Voice MCP
Call your Pact CRM on a phone number and get spoken answers — a signature-validated Twilio webhook routes each utterance through a turn-based voice agent into curated CRM intents.
Voice MCP lets a caller phone your workspace and talk to your CRM out loud. Ask about a deal, log a note, book a meeting, or get a pipeline read — and hear the answer back in a synthesized voice.
How a call works
A caller dials the tenant's provisioned Twilio number. Twilio posts to Pact's /v1/voice-mcp/incoming webhook, and Pact validates the Twilio request signature before processing anything. Pact then answers with turn-based speech gathering: it plays a prompt, listens for the caller's next utterance, and routes that utterance through an in-process voice agent. Each turn repeats the cycle.
Caller dials number
→ Twilio posts to /v1/voice-mcp/incoming (signature validated)
→ Pact answers, gathers speech for one turn
→ Voice agent routes the utterance to a CRM intent
→ Pact speaks the reply, gathers the next turn
Turn-based, not live audio
Voice MCP is built on Twilio's turn-based speech gathering (<Gather input="speech">), which uses
Twilio's native speech-to-text. It is not a live media stream — Pact does not process a
continuous audio feed of the call. Every feature here is framed around that turn-by-turn model.
What the agent understands
The phone agent recognizes a curated set of about a dozen CRM intents plus introspection — not Pact's full MCP tool catalog. Covered intents include:
- Querying deals, accounts, and contacts
- Pipeline health
- Logging a note on the call or on a specific record
- Sending a follow-up SMS or email
- Booking a meeting
- Transferring the call
When an utterance doesn't match a specific intent, the agent falls back to ask_workspace, a catch-all that answers open questions against your workspace. It also answers meta questions about itself — what it can do, recent history, who handles what, and knowledge-base lookups.
Explore Voice MCP
The intent router, clarifying questions, and confirm-then-commit actions.
Voice tiersStandard, Pro, and Premium text-to-speech with BYOK and fail-safe fallback.
Recording consentThe 13-state two-party consent gate that fails closed.
AuthenticationCaller authentication with a PIN for unknown callers.
Proactive & transferOutbound briefing calls and warm transfer into a conference.
Memory & personalizationDurable per-caller memory and known-caller greetings.
Cost controlsThe per-tenant daily voice budget gate.
MCP SDKsPact's broader Model Context Protocol surface for developers.