Question 1

How long does NexTalk take to set up?

Accepted Answer

Under 2 minutes for a basic live chat. Sign up, create your first widget, copy a single

Question 2

Do I need a credit card to start the free trial?

Accepted Answer

No. The 14-day free trial unlocks every Pro feature without a credit card. We only ask for payment when you choose a paid plan after the trial. You can also stay on the Free plan indefinitely with 1 agent, 1 widget, and 100 chats per month.

Question 3

What kind of website does NexTalk work on?

Accepted Answer

Any website that lets you add a <script> tag — WordPress, Webflow, Wix, Shopify, custom React or Vue apps, static HTML, Next.js, Astro. The widget mounts inside a Shadow DOM with z-index 2147483647, so it never conflicts with your existing CSS or other tools.

Question 4

Can I migrate from Intercom, Drift, Tidio, Crisp, or Zendesk?

Accepted Answer

Yes. The widget replacement is one line of code. Conversation history import is on the Pro and Enterprise roadmaps — for now, most teams run both in parallel for a week and switch when comfortable. See our dedicated /intercom-alternative, /drift-alternative, /tidio-alternative, and /crisp-alternative pages for step-by-step playbooks.

Question 5

Which AI models does NexTalk support?

Accepted Answer

Anthropic Claude (Sonnet, Haiku, Opus), OpenAI GPT-4o and GPT-4o-mini, Google Gemini 2.0 Flash/Pro, Meta Llama 3 (via OpenRouter), and Alibaba Qwen. Add any new model via OpenRouter in seconds. You pick which model handles which widget — switch in seconds, no contract.

Question 6

How does BYOK (Bring Your Own Key) work?

Accepted Answer

You paste your Anthropic, OpenAI, Google, or OpenRouter API key into the AI Agent settings. NexTalk encrypts it with AES-256 at rest (per-tenant encryption key) and decrypts it only inside the AI worker process for each LLM request. The key never leaves the server, is never returned to the dashboard, and is never logged. You pay the LLM vendor directly at their cost — NexTalk does not mark up tokens or charge per resolution.

Question 7

What's the difference between BYOK and platforms like Intercom Fin?

Accepted Answer

Intercom Fin charges you per AI resolution on top of seat pricing. So a spike in traffic = a spike in bill. With BYOK, you pay the model vendor for tokens (typically $0.0001–$0.01 per chat for Claude Haiku or GPT-4o-mini) — predictable, transparent, and you keep the rate negotiated by your own enterprise account if you have one.

Question 8

Can I use different AI models for different widgets?

Accepted Answer

Yes — and we encourage it. Run Claude Sonnet on your B2B sales page (high reasoning), GPT-4o-mini on your docs (cheap and fast), Llama 3 on internal helpdesk (private), Gemini Flash on volume FAQ widgets. Each widget has its own model, prompt, schedule, and persona.

Question 9

Can I write custom system prompts?

Accepted Answer

Yes. Every AI agent has its own system prompt — full control over tone, scope, knowledge boundaries, escalation triggers, and brand voice. Test prompts in the built-in playground before going live.

Question 10

What happens when the AI doesn't know the answer?

Accepted Answer

Configure escalation rules: keyword triggers (like 'speak to human', 'refund'), explicit fallback intents, or sentiment thresholds. The AI hands the conversation to your human queue with full chat history attached — your agent picks up in context, never asking the visitor to repeat themselves.

Question 11

How much does NexTalk cost?

Accepted Answer

Free ($0, 1 agent, 1 widget, 100 chats/mo), Starter ($9.99/mo, 3 agents, 2 widgets, 1,000 chats/mo), Pro ($19.99/mo flat, 10 agents, 5 widgets, 10,000 chats/mo, full AI), Enterprise (custom — unlimited agents, widgets, SSO, SLA, dedicated support). See /pricing for the full breakdown.

Question 12

Is the $19.99 per agent or for the whole team?

Accepted Answer

$19.99/month covers your whole Pro workspace — up to 10 agents, 5 widgets, 10,000 chats. Not per-seat. Compare to Intercom which charges $39–139 per seat: a 10-agent team on Intercom = $390–1,390/month for similar functionality.

Question 13

Are there per-resolution fees for the AI?

Accepted Answer

Zero. NexTalk does not charge per AI conversation, per resolution, per token, or any usage-based surcharge. You pay your LLM provider (Anthropic, OpenAI, Google, OpenRouter) directly at their published rates for tokens consumed.

Question 14

How does billing work?

Accepted Answer

We use Stripe. Monthly or annual billing. Upgrades and downgrades are prorated. Cancel anytime — your data remains accessible read-only for 30 days after cancellation, then is fully deleted per GDPR.

Question 15

Do you offer discounts for non-profits, startups, or open source?

Accepted Answer

Yes — contact sales (/contact). We offer 50% off for verified non-profits, free Pro for solo open-source maintainers, and startup pricing through accelerator partners.

Question 16

Can I have multiple widgets on different sites?

Accepted Answer

Yes — that's a flagship feature. Free includes 1 widget, Starter 2, Pro 5, Enterprise unlimited. Each widget has its own branding, AI agent, schedule, language, domain restriction, and analytics. One workspace runs your marketing site, your docs, your customer portal, and your e-commerce store — all separately.

