Now Live

Call Stream AI 3.0.
The biggest leap in
our platform's history.

The next generation of the Call Stream AI platform, and the most significant advancement we've ever shipped. Everything you already rely on keeps working — it now runs on a dramatically faster and more capable foundation.

Before
~1.2s
Now · 3.0
~500ms
A rebuilt pipeline cuts end-to-end response time by more than half — close to real time, with natural turn-taking and smooth interruption handling. Guests stop waiting for the AI to catch up.
The 3.0 release

This isn't a new product.
It's a new generation.

Think of 3.0 the way you'd think about moving to a new generation of phone, or a new operating system. The tools you count on stay familiar. The engine underneath gets faster, smoother, and more capable.

Everything still works

Call handling, reservations, guest requests, routing, and live write-back to your PMS, POS, and CRM all carry forward unchanged.

The foundation is stronger

A rebuilt engine powers every conversation — quicker, more natural, and more controllable property by property.

It's built to keep improving

The new platform is designed for continuous innovation, so new capabilities reach your property faster than before.

01 · At a glance

What actually changed.

The headline difference is how the platform feels in a live conversation — but the upgrades run across the board.

AreaBeforeNow · 3.0
Conversation speed ~1.2 second response time Around 500 milliseconds — close to real time, with natural turn-taking
Voices Previous v2 generation All-new v3 voices built for emotion, pacing, and natural flow
Transfers Basic call hand-off Live warm transfers that carry full context to your staff
Call handling General-purpose flows Conversational pathways tuned per department
Continuity Channels tracked separately Conversational syncing across Voice, Message, Email, and Agents
Visibility Standard call reporting A Business Intelligence Command Center with ROI insight
Model layer Frontier models only Frontier plus self-hosted open-source models in the Secure Cascading LLM
Standard integrations Custom build required Weather, Time, Traffic, Directions included at no additional cost
02 · Speed

Conversations that feel present.

At about 500 milliseconds end-to-end — down from roughly 1.2 seconds — conversations feel immediate instead of mechanical, with smooth, natural interruption handling.

In hospitality that gap is the whole experience. A guest who has to wait for the system to catch up knows they're talking to a machine. At 500ms, the call simply feels like talking to a person — they interrupt, they change their mind mid-sentence, they get answered.

03 · Voice

All-new v3 voices.

Voice is the first thing a guest judges, and the new generation is a major step up. The v3 voices are designed for genuine expression rather than a flat phone-tree read — with better prosody and timing so conversations flow.

Expression

Emotion & pacing

Warmth on a welcome, calm on a complaint, brevity on a quick confirmation.

Context-aware

Adapts to the moment

Delivery shifts with where the conversation actually is, not a fixed script read.

Voice pooling

Multiple voices per agent

Rotating voices so a repeat caller never hears the identical greeting twice.

Custom

Your brand voice

Custom voices tuned to your property — preserved across every language you serve.

04 · Handling

Smarter handling, cleaner hand-offs.

Two upgrades make a real difference here.

Live warm transfersNew

The conversation transfers — not just the line

When a human should take over, Call Stream hands off the full conversation. Your front desk already knows why the guest called, what was offered, and what they actually want. Guests never have to repeat themselves.

Conversational pathwaysNew

Department-specific flows

Routing is more controlled and tuned to how your property actually operates. Reservations behave like reservations. Service recovery behaves like service recovery. Neither borrows the other's script.

Front DeskReservationsConciergeFood & BeverageSpaHousekeepingEvents & Groups
05 · Continuity

One guest. One conversation.

A guest calls to book. Two days later she texts to move her arrival. The morning of check-in she opens chat to ask about parking. That night, from abroad, she messages on WhatsApp.

Before 3.0, those were four related records your team had to reconcile. Now they're one thread — with far tighter conversational syncing across every product, so context follows the guest instead of resetting at each channel boundary.

Voice

Calls

Inbound & outbound, ~500ms, 40+ languages.

