params
+```
+
+Give the analyzer to your user aggregator (`LLMUserAggregatorParams(vad_analyzer=vad)`) or to a `VADProcessor`, as you would Silero's.
+
+- **`AlkoveFilter`** keeps the closest voice, or with `voiceprint=` the voice of that print; `strength=` and `normalize=` work as in the web SDK. It works at the transport's input rate. `FilterEnableFrame(False)` gives the raw microphone back at the same delay; `FilterUpdateSettingsFrame(settings={"strength": 0.5})` and `{"voiceprint": ...}` change it while it runs. It returns the samples that are ready: a little less than the input at the start (Focus's 16 ms), then about the input's size.
+- **`AlkoveVADAnalyzer`** gives Cue's speech probability every 30 ms, at any input rate. Cue was tuned with a confidence of 0.5, so that is its default. Behind `AlkoveFilter`, it hears only the user.
+
+`example.py` runs both on your microphone and prints when you speak.
+
+Tested with pipecat-ai 1.13.0.
+
+## License
+
+Apache-2.0. See [NOTICE](./NOTICE).

pipecat_alkove-0.2.0/example.py

@@ -0,0 +1,41 @@
+"""Alkove on your microphone with Pipecat: AlkoveFilter keeps your voice, AlkoveVADAnalyzer says when you speak.
+
+pip install "pipecat-ai[local]" pipecat-alkove
+python example.py
+"""
+
+import asyncio
+import sys
+
+from loguru import logger
+from pipecat.frames.frames import Frame, VADUserStartedSpeakingFrame, VADUserStoppedSpeakingFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.worker import PipelineWorker
+from pipecat.processors.audio.vad_processor import VADProcessor
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
+from pipecat.workers.runner import WorkerRunner
+
+from pipecat_alkove import AlkoveFilter, AlkoveVADAnalyzer
+
+
+class SpeechLogger(FrameProcessor):
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+        if isinstance(frame, VADUserStartedSpeakingFrame):
+            logger.info("you speak")
+        elif isinstance(frame, VADUserStoppedSpeakingFrame):
+            logger.info("you stopped")
+        await self.push_frame(frame, direction)
+
+
+async def main():
+    transport = LocalAudioTransport(LocalAudioTransportParams(audio_in_enabled=True, audio_in_filter=AlkoveFilter()))
+    pipeline = Pipeline([transport.input(), VADProcessor(vad_analyzer=AlkoveVADAnalyzer()), SpeechLogger()])
+    runner = WorkerRunner(handle_sigint=sys.platform != "win32")
+    await runner.add_workers(PipelineWorker(pipeline))
+    await runner.run()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

pipecat_alkove-0.2.0/pipecat_alkove/__init__.py

@@ -0,0 +1,10 @@
+"""Alkove for Pipecat: `AlkoveFilter` as the transport's input filter, `AlkoveVADAnalyzer` as the VAD, both on the bot's CPU."""
+
+from alkove import Models
+
+from .filter import AlkoveFilter
+from .models import models
+from .vad import AlkoveVADAnalyzer
+
+__version__ = "0.2.0"
+__all__ = ["AlkoveFilter", "AlkoveVADAnalyzer", "Models", "models", "__version__"]

pipecat_alkove-0.2.0/pipecat_alkove/filter.py

@@ -0,0 +1,55 @@
+from __future__ import annotations
+
+import asyncio
+from typing import Any, Optional
+
+import numpy as np
+from pipecat.audio.filters.base_audio_filter import BaseAudioFilter
+from pipecat.frames.frames import FilterControlFrame, FilterEnableFrame, FilterUpdateSettingsFrame
+
+import alkove
+
+from .models import models as shared_models
+
+
+class AlkoveFilter(BaseAudioFilter):
+    """Alkove Focus as the transport's `audio_in_filter`: keeps the user's voice, the closest one or the voice of a print, and removes the others and the noise."""
+
+    def __init__(self, *, models: Optional[alkove.Models] = None, voiceprint: Any = None, strength: float = 1.0, normalize: bool = False) -> None:
+        self._models = models
+        self._voiceprint = voiceprint
+        self._strength = strength
+        self._normalize = normalize
+        self._enabled = True
+        self._live: Optional[alkove.Live] = None
+
+    async def start(self, sample_rate: int) -> None:
+        m = self._models or await asyncio.to_thread(shared_models)
+        self._live = alkove.Live(m, sample_rate, normalize=self._normalize, strength=self._strength, voiceprint=self._voiceprint)
+        self._live.set_enabled(self._enabled)
+
+    async def stop(self) -> None:
+        self._live = None
+
+    # FilterUpdateSettingsFrame: `strength` (0 to 1) and `voiceprint` (192 numbers, or None)
+    async def process_frame(self, frame: FilterControlFrame) -> None:
+        if isinstance(frame, FilterEnableFrame):
+            self._enabled = frame.enable
+            if self._live is not None:
+                self._live.set_enabled(frame.enable)
+        elif isinstance(frame, FilterUpdateSettingsFrame):
+            if "strength" in frame.settings:
+                self._strength = float(frame.settings["strength"])
+                if self._live is not None:
+                    self._live.set_strength(self._strength)
+            if "voiceprint" in frame.settings:
+                self._voiceprint = frame.settings["voiceprint"]
+                if self._live is not None:
+                    self._live.set_voiceprint(self._voiceprint)
+
+    # the samples that are ready, b"" while the first hop fills; disabled, the raw mic at the same delay
+    async def filter(self, audio: bytes) -> bytes:
+        if self._live is None:
+            return audio
+        out, _ = self._live.push(np.frombuffer(audio, dtype=np.int16))
+        return alkove.to_int16(out).tobytes()

