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

# Send app message

> Use this action to send app messages as part of Tavus's interaction protocol. [Learn more in Tavus documentation](https://docs.tavus.io/sections/conversational-video-interface/live-interactions).

### Fields

| **Field**           | **Type** | **Description**                                                                                                                                                                                |
| ------------------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **message type**    | String   | Indicates the product this event is associated with. For this use case, the `message_type` will be set to `conversation`.                                                                      |
| **conversation id** | String   | The unique identifier for the conversation.                                                                                                                                                    |
| **event type**      | String   | Specifies the type of event being sent. This field is included in all events and helps distinguish between different event types.                                                              |
| **modality**        | String   | Indicates the input type for this event. Possible values: `audio`, `text`.                                                                                                                     |
| **text**            | String   | If `modality` is set to `text`, this field contains the text that the replica will speak out loud.                                                                                             |
| **audio**           | String   | If `modality` is set to `audio`, this field contains the base64-encoded audio that the replica will speak out loud. The encoded audio must be in 16-bit PCM 16000 format.                      |
| **inference id**    | String   | A unique identifier for a given utterance. Multiple messages with the same `inference_id` indicate they belong to the same utterance.                                                          |
| **done**            | Boolean  | Indicates if all audio chunks for an utterance have been sent. If `done` is not set to `True`, audio chunks will continue to stream until a final event with `done` set to `True` is received. |
| **context**         | String   | Specifies the new conversational context that will be used by the LLM (Language Model).                                                                                                        |

### Returned Values

This action does not return any fields.

<CardGroup cols={2}>
  <Card title="Need Help?" icon="envelope" href="/support/plans">
    View our options for free community and priority support.
  </Card>

  <Card title="Have a feature request?" icon="lightbulb" href="https://lunchpaillabs.canny.io/feature-requests?selectedCategory=bubble-video-audio-live">
    Post your feature request on our

    <a href="https://lunchpaillabs.canny.io/feature-requests?selectedCategory=bubble-video-audio-live">
      idea board.
    </a>
  </Card>
</CardGroup>