Metadata-Version: 2.4
Name: kiarina-agi-audio
Version: 2.9.0
Summary: Audio sources, speech, tagging, embeddings, and voice activity for AI agents
Project-URL: Homepage, https://github.com/kiarina/kiarina-python
Project-URL: Repository, https://github.com/kiarina/kiarina-python
Project-URL: Issues, https://github.com/kiarina/kiarina-python/issues
Project-URL: Changelog, https://github.com/kiarina/kiarina-python/blob/main/packages/kiarina-agi-audio/CHANGELOG.md
Project-URL: Documentation, https://github.com/kiarina/kiarina-python/tree/main/packages/kiarina-agi-audio#readme
Author-email: kiarina <kiarinadawa@gmail.com>
Maintainer-email: kiarina <kiarinadawa@gmail.com>
License-Expression: MIT
Keywords: agents,ai,audio,embeddings,speech
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Typing :: Typed
Requires-Python: >=3.12
Requires-Dist: jaxtyping>=0.3.3
Requires-Dist: kiarina-agi-base>=2.7.0
Requires-Dist: kiarina-agi-data>=2.7.0
Requires-Dist: kiarina-utils-app>=2.4.0
Requires-Dist: kiarina-utils-common>=2.8.0
Requires-Dist: kiarina-utils-file>=2.3.1
Requires-Dist: numpy<3,>=2.0
Requires-Dist: pydantic-settings-manager>=3.2.0
Requires-Dist: pydantic-settings<3,>=2.10.1
Requires-Dist: pydantic<3,>=2.11.7
Provides-Extra: all
Requires-Dist: ai-edge-litert<3,>=2.1.4; extra == 'all'
Requires-Dist: audioop-lts>=0.2.2; (python_version >= '3.13') and extra == 'all'
Requires-Dist: google-genai<3,>=1.65.0; extra == 'all'
Requires-Dist: kiarina-lib-google>=2.4.0; extra == 'all'
Requires-Dist: kiarina-lib-openai>=2.3.1; extra == 'all'
Requires-Dist: onnxruntime>=1.25.1; extra == 'all'
Requires-Dist: openai<3,>=2.0.1; extra == 'all'
Requires-Dist: pydub<1,>=0.25.1; extra == 'all'
Requires-Dist: sounddevice<1,>=0.5.2; extra == 'all'
Requires-Dist: soundfile<1,>=0.13.1; extra == 'all'
Requires-Dist: tiktoken>=0.13.0; extra == 'all'
Provides-Extra: asr-provider-google
Requires-Dist: google-genai<3,>=1.65.0; extra == 'asr-provider-google'
Requires-Dist: kiarina-lib-google>=2.4.0; extra == 'asr-provider-google'
Provides-Extra: asr-provider-openai
Requires-Dist: kiarina-lib-openai>=2.3.1; extra == 'asr-provider-openai'
Requires-Dist: openai<3,>=2.0.1; extra == 'asr-provider-openai'
Provides-Extra: audio-embedding-provider-clap-onnx
Requires-Dist: onnxruntime>=1.25.1; extra == 'audio-embedding-provider-clap-onnx'
Provides-Extra: audio-embedding-provider-ecapa-tdnn-onnx
Requires-Dist: onnxruntime>=1.25.1; extra == 'audio-embedding-provider-ecapa-tdnn-onnx'
Provides-Extra: audio-source-file
Requires-Dist: soundfile<1,>=0.13.1; extra == 'audio-source-file'
Provides-Extra: audio-source-mic
Requires-Dist: sounddevice<1,>=0.5.2; extra == 'audio-source-mic'
Provides-Extra: audio-tagging-provider-yamnet
Requires-Dist: ai-edge-litert<3,>=2.1.4; extra == 'audio-tagging-provider-yamnet'
Provides-Extra: scd-provider-pyannote
Requires-Dist: onnxruntime>=1.25.1; extra == 'scd-provider-pyannote'
Provides-Extra: tts-provider-command
Requires-Dist: audioop-lts>=0.2.2; (python_version >= '3.13') and extra == 'tts-provider-command'
Requires-Dist: pydub<1,>=0.25.1; extra == 'tts-provider-command'
Provides-Extra: tts-provider-google
Requires-Dist: audioop-lts>=0.2.2; (python_version >= '3.13') and extra == 'tts-provider-google'
Requires-Dist: google-genai<3,>=1.65.0; extra == 'tts-provider-google'
Requires-Dist: kiarina-lib-google>=2.4.0; extra == 'tts-provider-google'
Requires-Dist: pydub<1,>=0.25.1; extra == 'tts-provider-google'
Provides-Extra: tts-provider-mock
Requires-Dist: audioop-lts>=0.2.2; (python_version >= '3.13') and extra == 'tts-provider-mock'
Requires-Dist: pydub<1,>=0.25.1; extra == 'tts-provider-mock'
Provides-Extra: tts-provider-openai
Requires-Dist: audioop-lts>=0.2.2; (python_version >= '3.13') and extra == 'tts-provider-openai'
Requires-Dist: kiarina-lib-openai>=2.3.1; extra == 'tts-provider-openai'
Requires-Dist: openai<3,>=2.0.1; extra == 'tts-provider-openai'
Requires-Dist: pydub<1,>=0.25.1; extra == 'tts-provider-openai'
Requires-Dist: tiktoken>=0.13.0; extra == 'tts-provider-openai'
Provides-Extra: vad-provider-silero
Requires-Dist: onnxruntime>=1.25.1; extra == 'vad-provider-silero'
Description-Content-Type: text/markdown

