docs/intro.md

# Welcome! Try ai‑coustics Quail Voice Focus 2.0

Our flagship real‑time enhancement model is engineered specifically for Speech-to-Text (STT). By isolating the foreground speaker and suppressing background chatter, it preserves the critical phonetic details that AI systems need to transcribe accurately.

> **Note:** This model is optimized for machine performance rather than perceptual quality. The output may sound less processed to a listener, but this ensures higher transcription accuracy.

## 🚀 Now Native in LiveKit & Pipecat

Build production-ready voice agents with ai‑coustics audio intelligence available natively in the most widely used real-time infrastructure layers:

- **[LiveKit](https://github.com/livekit/plugins-ai-coustics-python)** — official ai‑coustics plugin for LiveKit
- **[Pipecat](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/audio/filters/aic_filter.py)** — ai‑coustics audio filter for Pipecat

[Learn more in our documentation](https://docs.ai-coustics.com/guides/models#quail-voice-focus-2-0-l-16-khz)