SIP · SIPREC · HEP · 100% auto-hospedado

Observabilidade SIP feita para equipes de telecomunicações.

Projetado para que seus engenheiros de voz sejam mais rápidos, mais eficientes e mais efetivos. VoxyWatch ajuda equipes de voz a detectar anomalias, entender problemas SIP e acelerar a análise de incidentes através de observabilidade especializada e IA aplicada a telecomunicações.

Instale em uma linha — camada gratuita, sem cartão:
curl -fsSL https://raw.githubusercontent.com/VoxyWatch/publish/main/install.sh | sudo bash
Ver no GitHub
Detecção de anomalias por troncoIA que assiste, nunca executaVendor-agnostic, multi-SBC100% auto-hospedado

Funciona de imediato com

AsteriskKamailioFreeSWITCHAudioCodesRibbonCisco CUBEAvayaRTPEngine
The problem

Your customer detects the failure before your NOC does

The customer calls first

A trunk silently degrades ASR from 90% to 70%. Global thresholds never see it. The ticket comes from the customer, not from monitoring.

Hours per incident

Wireshark, grep on the SBC, manual captures and correlation by hand. Every incident burns hours of a senior engineer's time.

Escalating to the vendor

Without your own evidence, diagnosis ends in a ticket with the SBC vendor: days of waiting and zero control.

Zero inter-carrier visibility

Which carrier is degrading? Which destination is failing? Without per-trunk and per-country attribution, it's all opinion, not evidence.

🤖 The agentic NOC

A virtual NOC engineer that runs the incident loop end-to-end

DETECT INVESTIGATE DIAGNOSE NOTIFY ACT LEARN

Actions execute only after your approval — and the AI has no tool to change your network. By design, not by promise.

🚨

Incident engine

Every anomaly becomes a persistent incident with a lifecycle (open → acknowledged → resolved), deduplication, an auditable timeline and stability-based auto-resolve. A dedicated Incidents tab with one-click actions.

🔍

Autonomous investigator

The moment an incident opens, VoxyWatch investigates by itself: sample failing calls, dominant SIP codes, failing IP paths, and whether other trunks degraded too — the local-vs-carrier tell. With your LLM key, it writes the probable root cause citing that evidence.

📲

Telegram & email with action buttons

Critical incidents reach your phone with the diagnosis attached and inline buttons: Ack · Resolve · Investigate · plus a proposed remediation when one applies. Each portal user links their own chat with a one-time code. Every action audited by real username, gated by role.

📚

Runbooks + case memory

Ships with field runbooks the investigator follows and cites step by step — add your own as JSON. Resolved incidents become institutional memory: “same as incident #123, resolved: carrier maintenance”.

🛡️

Statistical confidence

CRITICAL must be earned: minimum sample size, measurement coverage, deviation from the trunk's own baseline, sustained degradation. Validated on production data: −92% false-critical noise.

📋

Capacity forecast & digest

Audio retention is measured, not guessed — capacity incidents open before you run out. A daily/weekly digest lands in Telegram or your webhook on schedule.

🛟 Safe remediation, with your approval

Proposed actions come from a closed, code-level catalog (restart the capture sniffer, recompute baselines — never your SBC), execute only after your tap, and land in the incident timeline with who-approved-what.

Para quem é

Projetado para as equipes que operam redes de voz reais

Operadoras, ITSPs, provedores UCaaS, integradores de voz. Vendor-agnostic, multi-SBC, auto-hospedado.

Operadoras

A visão do NOC sobre cada interconexão: ASR/NER por rota, detecção de anomalias por tronco, picos de 5xx sinalizados no momento.

ITSPs

Visibilidade por cliente, qualidade por destino, atribuição de operadora por ITU-T E.164 e áudio quando você precisa provar o que aconteceu.

Provedores UCaaS

Qualidade de voz auditável por tenant: MOS, jitter, perda, PDD. Detecte degradações antes que o cliente escale.

Integradores e MSPs de voz

Diagnostique chamadas sem escalar para o fabricante do SBC. Análise de incidentes baseada em evidências, multi-plataforma.