pipecat_alkove-0.2.0/pipecat_alkove/models.py

@@ -0,0 +1,16 @@
+import threading
+from typing import Optional
+
+import alkove
+
+_lock = threading.Lock()
+_models: Optional[alkove.Models] = None
+
+
+def models(*, download: bool = True) -> alkove.Models:
+    """Focus and Cue, loaded once for the process and shared by every session: downloaded once into the cache, checked by their sha256; `download=False` on the event loop."""
+    global _models
+    with _lock:
+        if _models is None:
+            _models = alkove.Models.load(["focus", "cue"], download=download)
+        return _models

pipecat_alkove-0.2.0/pipecat_alkove/vad.py

@@ -0,0 +1,39 @@
+from __future__ import annotations
+
+from typing import Optional
+
+import numpy as np
+from pipecat.audio.vad.vad_analyzer import VADAnalyzer, VADParams
+
+import alkove
+
+from .models import models as shared_models
+
+
+class AlkoveVADAnalyzer(VADAnalyzer):
+    """Alkove Cue as Pipecat's VAD: a speech probability every 30 ms, at any input rate; behind `AlkoveFilter` it hears only the user."""
+
+    def __init__(self, *, sample_rate: Optional[int] = None, params: Optional[VADParams] = None, models: Optional[alkove.Models] = None) -> None:
+        # Cue was tuned at 0.5; Pipecat's default of 0.7 misses quiet speech
+        super().__init__(sample_rate=sample_rate, params=params or VADParams(confidence=0.5))
+        # loaded here, as Silero's analyzer does, rather than when the transport sets the rate on the event loop
+        self._models = models or shared_models()
+        self._processor: Optional[alkove.Processor] = None
+        self._last = 0.0
+
+    def set_sample_rate(self, sample_rate: int) -> None:
+        super().set_sample_rate(sample_rate)
+        self._processor = alkove.Processor(self._models, cue=True, trace=True, rate=self.sample_rate)
+        self._last = 0.0
+
+    def num_frames_required(self) -> int:
+        return round(0.03 * self.sample_rate)
+
+    # Cue answers one window late: the latest probability it gave
+    def voice_confidence(self, buffer: bytes) -> float:
+        if self._processor is None:
+            return 0.0
+        part = self._processor.push(np.frombuffer(buffer, dtype=np.int16))
+        if part.trace and part.trace["cue"]:
+            self._last = part.trace["cue"][-1]["speech"]
+        return self._last

pipecat_alkove-0.2.0/pyproject.toml

@@ -0,0 +1,26 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "pipecat-alkove"
+dynamic = ["version"]
+description = "Alkove for Pipecat: AlkoveFilter keeps the user's voice, AlkoveVADAnalyzer finds speech, on the bot's CPU"
+readme = "README.md"
+license = "Apache-2.0"
+license-files = ["LICENSE", "NOTICE"]
+requires-python = ">=3.10"
+authors = [{ name = "Eddy Bordi" }]
+keywords = ["voice", "pipecat", "noise-cancellation", "voice-isolation", "vad", "voice-agent", "on-device"]
+classifiers = [
+  "Programming Language :: Python :: 3",
+  "Topic :: Multimedia :: Sound/Audio :: Speech",
+]
+dependencies = ["alkove>=0.2,<0.3", "pipecat-ai>=1.0,<2", "numpy>=1.21"]
+
+[project.urls]
+Homepage = "https://alkove.ai"
+Repository = "https://github.com/alkove-ai/alkove"
+
+[tool.hatch.version]
+path = "pipecat_alkove/__init__.py"

