aic-sdk
Python bindings for ai-coustics SDK
Decision gist · record as of 2026-08-14
Yes, if you need audio enhancement or voice activity detection and have a valid ai-coustics license. The SDK is actively maintained, permissively licensed, has no known vulnerabilities, and offers both sync and async APIs for flexible integration. Install friction is moderate due to compiled wheels, but platform coverage is broad. Requires Python >=3.10 and an environment variable for the license key.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python >=3.10 and a valid ai-coustics license key set in the AIC_SDK_LICENSE environment variable.
- Medium install friction due to compiled wheels across multiple Python versions and platforms.
- Active maintenance with recent release (4 days old).
License · maintenance · safety
permissive license (permissive) — Licensed under Apache Software License (permissive), allowing commercial and private use with minimal restrictions.
last release 2026-08-10 (4 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 296,351 downloads/mo, #7,898 on PyPI
Alternatives
Verify before relying
pip install aic-sdk
import aic_sdk as aic
import numpy as np
import os
license_key = os.environ["AIC_SDK_LICENSE"]
model_path = aic.Model.download("quail-vf-2.2-l-16khz", "./models")
model = aic.Model.from_file(model_path)
config = aic.ProcessorConfig.optimal(model)
processor = aic.Processor(model, license_key, config)
audio_block = np.zeros(config.block_size, dtype=np.float32)
processed = processor.process(audio_block)- Whether the SDK's telemetry (OpenTelemetry) is enabled by default and what data it collects.
- Performance characteristics and latency for real-time audio processing at different sample rates.
- Whether downloaded models are cached or re-downloaded on each call.
- Exact licensing terms and any restrictions on model redistribution or commercial deployment.
What it is and what it does
aic-sdk is a Python wrapper around ai-coustics' compiled audio processing engine, providing access to real-time audio enhancement, voice activity detection (VAD), and analysis capabilities. It processes audio as 1D mono numpy arrays and requires a license key to initialize. The SDK supports both synchronous and asynchronous APIs, allowing single-block processing or concurrent batch operations. It depends only on numpy for array handling and includes pre-built wheels for Python 3.10–3.14 across macOS, Linux, and Windows architectures.
The package is designed for streaming audio workflows: you load a model from disk or download it from ai-coustics' CDN, configure a processor with sample rate and block size, and then feed audio blocks through it. The processor maintains internal state and can be controlled via a thread-safe context object. VAD and enhancement can run independently or in parallel on the same audio stream, and telemetry can be configured per-instance via OpenTelemetry settings.
Use it for
- Real-time voice enhancement in VoIP or conferencing applications by processing audio blocks as they arrive.
- Voice activity detection in speech recognition pipelines to filter silence and reduce processing overhead.
- Audio quality analysis and diagnostics using the Tyto analysis model on recorded or streaming audio.
- Batch audio enhancement in post-processing workflows by downloading models and processing multiple files.
- Concurrent audio processing in multi-threaded applications using async APIs and processor contexts.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need audio enhancement or voice activity detection and have a valid ai-coustics license.
The SDK is actively maintained, permissively licensed, has no known vulnerabilities, and offers both sync and async APIs for flexible integration. Install friction is moderate due to compiled wheels, but platform coverage is broad. Requires Python >=3.10 and an environment variable for the license key.
Install
aic-sdk on PyPI
Before you install
Medium install friction due to compiled wheels across multiple Python versions and platforms. Active maintenance with recent release (4 days old). Requires a license key from developers.ai-coustics.com to function.
Requires Python >=3.10 and a valid ai-coustics license key set in the AIC_SDK_LICENSE environment variable.
License in practice
Licensed under Apache Software License (permissive), allowing commercial and private use with minimal restrictions.
Quickstart
pip install aic-sdk
import aic_sdk as aic
import numpy as np
import os
license_key = os.environ["AIC_SDK_LICENSE"]
model_path = aic.Model.download("quail-vf-2.2-l-16khz", "./models")
model = aic.Model.from_file(model_path)
config = aic.ProcessorConfig.optimal(model)
processor = aic.Processor(model, license_key, config)
audio_block = np.zeros(config.block_size, dtype=np.float32)
processed = processor.process(audio_block)Verify before relying
- Whether the SDK's telemetry (OpenTelemetry) is enabled by default and what data it collects.
