# Phone and voice in Connect

Connect answers your business number and places calls on it, on either of two engines: a turn-based carrier path that hears a sentence and reads a reply back, or a realtime speech-to-speech path where Connect holds the call itself. Both write the same `calls` record, obey the same autonomy and budget gates, and are configured from the Phone screen.

- **Status:** Available
- **Audience:** both
- **Channels:** phone
- **In the app:** #/calls, #/phone-advanced
- **Last verified:** 2026-09-10
- **Canonical:** https://connectbyjbrh.com/docs/phone/

## What the phone channel actually is

Phone is a channel like email or WhatsApp: a number the business owns, a set of rules about who may be called and when, and a record of every conversation that a person and the engine can both read afterwards. What makes it different is that the conversation happens in real time, so decisions that email can defer — whether to answer, in what language, how long to wait before speaking — have to be made while somebody is holding a phone to their ear.

Three layers carry that. `voice_carriers.py` is the adapter and the only place a provider's own vocabulary appears — its signature scheme, its XML dialect, its webhook shape. `telephony.py` is the core: what a line is, what an event means, who may be called when. Everything above that — `voice.py`, the consoles, the Phone screen — names no provider at all, and a test asserts it rather than trusting it. Anything that needs to know whether recording or transfer exists asks `telephony.can(provider, capability)`; branching on a provider's name is how a system ends up unable to remove that provider.

## Two engines

|  | Turn-based (carrier) | Realtime |
|---|---|---|
| How it hears | The carrier transcribes a sentence and posts it to a webhook | A realtime model listens to the audio stream directly |
| How it speaks | Connect returns instructions the carrier reads out | The model speaks; the greeting is synthesised during the ring |
| Interruption | Not possible — a turn is a whole sentence | The caller can speak over the voice and be heard |
| Where it runs | `voice.py` and the carrier adapter | `voice_engine.py` plus the `connect-voice` worker on LiveKit |
| Turned on by | The default path for a line | Setting `voice.engine = "realtime"` on the workspace |

The engines are not two products. They write the same `calls` row, run the same end-of-call work — summary, lead, memory, follow-up — and pass outbound calls through the same gate, so consent, memory blocks, autonomy and budget apply identically. Choosing between them is a choice about how the conversation feels, not about what Connect is allowed to do.

## What a workspace sets up

1. A number, claimed by the workspace as a line. See [Your business number in Connect](/docs/phone/business-number/).
2. Permissions and hours on that line, which decide whether it takes calls in, places them out, and when.
3. An autonomy mode for the `voice` channel, which decides what Connect may do on a call without asking a person.
4. A voice and a behaviour, tuned in the Voice Lab and resolved per line, per purpose or per contact.
5. A budget, because a live call is billed on audio tokens and a call that cannot be paid for is refused before it is answered.

> **Note** The Phone screen is the same screen for both audiences. The Owner reaches it directly and a customer reaches it through the tenant facade, but it is one implementation — there is no reduced customer view of the phone channel.

## Where the rest of this section is

**Getting a call in** — [How a call reaches your workspace](/docs/phone/carrier-routing/), [Carrier callback verification](/docs/phone/carrier-verification/) and [Answering inbound calls](/docs/phone/inbound-calls/).
**Getting a call out** — [Placing outbound calls](/docs/phone/outbound-calls/) and, when nobody should be rung, [Business hours and the closed line](/docs/phone/business-hours/).
**What is written down** — [The call record](/docs/phone/call-record/), [Call transcripts](/docs/phone/transcript/), [Call summaries](/docs/phone/call-summary/) and [Call outcomes and dispositions](/docs/phone/call-outcome/).
**How the voice behaves** — [The greeting](/docs/phone/greeting/), [Barge-in](/docs/phone/barge-in/), [Turn detection and end of speech](/docs/phone/turn-detection/) and [Reply latency on a call](/docs/phone/latency/).
**Running it** — [The voice worker](/docs/phone/voice-worker/), [Capacity and admission control](/docs/phone/worker-capacity/), [Phone line health](/docs/phone/phone-health/) and [What a call costs](/docs/phone/voice-cost/).

