Platform · Voice AI

Voice AI that stays the price you quoted.

ElevenLabs voice synthesis. Ten LLMs to choose from at build time. Telephony passed through at the carrier rate. Every minute is $0.086 to $0.140 all-in — locked the moment you ship the agent, and the caller can't move it.

See pricing & book a call → Compare to GoHighLevel →
What's in the box

Built for production. Not a demo.

01

Voice on ElevenLabs

Premium TTS tuned for sub-second turn-taking and clean barge-in. Your callers don't realize they're talking to an agent until they want to.

02

Pick your LLM

Ten models across three tiers — Gemini Flash at $0.006/min for high-volume routing, Claude Sonnet 4.6 at $0.060/min for hard cases. You pick once; the rate locks.

03

Pass-through telephony

$0.010/min at the carrier rate, no markup. Bring your own SIP trunk if you prefer. Inbound and outbound covered.

04

Knowledge base & tools

Ground every answer in your KB. Fire HighLevel actions (book the calendar, update the contact, trigger the workflow). Hand off to a human when the agent should.

05

Built-in barge-in

The agent yields when the caller interrupts and picks up coherently. Awkward "talk-over" silences are the #1 reason agents feel cheap.

06

Per-call observability

Every call is logged with transcript, audio, latency, tool calls fired, and effective per-minute cost. Audit the bill against the call.

The pricing model

$0.105/min default. Three line items. No surprises.

Voice AISTT + TTS + voice orchestration
$0.070/min
LLM (you pick)Flat per-minute by model, $0.006 to $0.060
$0.025/minHaiku 4.5 default
TelephonyPass-through carrier rate, no markup
$0.010/min
All-in (default Haiku config)
$0.105 / min
Range across the LLM menu: $0.086 (Gemini Flash) — $0.140 (Sonnet 4.6)

Full breakdown of the three Callibre service tiers — Operator (Tech-only), Coached Operator (Done With You), CEO Path (Done For You) — is on the pricing page. The per-minute math above flows through every tier.

Voice AI · FAQ

Straight answers.

What voice engine does Callibre use?
ElevenLabs. We tune for sub-second turn-taking and clean barge-in behavior on the voice path. The voice engine cost is included in the flat $0.07/min Voice AI line.
How does Callibre's voice AI pricing differ from GoHighLevel's?
Callibre is flat per-minute by design — pick your LLM at build time, lock the rate. GoHighLevel meters the LLM by tokens at call time, so a heavier caller or a bigger knowledge base moves the per-minute cost up. On the same agent and same model, we have measured GHL invoices move 51% in seven minutes. The full receipts are on our comparison page.
Which LLMs are available?
Ten models across three tiers, all flat per-minute. Budget: Gemini Flash 2.5 ($0.006), Llama 4 ($0.015). Balanced: Claude Haiku 4.5 ($0.025, default), Qwen3 ($0.030). Premium: GPT-5.2 / GPT-5.1 / GPT-5 ($0.040), GPT-4.1 ($0.045), GPT-4o ($0.050), Claude Sonnet 4.6 ($0.060). BYOK (bring your own key) drops the LLM line to $0 on the Callibre invoice.
How is telephony billed?
$0.010 per minute, passed through at the carrier rate with no markup. Same vendors anyone in this space uses. You can also bring your own SIP trunk and pay the carrier directly.
What kind of voice agents can be built?
Inbound qualification, outbound follow-up, appointment booking, lead recovery, customer support routing — any voice workflow you can describe in a prompt plus a set of tools. Agents can read from your knowledge base, fire HighLevel actions (book a calendar slot, update a contact field, trigger a workflow), and hand off to a human cleanly.

Pick the LLM. Quote the client. Keep the margin.

Founding-cohort rates are open. Lock today's pricing on an annual plan and we absorb every upstream change for the life of your subscription.

See pricing & book a call →