Aurigin.ai

What Aurigin.ai does

Aurigin.ai is a Zurich-based deep-tech company that builds real-time audio deepfake detection and voice anti-spoofing technology for enterprise and institutional customers. Its core engine is the Apollo detection model, currently in V4, which analyzes audio streams in under 50 milliseconds to determine whether a voice is AI-generated or authentic and simultaneously offers voice biometric identification through enrolled voiceprints. The company serves financial institutions, contact centers, video conferencing operators, and forensic investigators, with native integrations across Microsoft Teams, Zoom, Google Meet, Webex, and WhatsApp and language-agnostic support across 80+ languages.

The product portfolio is organized into three flagship offerings—AuriginGuard for real-time vishing protection on enterprise communications, AuriginShield for B2B biometric-pipeline integration, and AuriginInspect for forensic segment-level audio analysis—all powered by the Apollo model and exposed via the AuriginAPI REST interface with Python, TypeScript, and Swift SDKs and on-premise Docker/Kubernetes deployment. The company reports 1M+ hours of training data, continuous retraining against emerging synthesis engines (ElevenLabs, XTTS, RVC, Bark, open-source cloners), and benchmark-leading performance including 96.75% accuracy with a 1.5% false-positive rate in the independent Podonos benchmark and infrastructure economics approximately 100x cheaper than competitors at the same accuracy tier.

Revenue is generated through tiered usage-based API subscriptions in Swiss francs (CHF 0 to CHF 1,300 per month self-serve tiers) and custom enterprise contracts for on-premise deployments, dedicated SLAs, and integration support. The company employs 1–10 people, with leadership drawn from ETH Zurich, Sennheiser, McKinsey, PwC, and Lombard Odier, and has publicly named enterprise customers including 1291 Group (wealth management), Swisscom Digital Trust (telecom/financial services KYC), and the Misinformation Combat Alliance's Deepfakes Analysis Unit in India.

Name

Aurigin.ai

Legal name

Aurigin AI

Website

https://aurigin.ai

Company type

Private

Founded year

2024

Operating status

Operating

Headcount range

11–50 employees

Short description

Aurigin.ai is a Zurich-based deep-tech company that provides real-time audio deepfake detection and voice anti-spoofing technology via API and SDKs, serving financial institutions, contact centers, video conferencing operators, and forensic teams across 80+ languages.

Ownership category

akta.pro rank

Product category

AI Voice Security Software

NAICS

Software Publishers (513210)

SIC

Services-Prepackaged Software (7372)

akta.pro primary industry

Content Authenticity, Watermarking & Deepfake Detection (HDAAAKAK)

akta.pro secondary industries

Speaker Recognition & Voice Biometrics (HDAAAFAF), Automatic Speech Recognition (ASR) (HDAAAFAA)

Keywords

• Deepfake detection
• Voice anti-spoofing
• Audio authentication
• Voice biometric security
• Real-time audio AI

Headquarters

HQ city

Zürich

HQ country

Switzerland

HQ region

Europe

Offices1 record

Markets served

GTM type

B2B

Offering type

Software

Cost components

Technology or R&D, Personnel, Infrastructure, Marketing or Sales, Operations

Revenue model

1. API Credits: Usage-based API pricing with credits consumed per minute of audio analyzed. Tiered plans from free (50 one-time credits) to Business (5,000 credits/month).
2. Subscription Plans: Monthly subscription tiers (Personal CHF 20, Team CHF 160, Business CHF 1,300) with bundled credits and support levels. Annual billing available with 20% discount.
3. Enterprise Custom: Custom SLAs, on-premise deployment options, and dedicated support for enterprise customers requiring tailored solutions.

Pricing tiers

Go-to-market motion2 records

Distribution channels4 records

Marketing channels6 records

Core offering

Aurigin.ai provides real-time audio deepfake detection and voice anti-spoofing through an API-first platform powered by its proprietary Apollo V4 model. The offering combines deepfake classification, voice biometric verification, and forensic-grade segment-level analysis to protect voice biometrics, contact center authentication, video conferencing, and KYC workflows across 80+ languages, delivered via cloud API, on-premise deployment, or native SDKs.

Product overview

Aurigin.ai is a Swiss deep-tech security company offering a unified platform for real-time audio deepfake detection and voice anti-spoofing. The product portfolio centers on the Apollo deepfake detection model (now in V4 generation) powering three integrated products: AuriginGuard provides real-time vishing protection for enterprise video conferencing (Teams, Zoom, Google Meet, Webex); AuriginShield delivers voice anti-spoofing for contact centers and biometric systems; and AuriginInspect enables forensic audio analysis with segment-level deepfake localization. All products are accessible via the AuriginAPI (REST API with Python/TypeScript/Swift SDKs) for cloud or on-premise deployment.