## What phone does not do

Three things are deliberately absent, and no screen in Connect implies otherwise. Call recording is foundation: the capability is asked of the provider rather than assumed, and it is not enabled on the live carrier. A completed warm transfer to a human is foundation for the same reason — an escalation phrase queues a transfer and a colleague can act on a live call from the supervisor panel, but the handover itself depends on a provider capability that is not switched on. SMS on the live carrier does not exist at all, and the Phone screen's readiness section says so rather than showing a thread that could never send.

There is also a floor on how fast the realtime path can be. The model's first token plus its end-of-turn detection put the best measured call at a **3.3 s median reply**, not the one to two seconds a demonstration video might suggest. Settings move that number; no setting removes it.

## Everything in this section

57 pages, each with its own status and the date it was last checked against the running system.

| Page | What it covers |
|---|---|
| [A returning caller](/docs/phone/returning-caller/) | The second time somebody rings: what Connect has already, how little of it reaches the conversation, and why continuity is not the same as recital. |
| [Abandoned calls](/docs/phone/abandonment/) | Calls the caller walked away from: how the hang-up watcher recognises real abandonment, what it records, and why no closing line is spoken. |
| [Answering inbound calls](/docs/phone/inbound-calls/) | From ring to greeting to first reply: the gates a caller passes, what they hear at each refusal, and what is written down while they talk. |
| [Barge-in](/docs/phone/barge-in/) | Speaking over the voice on a live call: what stops it, the two-second rule that decides an interruption was ignored, and why the greeting is protected. |
| [Business hours and the closed line](/docs/phone/business-hours/) | How opening hours are set on a line, what a caller hears outside them, and why the closed-line message never speaks the hours aloud. |
| [Call outcomes and dispositions](/docs/phone/call-outcome/) | The engine's outcome and a person's disposition are two columns answering two questions. What each one says, and how to use them together. |
| [Call quality review](/docs/phone/voice-lab-review/) | What a finished call is scored on: deterministic findings with the setting each one points at, the model's opinion kept separate, and limits that do not lower the score. |
| [Call summaries](/docs/phone/call-summary/) | When a call summary is written, the two conditions under which Connect refuses to write one, and what a summary is allowed to contain. |
| [Call transcripts](/docs/phone/transcript/) | How a call transcript is assembled turn by turn, what the latency beside a reply actually measures, and the three things a transcript is not. |
| [Calling from the browser](/docs/phone/softphone/) | The browser line: a per-person SIP endpoint, why every state the dialler shows comes from a SIP event, and how a browser call actually makes a phone ring. |
| [Calls that were never a conversation](/docs/phone/not-a-conversation/) | no_answer, not_reached and silent failure are three different nothings. What each one means, how to tell them apart, and why none creates a lead. |
| [Capacity and admission control](/docs/phone/worker-capacity/) | How admission decides a call can be taken: load per core, the 0.85 threshold, why a silent worker reads as free, and what saturation does to a caller. |
| [Carrier callback verification](/docs/phone/carrier-verification/) | Why every carrier callback is signature-checked inside the owning workspace, what a replayed webhook looks like, and the index that stops one. |
| [Configuring a phone line](/docs/phone/line-configuration/) | The ten facts that make up a phone line, what each one refuses when it is set wrongly, and the order to decide them in. |
| [Connect's own voice](/docs/phone/connect-voice-tts/) | Why the words a caller hears are synthesised by Connect rather than the carrier, how a sentence becomes a cached MP3, and the rule that forbids silence. |
| [Consent on calls](/docs/phone/call-consent/) | Where consent for a phone call is decided, the single outbound path every call passes through, and why a block recorded elsewhere already applies to the phone. |
| [Detecting the caller's language](/docs/phone/language-detection/) | What counts as proof a caller has changed language: four tiers with four different bars, the transcript artefacts that never count, and what pinning overrides. |
| [Executing phone follow-ups](/docs/phone/phone-followup-drain/) | The drain that places a due call-back, the gates each one passes, the retry when no voice worker is ready, and the point at which a late follow-up is abandoned. |
| [Facts learned on a call](/docs/phone/call-facts/) | What a phone call leaves behind in Memory, which extracted facts are refused outright, and how something heard on a call reaches a conversation on another channel. |
| [Follow-ups from a call](/docs/phone/call-follow-up/) | How a spoken commitment on a call becomes a dated follow-up: the words that parse into a time, the channel it lands on, and the default when nothing parses. |
| [Greeting warm-up](/docs/phone/greeting-prewarm/) | How Connect has the first sentence of a call already synthesised before the phone is picked up, and the quota refusal that once cost every restart its warm greeting. |
| [How a call reaches your workspace](/docs/phone/carrier-routing/) | How a dialled number becomes a workspace, why every handler enters that workspace before reading a setting, and what an unclaimed number does. |
| [Human voice profiles](/docs/phone/human-voice-profiles/) | One choice that yields a whole person: 86 parameters across identity, speech, imperfections and psychology, and the ones marked unsupported rather than faked. |
| [Identifying the caller](/docs/phone/caller-identity/) | Turning the number that rang into a person: the phone key, the rule when two records share a number, and what happens when nobody gives a name. |
| [Leads captured from a call](/docs/phone/lead-from-call/) | When a phone call creates a Person and a lead, the two call endings that deliberately create nothing, and the key the record carries from the very first ring. |
| [Light code-mixing and slang](/docs/phone/code-mixing/) | Hinglish and light slang on a call: when a mixed sentence counts as evidence and when it does not, and what asking a model for a register achieves. |
