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 — official ai‑coustics plugin for LiveKit
• Pipecat — ai‑coustics audio filter for Pipecat

Learn more in our documentation