- Performance characteristics and latency for real-time audio processing at different sample rates.
- Whether downloaded models are cached or re-downloaded on each call.
- Exact licensing terms and any restrictions on model redistribution or commercial deployment.
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 1 packagenumpy |
| Maintenance | Actively maintained 4 days since the last release |
| First released | |
| Downloads | 296,351 / month, #7,898 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableLicense :: OSI Approved :: Apache Software LicenseOperating System :: MacOSOperating System :: Microsoft :: WindowsOperating System :: POSIX :: LinuxProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Programming Language :: RustTopic :: Multimedia :: Sound/Audio :: Speech |
Evidence: aic_sdk-3.1.0-cp310-cp310-macosx_10_12_x86_64.whl; aic_sdk-3.1.0-cp310-cp310-macosx_11_0_arm64.whl; aic_sdk-3.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; aic_sdk-3.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; aic_sdk-3.1.0-cp310-cp310-win_amd64.whl; aic_sdk-3.1.0-cp310-cp310-win_arm64.whl; aic_sdk-3.1.0-cp311-cp311-macosx_10_12_x86_64.whl; aic_sdk-3.1.0-cp311-cp311-macosx_11_0_arm64.whl; aic_sdk-3.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; aic_sdk-3.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; aic_sdk-3.1.0-cp311-cp311-win_amd64.whl; aic_sdk-3.1.0-cp311-cp311-win_arm64.whl; aic_sdk-3.1.0-cp312-cp312-macosx_10_12_x86_64.whl; aic_sdk-3.1.0-cp312-cp312-macosx_11_0_arm64.whl; aic_sdk-3.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; aic_sdk-3.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; aic_sdk-3.1.0-cp312-cp312-win_amd64.whl; aic_sdk-3.1.0-cp312-cp312-win_arm64.whl; aic_sdk-3.1.0-cp313-cp313-macosx_10_12_x86_64.whl; aic_sdk-3.1.0-cp313-cp313-macosx_11_0_arm64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “audio enhancement python”
- aic-sdkPython bindings for ai-coustics audio enhancement, voice activity…
- livekit-plugins-ai-cousticsA LiveKit plugin that applies Ai-coustics audio enhancement to…
- sherpa-onnx-coresherpa-onnx-core provides pre-built ONNX runtime binaries for speech…
Give your agent the search over MCP, or paste the wish link into any chat.
More Speech packages
Performs speech recognition and transcription using multiple online and offline engines, including Google, OpenAI Whisper, CMU Sphinx, and others.
The main gotcha is that most engines require optional dependencies or API credentials.
gTTS converts text to speech using Google Translate's API, writing MP3 audio to files, file-like objects, or stdout via Python library or command-line tool.
However, be aware that it depends on Google Translate's undocumented API—upstream changes can break it without notice, and it is not a substitute for official Google…
Lhotse prepares multimodal (speech, audio, video, image, text) data for machine learning model training with flexible pipelines, on-the-fly augmentation, and efficient data loading.
Install it if you are building speech, audio, or multimodal training pipelines; skip it if you only need simple audio I/O without data augmentation or complex dataset…
Piper TTS is a local neural text-to-speech engine that converts text to speech using embedded phonemization, with support for multiple languages and voices.
FunASR is a speech recognition toolkit that transcribes audio offline or via streaming, with integrated voice activity detection, speaker identification, punctuation restoration, and emotion/audio-event tagging across multiple languages and deployment targets.
Install it if you need speaker diarization, emotion detection, streaming support, or self-hosted deployment.
PocketSphinx provides Python bindings for Carnegie Mellon University's open-source speech recognition engine, enabling continuous speech-to-text and keyword spotting from live microphone input or audio files.
See also livekit-plugins-ai-coustics · webrtcvad · kugelaudio · webrtcvad-wheels · pyrnnoise · audiomentations · livekit-plugins-azure · pymicro-vad · speechmatics-voice · deepgram-sdk