| [Multilingual calling](/docs/phone/multilingual-calls/) | Calls held in more than one language: how the opening choice is made, what may change part-way through, and what a mixed sentence does. |
| [Names heard on a call](/docs/phone/names-on-calls/) | What happens to a name spoken on a call: the protected markers, why a form of address never becomes one, and every door it must pass on the way in and out. |
| [Phone for the Owner and for a customer](/docs/phone/phone-owner-tenant/) | What the phone channel does identically for the operator and for a customer workspace, what a plan changes, and the small set of things that stay operator-only. |
| [Phone line health](/docs/phone/phone-health/) | The four things line health reports about a phone line, what each one means for somebody ringing the number, and why none of them has to be cleared by hand. |
| [Placing outbound calls](/docs/phone/outbound-calls/) | The five gates an outbound call passes before a number is dialled, what each refusal means, and how a call-back gets placed at all. |
| [Promises made on a call](/docs/phone/promise-integrity/) | The rule that refuses a follow-up time the caller never said, what counts as agreeing to one, when a read-back is asked, and the finding for an empty promise. |
| [Regional speaking style](/docs/phone/regional-speech/) | The regional speaking-style layer: the prompt directions it adds, the things it cannot touch, and why a rendered cadence rule was removed rather than kept. |
| [Remembering a caller's language](/docs/phone/known-language/) | A caller's remembered speaking preference: where it is held, why Connect speaks it from the first reply, what overrides it, and what it costs in the brief. |
| [Reply latency on a call](/docs/phone/latency/) | How long a caller waits for a reply: what the clock measures, where the floor comes from, and how to tell a slow reply from a slow model. |
| [Session limits and long calls](/docs/phone/session-limits/) | The model's session cap, the context window, the provider cap and the product's own thirty-minute ceiling — which one ends a long call, and what a caller notices. |
| [Silence and check-ins](/docs/phone/silence/) | What Connect does when nobody is speaking: how presence is tracked, why nothing is said over a caller, and what a silent stretch leaves on the record. |
| [Steering a live call](/docs/phone/supervisor/) | The panel a colleague uses to steer a call in progress: why guidance never reaches the caller, and why pause, take over and release are read back out of the log. |
| [Stuck calls and the sweep](/docs/phone/stuck-calls/) | Call rows left active by a worker that died or a browser call with no worker behind it, the sweep that closes them against the provider cap, and what it charges. |
| [Switching the line off](/docs/phone/line-off/) | What switching a phone line off does to a caller, to the call record and to work already scheduled on that line — and why it is not silence. |
| [Telling the voice how to speak](/docs/phone/speaking-guide/) | The style block and the behaviour block: which settings become session parameters, which become instructions a model may only approximate, and which are neither. |
| [The budget that stops a call](/docs/phone/voice-budget/) | The budget question asked before an outbound call and before answering an inbound one, what a refused caller hears, and how the quota breaker differs from it. |
| [The call brief](/docs/phone/call-context/) | Everything assembled before a call starts: persona, purpose, contact facts, knowledge, rules and guidance — each with a character budget, and why the budgets exist. |
| [The call record](/docs/phone/call-record/) | Every field on a call: ring and answer times, provider status, cost, participants, quality, and why outcome and disposition are separate columns. |
| [The carrier turn-based engine](/docs/phone/turn-based-engine/) | The carrier webhook path — gather, reply, redirect — when it is the right engine for a line, and the three things it cannot do. |
| [The greeting](/docs/phone/greeting/) | How the first sentence of a call is chosen, why it is synthesised while the phone is still ringing, and what happens when it cannot be spoken. |
| [The realtime voice engine](/docs/phone/realtime-engine/) | The speech-to-speech calling path: how a workspace turns it on, what the worker is given for each call, and what it is never allowed to know. |
| [The response watchdog](/docs/phone/response-watchdog/) | The timer that asks a stalled model to answer: why its default is 5.5 seconds, what disarms it, and how a nudge can cancel the very reply it was waiting for. |
| [The Voice Lab](/docs/phone/voice-lab/) | The screen where a line's voice is tuned: engine settings that take effect exactly, steering text the model interprets, drafts and test calls. |
| [The voice worker](/docs/phone/voice-worker/) | The process that holds a realtime call: how it starts, what it heartbeats, how a deploy drains it, and what a caller gets when none is running. |
| [Transfer and escalation](/docs/phone/live-transfer/) | What an escalation phrase queues on a live call, why the transfer capability is asked of the provider rather than assumed, and what the live carrier does not carry. |
| [Turn detection and end of speech](/docs/phone/turn-detection/) | Deciding that the caller has finished speaking: the model's own detection, the host semantic path with dynamic endpointing, and how to choose between them. |
| [Voice profiles](/docs/phone/voice-profile/) | Named bundles of voice settings: where one can be attached, the six-step resolution order that decides which wins, and what is recorded on the call. |
| [What a call costs](/docs/phone/voice-cost/) | Why a voice call is metered by modality rather than by a total token count, the reporting field that never existed, and what a call reporting no tokens is charged. |
| [What a setting cannot change](/docs/phone/model-limits/) | Findings the call review counts but does not score, why they come with no control to turn, and the two behaviours proven unreachable by prompting. |
| [Who ended the call](/docs/phone/hangup-attribution/) | The six values of hangup_by, why every non-caller ending once read as 'agent', and how to tell an ended call from a dropped one. |
| [Your business number in Connect](/docs/phone/business-number/) | What a phone number becomes once a workspace claims it: a channel_routes line that carries the provider, the permissions, the hours and the routing. |

