ai-coustics
Real-time speech enhancement SDK that helps Voice AI work reliably in noisy, real-world audio.
- SI Score
- Not scored
- Pricing
- Not confirmed
- Free plan
- Not confirmed
- Sign-up required
- Not confirmed
Ask SI about ai-coustics
Answers use saved listing facts and recorded sources.Homepage screenshot
What it does
ai-coustics builds an audio reliability layer for Voice AI. Its models clean and analyze speech before it reaches speech-to-text, voice activity detection and language models. Quail covers ASR-optimized speech enhancement, speaker isolation and multi-speaker audio. Tyto scores incoming audio and points to the cause of degraded input. A dedicated voice activity detection model and Sparrow perceptual audio quality enhancement are also listed. SDKs are offered for Python, Node.js, C, C++, Rust and WebAssembly, with integrations for LiveKit and Pipecat. A developer platform lets teams test models and generate SDK keys, and the company books technical demos.
The site links to pricing, documentation, a blog, a glossary and a developer platform signup. Documentation includes a LiveKit quickstart with complete Python and Node.js examples for adding voice activity detection and Tyto analysis to a LiveKit room. The company states the SDK needs no GPU and runs inference at 8 kHz and 16 kHz PCM, and that models are trained on a wide range of noise types and acoustic environments.