ai-coustics website screenshot

ai-coustics

ai-coustics is a Berlin-based audio-intelligence company providing a real-time speech-enhancement SDK for Voice AI systems. Its Quail, Rook, Quail VAD, Quail Voice Focus, and Tyto models remove background noise, isolate the primary speaker, detect voice activity, and score audio risk to make automatic speech recognition (ASR) more accurate and voice-activity detection steadier in the real world. The SDK runs on the proprietary AirTen CPU-first inference runtime (no GPU, no ONNX dependency) with sub-30ms latency, and ships official bindings for Python, Rust, Node.js, C, C++, and WebAssembly, plus LiveKit and Pipecat integrations. Authentication uses self-service license keys or short-lived JWTs; a legacy REST API was sunset in favor of the SDK. Backed by Partech.

ai-coustics publishes 1 API on the APIs.io network. Tagged areas include Company, Ai/Ml, Audio, Speech Enhancement, and Voice AI.

ai-coustics’ developer surface includes documentation, API reference, getting-started guide, engineering blog, pricing, signup flow, changelog, and 15 more developer resources.

36.2/100 thin ▬ flat Agent 10/100 human only Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
1 APIs
CompanyAi/MlAudioSpeech EnhancementVoice AISpeech RecognitionSDKReal-TimeMachine Learning

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 36.2/100 · thin
Contract Quality 0.0 / 25
Developer Ergonomics 12.2 / 20
Commercial Clarity 8.9 / 20
Operational Transparency 5.8 / 13
Governance 0.0 / 12
Discoverability 9.3 / 10
Agent readiness — 10/100 · human only
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 15
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/ai-coustics: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 1

Individual APIs this provider publishes, each with its own machine-readable definition.

ai-coustics SDK

Real-time speech-enhancement SDK (Quail, Rook, Quail VAD, Quail Voice Focus, Tyto) with a JWT token-minting API for client authentication. Delivered as native language bindings.

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Ai Coustics Authentication

licenseKey/jwt/http-basic · 3 schemes

SECURITY

Ai Coustics Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 4

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 2

Pagination, idempotency, versioning, errors, and events

Build 3

SDKs, sample code, and the tooling you integrate with

Access & Security 2

Authentication, authorization, and security posture

Operate 3

Status, limits, changes, and where to get help

Commercial 3

Pricing, plans, and the legal terms of use

Company 2

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
aid: ai-coustics
name: ai-coustics
description: ai-coustics is a Berlin-based audio-intelligence company providing a real-time speech-enhancement SDK for Voice
  AI systems. Its Quail, Rook, Quail VAD, Quail Voice Focus, and Tyto models remove background noise, isolate the primary
  speaker, detect voice activity, and score audio risk to make automatic speech recognition (ASR) more accurate and voice-activity
  detection steadier in the real world. The SDK runs on the proprietary AirTen CPU-first inference runtime (no GPU, no ONNX
  dependency) with sub-30ms latency, and ships official bindings for Python, Rust, Node.js, C, C++, and WebAssembly, plus
  LiveKit and Pipecat integrations. Authentication uses self-service license keys or short-lived JWTs; a legacy REST API was
  sunset in favor of the SDK. Backed by Partech.
url: https://raw.githubusercontent.com/api-evangelist/ai-coustics/refs/heads/main/apis.yml
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://framerusercontent.com/images/1bJnBz9PHkEocX9YfiBn69WgGao.png
x-type: company
x-source: vc-portfolio
x-backed-by:
- partech
x-tier: enriched
x-tier-reason: enrichment-pipeline
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-18'
tags:
- Company
- Ai/Ml
- Audio
- Speech Enhancement
- Voice AI
- Speech Recognition
- SDK
- Real-Time
- Machine Learning
apis:
- name: ai-coustics SDK
  description: Real-time speech-enhancement SDK (Quail, Rook, Quail VAD, Quail Voice Focus, Tyto) with a JWT token-minting
    API for client authentication. Delivered as native language bindings.
  humanURL: https://docs.ai-coustics.com/
  baseURL: https://api.ai-coustics.io/v1/
  tags:
  - Audio
  - Speech Enhancement
  - Voice AI
  - SDK
  properties:
  - type: Documentation
    url: https://docs.ai-coustics.com/
  - type: GettingStarted
    url: https://docs.ai-coustics.com/models/get-started/sdk-quickstart
  - type: APIReference
    url: https://docs.ai-coustics.com/reference/sdk/models
  - type: Authentication
    url: authentication/ai-coustics-authentication.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
  X-twitter: apievangelist
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://ai-coustics.com/
- type: DeveloperPortal
  url: https://developers.ai-coustics.com/
- type: Documentation
  url: https://docs.ai-coustics.com/
- type: APIReference
  url: https://docs.ai-coustics.com/reference/sdk/models
- type: GettingStarted
  url: https://docs.ai-coustics.com/models/get-started/sdk-quickstart
- type: Blog
  url: https://ai-coustics.com/blog
- type: GitHubOrganization
  url: https://github.com/ai-coustics
- type: Pricing
  url: https://ai-coustics.com/pricing
- type: SignUp
  url: https://developers.ai-coustics.com/signup
- type: TermsOfService
  url: https://ai-coustics.com/terms
- type: PrivacyPolicy
  url: https://ai-coustics.com/privacy
- type: StatusPage
  url: https://status.ai-coustics.com/
- type: Deprecation
  url: https://docs.ai-coustics.com/models/older-models/deprecated-models
- type: ChangeLog
  url: changelog/ai-coustics-changelog.yml
- type: Authentication
  url: authentication/ai-coustics-authentication.yml
- type: Packages
  url: packages/ai-coustics-packages.yml
- type: SDKs
  url: packages/ai-coustics-packages.yml
- type: LLMsTxt
  url: llms/ai-coustics-llms.txt
- type: Lifecycle
  url: lifecycle/ai-coustics-lifecycle.yml
- type: Sandbox
  url: sandbox/ai-coustics-sandbox.yml
- type: Conventions
  url: conventions/ai-coustics-conventions.yml
- type: DomainSecurity
  url: security/ai-coustics-domain-security.yml
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence