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

# Realtime: Contexts, Flush and Cancel

> How the Plivo Text-to-Speech WebSocket handles multiple replies, partial text, flushing and barge-in.

> [!NOTE]
>
> How to stream speech for a voice agent: send text in pieces, run up to 8 replies on one socket, flush to speak now, and cancel when the caller interrupts.

## Contexts: one reply each

A **context** is one spoken reply, named by your `context_id`.

* The first `text` message with a new `context_id` opens the reply. It sets the voice and options for that reply.
* Later `text` messages with the same `context_id` add more text. Send `"finish": true` on the last one.
* One socket can hold up to **8** open contexts. Reuse the socket across turns instead of reconnecting.
* Each context ends with one `done` event that reports the billed `characters`.
* Use a new `context_id` for every reply. Reusing one on the same socket returns an `error` event (`invalid_request`, `param: context_id`).

## Sending text as your LLM writes it

Send text in pieces as it arrives. Plivo speaks each sentence as soon as it ends, and holds a sentence that hasn't ended yet. Plivo speaks the held text when the sentence ends, or when you send `flush` or `"finish": true`.

For example, `"Your order ships"` on its own produces no audio. `"Your order ships tomorrow. It will"` produces audio for the first sentence right away.

## Flush: speak what you have now

```json theme={null}
{"type": "flush", "context_id": "c1", "flush_id": "f1"}
```

Generates audio for all text sent so far in `c1`, including an unfinished sentence, without closing it. Add a `flush_id` to get a `flush_done` event when it's done.

## Cancel: handle barge-in

```json theme={null}
{"type": "cancel", "context_id": "c1"}
```

Stops generating `c1` at once. Use it when the caller interrupts. A `cancel` with no `context_id` cancels every reply on the socket. Each canceled reply still ends with a `done` event, with `reason: "cancelled"`. `characters` counts all the text the reply received, and `spoken_chars` counts the part spoken before the cancel.

## Audio frames

Audio comes as binary frames tagged with their context:

```text theme={null}
[2 bytes: length of context_id, little-endian][context_id bytes][audio bytes]
```

Strip the header and route the audio to the right reply.

## Related

* [Realtime API reference](https://plivo.com/docs/models/text-to-speech/api/realtime.md)