## Questions

### Do I have to choose an engine before I can use the phone channel?

No. A line works on the turn-based carrier path without any extra configuration. The realtime engine is something a workspace opts into by setting `voice.engine = "realtime"`, and it needs the number linked at the carrier to an inbound trunk, which is console work at the provider rather than a switch in Connect.

### If a call goes wrong, where do I look first?

Put the carrier's own call log next to the `calls` list for the same period. A call the carrier records as completed with no matching row in Connect is a bug every time, and it narrows the problem to routing or verification rather than to the conversation.

### Is the phone channel the same for the Owner and for a customer?

Yes. One implementation serves both, with the customer session reaching it through the tenant facade. The only asymmetry is commercial: a customer's usage is bounded by their plan's allowances.

## Related

- [Your business number in Connect](https://connectbyjbrh.com/docs/phone/business-number/)
- [Answering inbound calls](https://connectbyjbrh.com/docs/phone/inbound-calls/)
- [The realtime voice engine](https://connectbyjbrh.com/docs/phone/realtime-engine/)
- [The call record](https://connectbyjbrh.com/docs/phone/call-record/)
- [WhatsApp in Connect](https://connectbyjbrh.com/docs/whatsapp/)
- [What Connect may do](https://connectbyjbrh.com/docs/autonomy/)

## What this page is based on

- AGENTS.md §9a — the phone system (via docs-source/sources/PHONE.md)
- `backend/app/telephony.py` — the provider-independent core
- `backend/app/voice_carriers.py` — the carrier adapter
- Connect capability registry (docs-source/facts.py)