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

# Asynchronous Ambient Documentation

> Ambient note generation from audio recording and conversational transcript

## Introduction

The **Asynchronous Ambient Documentation Workflow** is the most common "AI scribe" workflow in use today. While the [real-time ambient documentation workflow](/workflows/ambient-rt/) is designed for scenarios where immediate processing and feedback are essential during the patient visit, this workflow processes a complete audio file and within seconds returns a document generated based on the conversational transcript. In scenarios where real-time processing isn't required or feasible, the asynchronous workflow provides flexibility and predictability.

### Endpoints and Capabilities

| Endpoint     | Capability                                                                                                                                                                         | Use      |
| :----------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------- |
| Interactions | The foundational unit that ties together all related data and operations, enabling a cohesive workflow from the start of the interaction to the generation of final documentation. | Required |
| Recordings   | Upload audio files that can be used for transcript generation                                                                                                                      | Required |
| Transcripts  | Generate transcripts for audio files that are associated with the interaction                                                                                                      | Required |
| Documents    | Ambient note generation based on template and language defined in the request                                                                                                      | Required |
| Templates    | Get details for available templates that define the structure and language of generated documents                                                                                  | Optional |

## Workflow

<Card>
  ```mermaid theme={null}
        sequenceDiagram
        Client ->> Public API: POST /interactions
        Public API -->> Client: 200, interactionId, wssUrl
        Client ->> Public API: POST /interactions/:id/recording
        Public API -->> Client: 200, recordingId
        Client ->> Public API: POST /interactions/:id/transcripts
        Public API -->> Client: 200, transcript
        Client ->> Public API: POST /interactions/:id/documents
        Public API -->> Client: 200, document
  ```
</Card>

<Steps titleSize="h3">
  <Step title="Create interaction">
    1. The workflow begins with the client initiating an interaction by sending a `POST` request to the `/interactions` endpoint.
    2. The API responds with a unique `id` for the interaction and a WebSocket URL (`wssUrl`). The identifier will be used to manage the subsequent steps of the workflow.
  </Step>

  <Step title="Upload audio recording">
    3. Once the interaction is initialized, the client uploads an audio file associated with that interaction by sending a `POST` request to `/interactions/:id/recording`.
    4. The API responds with a `200` status and returns a `recordingId`, confirming that the audio file has been successfully uploaded and linked to the interaction.
  </Step>

  <Step title="Create conversational transcript">
    5. After the recording is uploaded, the client initiates the transcription process by sending a `POST` request to `/interactions/:id/transcripts`.
    6. The API processes the audio and returns a `200` status with the generated transcript. This transcript contains the text version of the recorded interaction, extracted and formatted for review.
  </Step>

  <Step title="Generate document(s)">
    7. Finally, the client creates the necessary documentation by sending a `POST` request to `/interactions/:id/documents`. This request includes the transcript generated in the previous step and a `templateKey` to specify the format of the output document.
    8. The API processes the request and returns a `200` status along with the final document, which is ready for use or further editing.
    9. Submit multiple `POST` requests to the `/documents` endpoint with different `templateKey` to generate multiple notes for a given interaction.
  </Step>
</Steps>

<Check>See details on Templates and how to use them [here](/textgen/templates/)</Check>