# kiarina-agi-audio

English | [日本語](README.ja.md)

[![PyPI](https://img.shields.io/pypi/v/kiarina-agi-audio.svg)](https://pypi.org/project/kiarina-agi-audio/)
[![Python](https://img.shields.io/badge/python-3.12%2B-blue.svg)](https://www.python.org/downloads/)
[![License](https://img.shields.io/badge/license-MIT-blue.svg)](../../LICENSE)

> [!NOTE] What is this?
> `kiarina-agi-audio` provides audio sources, speech-to-text, text-to-speech, voice activity detection, speaker change detection, audio tagging, and audio embeddings for AI agents.

## Dependencies

### Required Dependencies

| Package | Version | License |
| --- | --- | --- |
| [jaxtyping](https://github.com/patrick-kidger/jaxtyping) | `>=0.3.3` | MIT |
| [kiarina-agi-base](../kiarina-agi-base/) | `>=2.7.0` | MIT |
| [kiarina-agi-data](../kiarina-agi-data/) | `>=2.7.0` | MIT |
| [kiarina-utils-app](../kiarina-utils-app/) | `>=2.4.0` | MIT |
| [kiarina-utils-common](../kiarina-utils-common/) | `>=2.8.0` | MIT |
| [kiarina-utils-file](../kiarina-utils-file/) | `>=2.3.1` | MIT |
| [NumPy](https://github.com/numpy/numpy) | `>=2.0,<3` | BSD-3-Clause |
| [Pydantic](https://github.com/pydantic/pydantic) | `>=2.11.7,<3` | MIT |
| [pydantic-settings](https://github.com/pydantic/pydantic-settings) | `>=2.10.1,<3` | MIT |
| [pydantic-settings-manager](https://github.com/kiarina/pydantic-settings-manager) | `>=3.2.0` | MIT |

### Optional Dependencies

| Package | Extras |
| --- | --- |
| ai-edge-litert | `audio-tagging-provider-yamnet` |
| audioop-lts | `tts-provider-command`<br>`tts-provider-google`<br>`tts-provider-mock`<br>`tts-provider-openai` |
| google-genai | `asr-provider-google`<br>`tts-provider-google` |
| kiarina-lib-google | `asr-provider-google`<br>`tts-provider-google` |
| kiarina-lib-openai | `asr-provider-openai`<br>`tts-provider-openai` |
| onnxruntime | `audio-embedding-provider-clap-onnx`<br>`audio-embedding-provider-ecapa-tdnn-onnx`<br>`scd-provider-pyannote`<br>`vad-provider-silero` |
| openai | `asr-provider-openai`<br>`tts-provider-openai` |
| pydub | `tts-provider-command`<br>`tts-provider-google`<br>`tts-provider-mock`<br>`tts-provider-openai` |
| sounddevice | `audio-source-mic` |
| soundfile | `audio-source-file` |
| tiktoken | `tts-provider-openai` |

The `all` Extra installs every optional dependency listed above.