VoxyWatch

De um pacote SIP à ação que seu NOC precisa executar

Capture, atribua, aprenda e explique — tudo num único binário auto-hospedado.

Captura universal multi-fonte

HEP v1/v2/v3 sobre UDP e TCP de Asterisk, Kamailio, OpenSIPS, FreeSWITCH, Oracle/ACME, Ribbon, AudioCodes, Cisco CUBE — mais o voxywatch-probe incluído (Go + libpcap, amd64 e arm64) para fontes que não emitem HEP.

Inteligência de operadora e país

Carregue seus troncos uma única vez. Cada chamada é atribuída à sua operadora por IP/CIDR e ao país de destino via motor ITU-T E.164 longest-match (197 códigos). Tráfego ONNET sinalizado separadamente.

Baselines automáticas por tronco

Cada tronco aprende seu próprio normal (média ± σ por hora). Detecta drifts silenciosos que limites globais não pegam — como ASR caindo de 90% para 70% em uma única operadora.

Copiloto IA para NOC — sua própria chave

Copiloto por tronco e resumo: lê saúde + baseline + tendência 48h, retorna causa provável e a ação para o NOC. Funciona com OpenAI, Anthropic, Gemini ou OpenRouter. Nunca toca o SBC.

Agente SNMP embarcado + traps

Agente SNMP v2c/v3 integrado com mais de 30 OIDs e traps por borda para perda de captura, sniffer caído, ASR/MOS baixos, pressão de disco/CPU/RAM. MIB para download. Integra com PRTG, Zabbix, Nagios.

100% auto-hospedado, sem exceções

Um binário + PostgreSQL/TimescaleDB, provisionado pelo instalador em 60 segundos. Seu hardware, seus dados, sem nuvem, sem telemetria, sem call-home.

VoxyWatch vs.

Onde o VoxyWatch se encaixa

VoxyWatch é feito para observabilidade 24/7 do NOC. Complementa — não substitui — ferramentas como Wireshark ou projetos open source como HOMER.

VoxyWatchHOMERDashboards SBCWireshark
Auto-hospedado
Portal web
HEPv1 / v2 / v3 ~~
MOS E-model ~
Reconstrução de áudio SIPREC ~
Reprodução de áudio no navegador ~
Assistente com IA
Instalação em um binário ·
Inspeção forense de pacotes (ferramenta especializada) ·~
🔒 PCI-DSS

Built for PCI-DSS environments

When your customers dictate card numbers by phone, sensitive RTP is dropped at the source. Payment audio never leaves the secure environment, never travels the network, never reaches VoxyWatch.

Strictest scope reduction

The Probe drops RTP of a payment window at the source — the smallest possible PCI scope for your deployment.

Hot-reload via JSON

Add or remove SSRCs in pci_suppress.json — Probe applies within seconds, no restart, no service window.

Defense in depth

Pairs with portal-side suppression for a two-layer guarantee: misconfigured Probe entries are caught server-side before storage.

CRM-friendly

Your contact-center system writes the SSRC entry when the agent triggers pause. Resume removes it. No new infrastructure.

🔗 MCP server

Your voice network, exposed to your agents

VoxyWatch ships a standalone Model Context Protocol server: connect Claude Desktop, Claude Code or any MCP-compatible agent and let it query health, KPIs, trunk status, CDRs and incidents — with evidence and diagnosis — through 6 read-only tools. Authenticated with the same scoped API keys.

voxywatch-mcp.js · 6 read-only tools · scoped API keys

Your corporate AI can now interrogate your voice network.

specs

Especificações técnicas

Leve. Roda tranquilo em um servidor modesto.

Porta do portal 3080 (HTTP) · 3443 (HTTPS)
Portas HEP 9060 UDP+TCP · 9910/9911 UDP
Banco de dados SQLite 3 (modo WAL)
RAM mínima 512 MB (recomendado 2 GB)
Sistema operacional Linux (Debian / Ubuntu / RHEL)
Versões HEP 1, 2 e 3 (autodetectadas)
Codec de áudio G.711 / G.722
Formatos de exportação PCAP · WAV · CSV · JSON
use cases

Casos de uso reais

Da teoria ao diagnóstico em minutos.