Question 17

How customizable is the widget appearance?

Accepted Answer

Brand colors, greeting text, agent avatar and name, welcome card content, chat bubble position (bottom-left or bottom-right), corner radius, font preference, and CSS overrides for advanced users (Enterprise). Match your brand exactly without writing code.

Question 18

Can I restrict a widget to specific domains?

Accepted Answer

Yes. Each widget supports a whitelist of allowed domains. Embeds from any other origin are silently rejected — protects against widget theft and unauthorized use on competitor sites.

Question 19

Does the widget work on mobile?

Accepted Answer

Yes, fully responsive. Adapts to iPhone Safari, Android Chrome, and in-app browsers. The chat opens as a bottom sheet on small screens instead of a floating window.

Question 20

Does the widget slow down my website?

Accepted Answer

No. The widget loader is ~6 KB gzipped and loads asynchronously after page paint. The full widget bundle (~80 KB gzipped) only loads when the visitor opens the chat. No render-blocking, no Core Web Vitals impact.

Question 21

Can NexTalk integrate with Slack, Discord, or Zapier?

Accepted Answer

Yes — via outgoing webhooks. Subscribe any URL to events: new_chat, new_message, conversation_closed, csat_submitted. HMAC-SHA256 signatures verify authenticity. Pre-built templates for Slack and Discord; works with Zapier, Make, n8n, Pipedream, and custom internal systems.

Question 22

Is there a REST API?

Accepted Answer

Yes, on Pro (read-only for analytics export) and full access on Enterprise. OpenAPI 3.1 spec, JWT-authenticated, rate-limited. Programmatic access to conversations, messages, agents, widgets, AI agents, and analytics.

Question 23

Do you support SSO / SAML?

Accepted Answer

Yes, on the Enterprise plan. SAML 2.0 and OIDC. SCIM provisioning available on request. We do not currently support free social sign-in (Google/Microsoft consumer SSO) for the dashboard — only enterprise IdPs.

Question 24

Can I export my data?

Accepted Answer

Yes. CSV export for conversations, messages, agents, and CSAT in the dashboard. Full JSON export via API on Enterprise. GDPR-compliant data deletion on request.

Question 25

Has NexTalk been pentested?

Accepted Answer

Yes. Independent pentest in March 2026 by a third-party security firm. Critical and high findings remediated within the disclosure window. Notable fixes: JWT moved from localStorage to HttpOnly + Secure + SameSite cookies (immune to XSS), AES-256 encryption for AI provider API keys at rest, strict CSP and security headers, tenant isolation verified across every endpoint.

Question 26

Where is my data stored?

Accepted Answer

PostgreSQL 16 hosted on Microsoft Azure (Europe region by default). Redis 7 for cache and pub/sub. Conversations, messages, agents, settings, and analytics — all encrypted in transit (TLS 1.3) and at rest (Azure-managed keys + per-tenant application-layer encryption for sensitive secrets).

Question 27

Is NexTalk GDPR-aware?

Accepted Answer

Yes. Tenant data is fully isolated. Visitor data minimization built-in (we don't track visitors across sites). Right to access and right to deletion exposed via dashboard and API. Data Processing Agreement available on the Enterprise plan.

Question 28

Is my AI provider API key safe?

Accepted Answer

Yes. Keys are encrypted with AES-256-GCM using a per-tenant data encryption key (DEK), which is itself encrypted with a key encryption key (KEK) rooted in Azure Key Vault. The plaintext key only exists in memory inside the AI worker process for the duration of each LLM call. Never logged, never returned to the dashboard.

Question 29

What happens to visitor data after a chat ends?

Accepted Answer

Conversation history is retained per your plan's retention policy (default: 1 year on Free/Starter, 2 years on Pro, configurable on Enterprise). Visitors can request deletion at any time; you can also bulk-purge in the admin dashboard.

Question 30

How many concurrent chats can NexTalk handle?

Accepted Answer

Thousands per tenant. The backend is a horizontally-scaled FastAPI cluster with a Redis pub/sub layer for cross-instance WebSocket fan-out. We run hot-standby PostgreSQL replicas and have load-tested past 10,000 concurrent WebSocket connections per node.

Question 31

What's the uptime SLA?

Accepted Answer

99.9% on Pro (best-effort), 99.95% on Enterprise (contractual with credits). Status page at status.privum.cloud. We publish post-incident write-ups for any major event.

Question 32

Can I self-host NexTalk?

Accepted Answer

On request, for Enterprise customers. The full stack ships as Helm charts for Kubernetes (we use the same charts internally — same platform that runs Privum Cloud's SRExpert product). Contact sales (/contact) for self-host pricing and support terms.

Question 33

What region are you hosted in?

Accepted Answer

Primary region is Europe (Azure West Europe / North Europe). US region available on Enterprise. Multi-region failover is on the 2026 roadmap.

Question 34

Do you have a status page?

Accepted Answer

Yes — status.privum.cloud. Covers NexTalk along with the rest of the Privum Cloud platform (SRExpert, DNS Manager, consulting infrastructure).

Answers from the team that built it.

Getting started

AI providers & BYOK

Billing & plans

Widgets & embedding

Integrations & webhooks

Security & privacy

Scaling & reliability

Talk to the team that built NexTalk.