Differentiator

Problem solved

Functional benefit

Brands

• AuriginGuard: Real-time vishing protection for enterprise communication - analyzes calls on Teams, Zoom, Google Meet, and Webex in real time to detect AI-generated voices
• AuriginShield
• AuriginInspect
• Apollo
• Real or Fake

Products and services

• AuriginGuard Real-time vishing protection for enterprise communication that analyzes every call on Microsoft Teams, Zoom, Google Meet, Webex and WhatsApp, silently detecting AI-generated voices, verifying caller identity via voice biometrics, and identifying social engineering patterns. Three protection layers include synthetic voice detection, voice identity verification, and behavioral style matching.
• AuriginShield Voice anti-spoofing product for B2B integration that detects synthetic, cloned and AI-generated voices in real time, protecting biometric pipelines from spoofing attacks across 40+ languages. Designed for contact center security and authentication providers.
• AuriginInspect Audio analysis tool for forensic investigations that provides granular, segment-level detection identifying which segments of a recording are real versus fake, enabling audio/video forensics authentication for legal and investigative use cases.
• AuriginAPI REST API providing dual-layer voice security: deepfake detection to verify whether audio is AI-generated, and Voice ID to confirm speaker identity by matching voice samples against enrolled voiceprints. Available via cloud API and on-premise Docker/Kubernetes deployments, with native SDKs for Python, TypeScript and Swift.
• Apollo V4 Latest generation of Aurigin's proprietary deepfake detection model powering all Aurigin products. Extends detection into real-world communication complexity including meeting platform pipelines, codec degradation, and network variability across 80+ languages, with 98%+ accuracy and sub-50ms latency. Doubled training data, tripled model size, quadrupled training compute compared to V3.

Quantifiable outcome

• 96.75% accuracy with 1.5% false positive rate in Podonos independent benchmark
• +6 more outcomes

Named customers3 records

Segments4 records

Ideal customer profiles4 records

Technology focussed Yes

API detail

Has API

Yes

API docs

API detail

Core technology

AI maturity

App detail

Integration6 records

AI capability4 records

Feature6 records

Partnerships

Three partnerships are on record, tiered core.

• Swisscom Digital TrustcoreTechnology or Integration · 14 November 2025Integration of voice-based liveness verification and AI deepfake detection into Swisscom's existing KYC identity infrastructure. System analyzes short audio samples in real time (under 15 seconds) to verify liveness and link voice fingerprint to customer digital identity for reusable authentication across future interactions including call center verification. Aligned with EU and FINMA regulatory mandates for auditable liveness verification.
• Misinformation Combat Alliance (MCA India) - Deepfakes Analysis UnitcoreStrategic or Co-development Partner · 21 October 2025Integration of Aurigin.ai's audio deepfake detection engine into MCA India's Deepfakes Analysis Unit verification workflow. Enhances DAU's multi-layered approach combining automated tools, cross-validation, and expert human analysis. Provides faster and more reliable analysis with real-time detection and probabilistic scoring for scalable verification workflows.
• 1291 GroupcoreTechnology or Integration · 24 September 2025Deployment of Aurigin.ai's real-time, on-device deepfake detector across 1291 Group's worldwide workforce. Privacy-first architecture with 100% on-device processing ensuring compliance with Swiss, EU (GDPR) and global data protection laws. Works natively with Microsoft Teams, Zoom, WhatsApp, Webex without add-ons. Initial rollout covers subset of employees with expansion planned.

Scale indicators7 records

Recent moves6 records

Expansion highlights6 records

Direct peers

• Veridas: Veridas provides voice biometrics, liveness detection, and identity verification for banks and regulated enterprises — overlapping in voice liveness/anti-spoofing and a similar enterprise/government buyer profile.
• Sensity AI: Sensity AI is a deepfake detection platform covering audio and video synthetic media, serving KYC, fraud, and content authenticity use cases — directly overlapping mission and target buyers.
• Loccus.ai: Loccus.ai builds real-time audio deepfake detection for voice calls and media, targeting call centers, contact centers, and platforms — overlapping customer base, similar real-time detection emphasis, and identical technology category.
• Pindrop Security: Pindrop is a long-established voice fraud and authentication vendor offering liveness, anti-spoofing, and deepfake detection for contact centers and financial institutions — directly comparable product category, target buyer, and use case set.

Others

• ElevenLabs: ElevenLabs is the leading commercial voice synthesis platform that Aurigin explicitly retrains against — adjacent ecosystem participant rather than competitor, but shapes the threat surface Aurigin must continually address.
• Resemble AI: Resemble AI is a voice synthesis/cloning platform with an adjacent deepfake detection offering — adjacent rather than directly competitive, but comparable on the underlying voice AI technology stack and threat landscape.

Emerging players

• Phonexia: Phonexia provides speaker recognition and voice biometrics/speech analytics for security and contact center use cases — overlapping deepfake-adjacent voice technology, with regional strength in EMEA, and is cited as a partner/evaluator of Aurigin.
• ID R&D (LumenVox): ID R&D offers voice biometrics and anti-spoofing/liveness APIs integrated into contact center and authentication platforms — overlapping voice anti-spoofing capability with a developer/SDK-first delivery model.
• Aculab: Aculab provides voice biometrics and liveness/anti-spoofing APIs for contact center and telephony platforms — comparable voice anti-spoofing capability and enterprise/government customer overlap.

Broad incumbents

• Microsoft (Azure AI Speech / Nuance): Microsoft, via Nuance, is a dominant voice biometrics and call-center analytics vendor and is the largest incumbent capable of bundling native deepfake detection into Teams and Azure AI Speech — the most significant broad incumbent competitive threat.

Market position

Strengths5 records

Weaknesses5 records

Competitive moat6 records

Key risks6 records

Key highlights7 records

Customer concentration

• GitHubgithub.com/Aurigin-ai
• LinkedInlinkedin.com/company/aurigin-ai

Compliance3 records

Revenue estimate

Valuation estimate

Number of profiles

Profiles9 records

Funding overview

Funding rounds2 records

Investors

Funding detail is available on the Subscription and Enterprise plan.Contact sales →

M&A

Investments

M&A and investment is available on the Subscription and Enterprise plan.Contact sales →

Frequently asked questions about Aurigin.ai