01

Depurar um interconnect de carrier

Filtre por status = falha, abra qualquer chamada e o diagrama SIP mostra INVITE → 100 → 486. Causa raiz confirmada em menos de 5 minutos.

02

Auditar gravações SIPREC

Reconstrua o áudio, ouça por canal e cruze com jitter e RTCP para localizar exatamente onde o áudio do destinatário caiu.

03

Validar um SBC novo

Faça chamadas de teste e confirme que aparecem com números corretos, MOS alto e diagramas limpos antes de ir para produção.

Quem construiu

Construído por engenheiros de rede com experiência real operando redes de voz carrier-grade.

VoxyWatch não é uma plataforma genérica de observabilidade que aprendeu SIP no último trimestre. Foi projetado por quem opera redes de voz — e construído especificamente para os engenheiros que o fazem.

🔒 O preço para early adopters está bloqueado enquanto incorporamos a primeira leva de clientes.

FAQ

Frequently asked questions

The most common things buyers ask before getting started.

How do I cancel my subscription?

Open the Paddle customer portal and cancel from there in one click — link below. Your license stays active until the end of the billing period.

Open Paddle customer portal →
Do you accept bank transfer, PayPal, or Stripe?

Yes, on request. Write to contact@voxywatch.com with your preferred method and plan length, and we set it up.

Can I upgrade from Pro to Telco without losing what I already paid?

Yes. Open a support ticket and we credit the unused portion of your Pro license toward the Telco plan.

What if my server is damaged or I need to change hardware?

Open a support ticket. We re-issue your license for the new HWID. Same plan, same expiration.

Do you issue an invoice for accounting?

Yes. Open a support ticket with your billing details (legal name, tax ID, address) and we send a proper invoice for your records.

Can I be billed in MXN, EUR, or another local currency?

On request. Open a support ticket with the currency and plan length, and we coordinate it outside the default Paddle USD flow.

What happens when my license expires? Do I lose my data?

No. Your CDRs, audio recordings, and configuration stay intact on your server. Only new captures are paused until you renew.

Does VoxyWatch send any data to the cloud?

No. VoxyWatch is 100% self-hosted. No telemetry, no call-home, no data leaves your network. The only outbound calls are AI copilot requests — and those use YOUR API key, going to YOUR chosen provider.

Is there a free trial?

Yes. The Free tier (50 concurrent calls, 1,000 CDRs) is lifetime free and includes every feature. No credit card. Install in 60 seconds.

Can the AI agent change my network?

No. The AI has no tool to touch your SBC — by design, not by promise. Proposed remediations come from a closed, code-level catalog (restart the capture sniffer, recompute baselines) and execute only after a human explicitly approves, with full audit of who approved what.

How does the AI copilot handle privacy?

It is bring-your-own-key. You configure your own OpenAI, Anthropic, Gemini, or OpenRouter API key. Requests go directly from your VoxyWatch instance to your AI provider. VoxyWatch never sees the data and never proxies through our servers.

🤝 Partners

Refer a customer, earn a commission

Earn 10% to 30% of the first payment when you refer a customer to VoxyWatch. The exact percentage depends on your involvement: a simple referral starts at 10%; active sales support (introductions, technical pre-sales, demo coordination) goes up to 30%.

  1. 1

    Contact us at partners@voxywatch.com with the prospect details.

  2. 2

    We agree on the commission percentage based on the support level.

  3. 3

    When the customer pays for any plan (1 month, 6 months, 1 year, or 2 years), you receive your commission on that first payment.

  4. 4

    Payment method and minimum payout agreed by email.

Get the terms

Email partners@voxywatch.com and we send the full program terms.

Comece a ver suas chamadas hoje

Sem nuvem. Sem SaaS. Sem cartão. Implante o VoxyWatch no seu próprio servidor e tenha visibilidade SIP de nível carrier.