pipecat_alkove-0.2.0/tests/test_pipecat.py

@@ -0,0 +1,97 @@
+"""The integration against the Pipecat classes it plugs into, on the SDK's test files."""
+
+import asyncio
+import wave
+from pathlib import Path
+
+import numpy as np
+import pytest
+from pipecat.audio.vad.vad_analyzer import VADState
+from pipecat.frames.frames import FilterEnableFrame, FilterUpdateSettingsFrame
+
+import alkove
+from pipecat_alkove import AlkoveFilter, AlkoveVADAnalyzer
+
+ROOT = Path(__file__).resolve().parents[3]
+FIXTURES = ROOT / "packages/alkove/test/fixtures"
+MODELS = ROOT / "packages/alkove/.cache/models"
+
+pytestmark = pytest.mark.skipif(not (MODELS / "alkove-focus-1-preview.alk").exists(), reason="the models are not in packages/alkove/.cache/models")
+
+
+@pytest.fixture(scope="module")
+def models():
+    return alkove.Models.load(["focus", "cue"], dir=MODELS)
+
+
+def wav(name, rate=16000):
+    with wave.open(str(FIXTURES / name)) as w:
+        pcm = np.frombuffer(w.readframes(w.getnframes()), dtype="<i2").astype(np.float32) / 32768
+    return alkove.to_int16(alkove.resample(pcm, 16000, rate))
+
+
+def chunks(pcm, n):
+    return [pcm[i : i + n].tobytes() for i in range(0, len(pcm), n)]
+
+
+def test_filter_is_alkove_live_on_the_transport_audio(models):
+    async def go():
+        f = AlkoveFilter(models=models)
+        await f.start(24000)
+        pcm = wav("mix.wav", 24000)
+        out = [await f.filter(c) for c in chunks(pcm, 480)]
+        live = alkove.Live(models, 24000)
+        want = [alkove.to_int16(live.push(np.frombuffer(c, np.int16))[0]).tobytes() for c in chunks(pcm, 480)]
+        assert out == want
+        got = np.frombuffer(b"".join(out), np.int16)
+        assert len(pcm) - 480 < len(got) <= len(pcm)
+        assert np.abs(got.astype(np.int32) - pcm[: len(got)]).max() > 1000
+        await f.stop()
+        assert await f.filter(b"\x01\x00") == b"\x01\x00"
+
+    asyncio.run(go())
+
+
+def test_filter_control_frames(models):
+    async def go():
+        pcm = wav("mix.wav")
+        f = AlkoveFilter(models=models)
+        await f.start(16000)
+        await f.process_frame(FilterEnableFrame(enable=False))
+        off = np.frombuffer(b"".join([await f.filter(c) for c in chunks(pcm, 320)]), np.int16)
+        # disabled: the raw mic, Focus's 256 samples late
+        assert np.abs(off[4000:].astype(np.int32) - pcm[4000 - 256 : len(off) - 256]).max() <= 1
+        g = AlkoveFilter(models=models)
+        await g.start(16000)
+        await g.process_frame(FilterUpdateSettingsFrame(settings={"strength": 0}))
+        raw = np.frombuffer(b"".join([await g.filter(c) for c in chunks(pcm, 320)]), np.int16)
+        assert np.abs(raw[4000:].astype(np.int32) - pcm[4000 - 256 : len(raw) - 256]).max() <= 1
+
+    asyncio.run(go())
+
+
+@pytest.mark.parametrize("rate", [16000, 48000])
+def test_vad_hears_speech_then_quiet(models, rate):
+    async def go():
+        vad = AlkoveVADAnalyzer(models=models)
+        vad.set_sample_rate(rate)
+        assert vad.num_frames_required() == rate * 3 // 100
+        pcm = np.concatenate([wav("speech.wav", rate), np.zeros(rate, np.int16)])
+        states = [await vad.analyze_audio(c) for c in chunks(pcm, rate // 50)]
+        # speech.wav's voice is clear from 1.26 s; SPEAKING after start_secs (0.2 s)
+        first = states.index(VADState.SPEAKING)
+        assert 1.3 < first / 50 < 1.7
+        assert states[-1] == VADState.QUIET
+        await vad.cleanup()
+
+    asyncio.run(go())
+
+
+def test_vad_confidence_is_cues_probability(models):
+    vad = AlkoveVADAnalyzer(models=models)
+    vad.set_sample_rate(16000)
+    pcm = wav("speech.wav")
+    got = [vad.voice_confidence(c) for c in chunks(pcm, 480)]
+    p = alkove.Processor(models, cue=True, trace=True)
+    want = [r["speech"] for c in chunks(pcm, 480) for r in (p.push(np.frombuffer(c, np.int16)).trace or {"cue": []})["cue"]]
+    assert got[1 : len(want) + 1] == want