> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bland.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Speech

> Control how readily your agent pauses for callers and how quickly it responds after they stop talking.

Two settings control how your agent shares the conversation:

* **Interruptibility** governs what happens while the agent is speaking: how readily it yields when the caller talks over it.
* **Resumption speed** governs what happens after the caller finishes: how quickly the agent takes its turn.

They are independent, and both are optional. An agent with neither set uses the balanced defaults described below.

## Agent pauses

When a caller makes a sound while the agent is speaking, the agent does not cut off at the first sound. It keeps talking for a brief moment while it works out what the caller is doing, then reacts:

| The caller says                            | What it is             | What the agent does                                                      |
| :----------------------------------------- | :--------------------- | :----------------------------------------------------------------------- |
| "Uh-huh."                                  | A short acknowledgment | Keeps talking. No pause at all.                                          |
| "Stop for a second."                       | A short interruption   | Finishes its current word, stops, and responds.                          |
| "Wow, that is really, really interesting." | A long acknowledgment  | Pauses while the caller speaks, then picks up exactly where it left off. |
| "Hey, I have a question about that."       | A long interruption    | Finishes its current word, stops, and responds.                          |

Two things hold in every case:

* The agent always stops at a word boundary. It never cuts off mid-word.
* Acknowledgments never derail the agent. Short ones are spoken through; long ones get a pause, and the agent picks up where it stopped.

What counts as a "short" utterance scales with the interruptibility setting: an easy-to-interrupt agent pauses for shorter caller utterances, while a difficult-to-interrupt agent holds through more.

## Interruptibility

How readily the agent yields the floor when the caller speaks over it. Set with the `interruptibility` field (integer, `0`-`4`, default `2`).

| Setting             | API value | Caller experience                                                                                                       |
| :------------------ | :-------- | :---------------------------------------------------------------------------------------------------------------------- |
| Always interrupt    | `4`       | Any caller speech stops the agent. Nothing is treated as an acknowledgment; every utterance gets a stop and a response. |
| Easy                | `3`       | Yields quickly. Only the briefest acknowledgments are spoken through.                                                   |
| Balanced            | `2`       | Default. Short acknowledgments do not stop the agent; real interruptions do.                                            |
| Difficult           | `1`       | Holds the turn longer and treats more caller speech as acknowledgment. Good for noisy lines and chatty listeners.       |
| Block interruptions | `0`       | The agent ignores caller speech entirely while talking and always finishes what it is saying.                           |

## Resumption speed

How quickly the agent responds once the caller stops talking. Set with the `resumption_speed` field (integer, `1`-`3`, default `2`).

| Setting | API value | Caller experience                                                                                                                                          |
| :------ | :-------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Fast    | `1`       | Responds almost as soon as the caller stops. Snappy, suited to quick transactional exchanges. May jump in when a caller pauses mid-thought.                |
| Medium  | `2`       | Default. Balanced for most conversations.                                                                                                                  |
| Slow    | `3`       | Leaves a deliberate beat before responding. Suited to callers who pause to think mid-answer: the agent does not take a thinking pause as its cue to speak. |

<Note>
  `resumption_speed` supersedes the older `interruption_threshold` field. When both are set, `resumption_speed` wins. Prefer `resumption_speed` for new configurations; `interruption_threshold` remains accepted for backward compatibility.
</Note>

## Where to set them

* **Send Call API**: pass `interruptibility` and `resumption_speed` in the [`/v1/calls`](/api-v1/post/calls) request body. They apply to the whole call.
* **Inbound numbers**: the same fields on your inbound number configuration.
* **Pathways**: per node, in the node inspector under Advanced options.

<Warning>
  A node's setting stays in force for the rest of the call, not just that node, unless a later node changes it. If the agent misbehaves at a node with no setting of its own, check the nodes before it.
</Warning>

## Choosing values

| Symptom                                                       | Try                                                |
| :------------------------------------------------------------ | :------------------------------------------------- |
| The agent takes too long to respond                           | Fast resumption                                    |
| The agent jumps in while callers are still thinking           | Slow resumption                                    |
| The agent talks over callers who want to say something        | Easy interruptibility, or Always interrupt         |
| The agent stops for background noise or brief acknowledgments | Difficult interruptibility, or Block interruptions |

The two combine. A common "let the caller drive" setup is Easy interruptibility with Slow resumption; a common "get through the script" setup is Difficult interruptibility with Fast resumption.