Message

SMS & WhatsApp

Two-way messaging with shared team inboxes.

Email

Managed inboxes

Triage, draft, and resolve — assist or automate.

Agents

Chat & internal AI

Guest chat out front, Teams & Slack behind.

06 · Visibility

From reporting to a command center.

Reporting tells you what happened. The new client portal is built to help you understand what to do next.

Instead of call counts, basic logs, and backward-looking snapshots you have to connect yourself, the Business Intelligence Command Center delivers real operating insight.

ROI reporting

Revenue, not volume

Reservations captured, upsells converted, and service demand met — reported as revenue influenced rather than calls handled.

Portfolio view

Outcomes across properties

Performance and outcomes rolled up across every property, so a group can compare locations on the same terms.

Insight

Actionable, not just numbers

Demand signals, sentiment shifts, and missed-revenue alerts surfaced as things to act on — not a dashboard to interpret.

100%
Answered · every channel
78%
First-contact resolution
~500ms
End-to-end latency
99.7%
Uptime SLA
07 · Intelligence & security

Faster and more secure.

3.0 adds self-hosted open-source models to our Secure Cascading LLM. Routine, high-volume conversations are handled fast by models running inside our own infrastructure, while complex requests still escalate to the right frontier model for the job.

Frontier modelsEstablished
GPTOpenAI
ClaudeAnthropic
GeminiGoogle
Self-hosted open sourceNew in 3.0
NemotronNVIDIA
LlamaMeta
— Inside our trust boundary

Conversations run on dedicated infrastructure inside our trust boundary — never routed through a third-party AI proxy. Your guest data stays yours, stays inside Call Stream AI, and is never used to train outside models.

This is the architectural point, not just a feature: Call Stream AI is a platform, not a proxy. Model selection, security, and auditability are all part of execution — which is why adding a self-hosted model layer reduces exposure rather than adding another vendor dependency. The platform remains model-flexible throughout.

SOC 2 AlignedTCPACASLGDPRCCPACall Stream Verify · SHA-256
08 · Standard integrations

Four new integrations. No extra cost.

Guests ask about conditions constantly — and until now, answering well meant a custom integration. In 3.0 these are standard on every subscription, including basic, at no additional cost.

Weather

Live conditions and forecast — for pool days, patio seating, tee times, and packing questions.

Time

Local time and time-zone awareness — so an overseas guest gets accurate hours, not confusion.

Traffic

Real-time conditions — for airport runs, dinner reservations, and realistic arrival windows.

Directions

Turn-by-turn guidance from wherever the guest is — spoken naturally, or texted to them mid-call.

These sit alongside the integrations you already run — Oracle Opera Infor HMS Maestro Agilysys HotSOS ALICE OpenTable Resy SevenRooms Book4Time Toast Stripe Slack Microsoft Teams — plus 3,000+ more via Pipedream MCP.

09 · Getting there

We handle the migration.

Moving to 3.0 doesn't put work on your team. Our implementation team manages the transition and tuning for your property.

01

We migrate your setup

Your configuration and integrations are carried onto the new platform foundation — agents, knowledge base, workflows, and write-back all intact.

02

We tune for your property

Property-specific refinements are re-applied and validated against real call flows — including voice selection and mapping your departments onto conversational pathways.

03

A short settling period

As the new engine tunes in, anything you flag gets addressed quickly. Questions during rollout go straight to your implementation team — no tickets lost, no guesswork.

04

You're on the best platform we've built

Faster conversations, new voices, richer insight — fully supported, and built for continuous release so new capabilities keep arriving.

— Fully managed, as always

Call Stream AI remains a fully managed service. There's no engineering lift on your side for 3.0 — no migration plan to own, no configuration to rebuild. Our team does the work and validates it before your property switches over.

Now live

Hear the difference.

A 30-minute walkthrough on 3.0 — the new v3 voices, the sub-500ms back-and-forth, the Command Center, and how your departments map onto conversational pathways.