---
license: other
license_name: aic-sdk-binary-license
license_link: https://huggingface.co/ai-coustics/audio-insight/blob/main/LICENSE
pipeline_tag: audio-classification
library_name: aic-sdk
tags:
  - audio
  - audio-insight
  - audio-insights
  - audio-quality
  - quality-estimation
  - call-quality
  - observability
  - voice-ai
  - voice-agents
  - real-time
  - ai-coustics
---

# Audio Insight — ai-coustics

**Predict and diagnose downstream failures in Voice AI stacks.**

Tyto is an audio insight model by [ai-coustics](https://ai-coustics.com/). Tyto predicts whether the audio reaching your agent will cause downstream failures, with a single risk score and the likely cause behind it. Catch degraded audio before it breaks your voice agent — in real time or post-call. *Real-time audio intelligence that makes Voice AI work in production. Not just in the lab.* Inference runs through the [`aic-sdk`](https://pypi.org/project/aic-sdk/) Python package (also available for Rust, C/C++, Node.js, and WebAssembly).

## Setup

1. Install the SDK:
   ```bash
   pip install aic-sdk
   ```
2. [Create a free SDK key](https://developers.ai-coustics.com) on the ai-coustics playground — 30-day trial included, no credit card required.

## Usage

```python
# initialize the audio insight analyzer
import aic_sdk as aic

model = aic.Model.from_file(aic.Model.download("tyto-1.1-l-16khz", "./models"))
analyzer = aic.FileAnalyzer(model, "{aic-sdk-key}")  # get a free SDK key: https://developers.ai-coustics.com/login

# score a mono float32 buffer — one AnalysisResult per 5-second window
results = analyzer.analyze(audio, sample_rate)

# predict downstream failures, with the exact cause behind them
for window in results:
    print(f"risk={window.risk_score:.2f} noise={window.noise:.2f} interfering={window.interfering_speech:.2f}")
```

## What you get

Every analysis window returns one headline score plus six diagnostic dimensions (all 0.0–1.0; lower is less problematic, except loudness):

| Field | Meaning |
|---|---|
| `risk_score` | Headline score — predicted likelihood of failure of downstream STT, VAD, turn-taking, or speech-to-speech models |
| `noise` | Ambient / environmental noise |
| `speaker_reverb` | Speaker distance and reverberation |
| `speaker_loudness` | Speaker loudness |
| `interfering_speech` | Interference from additional speakers |
| `packet_loss` | Dropouts / discontinuities (packet loss, frame erasure, jitter, CPU overload) |
| `codec_degradation` | Artifacts from lossy or narrowband speech codecs |

### Streaming / real-time analysis

For live audio, use a `Collector`/`Analyzer` pair: the collector buffers on the audio thread (real-time safe), the analyzer runs on a separate thread (analysis is computationally expensive):

```python
import aic_sdk as aic

model = aic.Model.from_file(aic.Model.download("tyto-1.1-l-16khz", "./models"))
collector, analyzer = aic.analyzer_pair(model, "{aic-sdk-key}")  # get a free SDK key: https://developers.ai-coustics.com/login

config = aic.ProcessorConfig.optimal(model)
collector.initialize(config)

# audio thread (real-time safe):
for block in audio_blocks():              # np.ndarray, config.block_size samples
    collector.buffer(block)

# non-audio thread, whenever you want a reading:
result = analyzer.analyze_buffered()
print(result.risk_score, result.packet_loss, result.codec_degradation)
```

## Model variants

Weights are hosted on the ai-coustics artifact CDN. `aic.Model.download()` fetches the latest compatible artifact and verifies its checksum automatically; the direct links below are for manual download.

| SDK model ID | Sample rate | Artifact | SHA-256 (prefix) |
|---|---|---|---|
| **`tyto-1.1-l-16khz`** — latest, recommended | 16 kHz | [v7](https://artifacts.ai-coustics.io/models/tyto-1-1-l-16khz/v7/tyto_1_1_l_16khz_t7y7v3h5_v58.aicmodel) | `d350724ed394` |
| `tyto-l-16khz` (previous generation) | 16 kHz | [v6](https://artifacts.ai-coustics.io/models/tyto-l-16khz/v6/tyto_l_16khz_yhlek4hc_v43.aicmodel) | `02bb6b7fbce5` |

Full SHA-256 checksums for every artifact are listed next to each download at [artifacts.ai-coustics.io](https://artifacts.ai-coustics.io).

## Related ai-coustics models

- 🔊 **[Speech Enhancement](https://huggingface.co/ai-coustics/speech-enhancement)** — real-time, ASR-optimized speech enhancement (Quail & Rook)
- 🎙️ **[Voice Activity Detection](https://huggingface.co/ai-coustics/voice-activity-detection)** — real-time, noise-robust turn-taking for voice agents

## Resources

- 📖 Documentation & model guide: [docs.ai-coustics.com](https://docs.ai-coustics.com)
- 🧩 Framework quickstarts: [LiveKit](https://docs.ai-coustics.com/models/get-started/livekit-quickstart), [Pipecat](https://github.com/pipecat-ai/pipecat/blob/main/examples/voice/voice-aicoustics.py)
- 📦 Python SDK: [pypi.org/project/aic-sdk](https://pypi.org/project/aic-sdk/)
- 🔑 Free SDK key: [developers.ai-coustics.com](https://developers.ai-coustics.com)
- 🏢 Enterprise licensing: [ai-coustics.com](https://ai-coustics.com/)