Skip to main content
🎉 API version '2024-10-01' just released with many new features. If you are still on an older version, check the migration guide.

Generate a note asynchronously

POST 

/generate-note-async

Creates an asynchronous task (also called asynchronous request) that will generate a structured clinical note given the transcript, then keeps the response for a short period to be fetched using the poll endpoint.

Request​

Body

required
    note_locale note_locale (string)required

    Possible values: [ENGLISH_US, ENGLISH_UK, FRENCH_FR]

    Locale of the note.

    transcript_items object[]required

    The transcript from which to generate the note.

    You don't need to specify each item's start or end time, but make sure they are sorted. In fact, due to its asynchronous nature, our real-time transcription API does not guarantee its results order. Thus, before calling this note-generation API please filter-out non-final items and sort them by start_offset_ms.

  • Array [
  • text stringrequired

    The transcribed text.

    speaker_type core_api_speaker (string)required

    Possible values: [DOCTOR, PATIENT, UNSPECIFIED]

    Who said the text in this transcript item.

  • ]
  • note_template core_api_note_template (string)

    Possible values: [GENERIC_MULTIPLE_SECTIONS, GENERIC_MULTIPLE_SECTIONS_AP_MERGED, GENERIC_SOAP, CARDIOLOGY_MULTIPLE_SECTIONS, PSYCHIATRY_MULTIPLE_SECTIONS, DIET_MULTIPLE_SECTIONS, PSYCHOLOGY_MULTIPLE_SECTIONS, WCC_MULTIPLE_SECTIONS, WCC_SOAP, EMERGENCY_MULTIPLE_SECTIONS, EMERGENCY_SOAP]

    The desired template of the generated note.

    Some templates are only available in specific languages. Check Note template for details.

    note_sections_customization object[]

    Advanced per-section customization options for the chosen template.

    You should only specify sections that belong to the given template, and only specify customization options that are supported for the given section. Also, only specify sections you want to customize, no need to be exhaustive.

    Check Note templates sections for compatibility matrix.

  • Array [
  • section_key core_api_note_section_key (string)required

    Possible values: [ALLERGIES, APPOINTMENTS, ASSESSMENT, ASSESSMENT_AND_PLAN, CARDIOVASCULAR_RISK_FACTORS, CHIEF_COMPLAINT, CURRENT_MEDICATIONS, FOOD_HABITS, LIFESTYLE, PAST_MEDICAL_HISTORY, OBJECTIVES_AND_ADVICE, FAMILY_HISTORY, HISTORY_OF_PRESENT_ILLNESS, IMAGING_RESULTS, IMMUNIZATIONS, LAB_RESULTS, MENTAL_HEALTH_EXAM, MENTAL_HEALTH_HISTORY, PAST_MEDICAL_HISTORY, PAST_OBSTETRIC_HISTORY, PAST_SURGICAL_HISTORY, PHYSICAL_EXAM, PLAN, PRESCRIPTION, HISTORY_OF_PRESENT_COMPLAINT, OBJECTIVE, SUBJECTIVE, SOCIAL_HISTORY, VITALS, WELL_CHILD_CARE]

    Key of the note section this customization should apply to.

    style copilot_note_section_customization_section_style (string)

    Possible values: [AUTO, PARAGRAPH, BULLET_POINTS]

    Specifies the desired style for the note section:

    • PARAGRAPH: Prioritizes generating paragraphs;

    • BULLET_POINTS: Prioritizes structuring content using bullet points.

    • AUTO: Automatically picks the most natural formatting option.

    Default is AUTO.

    level_of_detail copilot_note_section_customization_level_of_detail (string)

    Possible values: [DEFAULT, DETAILED]

    Specifies the desired level of details. Use detailed to get more details in the note section.

    split_by_problem boolean

    Flag to structure the content of the note sections according to distinct clinical problems or topics addressed during the consultation.

  • ]
  • previous_note object

    Optional initial Note to be enhanced using the new transcript_items. This is useful if you generate notes gradually to avoid accumulating a very long transcript items list. Typically, this will be the last note Nabla generated for you along with the new transcript_items that did not serve for its generation. Important: This is expected to be a recent (up to few-hours old) Nabla-generated note. If the note is too old or altered, you might get an error.

    title string

    Title of the note.

    sections object[]required

    Sections of the note.

  • Array [
  • key core_api_note_section_key (string)required

    Possible values: [ALLERGIES, APPOINTMENTS, ASSESSMENT, ASSESSMENT_AND_PLAN, CARDIOVASCULAR_RISK_FACTORS, CHIEF_COMPLAINT, CURRENT_MEDICATIONS, FOOD_HABITS, LIFESTYLE, PAST_MEDICAL_HISTORY, OBJECTIVES_AND_ADVICE, FAMILY_HISTORY, HISTORY_OF_PRESENT_ILLNESS, IMAGING_RESULTS, IMMUNIZATIONS, LAB_RESULTS, MENTAL_HEALTH_EXAM, MENTAL_HEALTH_HISTORY, PAST_MEDICAL_HISTORY, PAST_OBSTETRIC_HISTORY, PAST_SURGICAL_HISTORY, PHYSICAL_EXAM, PLAN, PRESCRIPTION, HISTORY_OF_PRESENT_COMPLAINT, OBJECTIVE, SUBJECTIVE, SOCIAL_HISTORY, VITALS, WELL_CHILD_CARE]

    A key identifying a section of a note. The set of possible keys depend on the template that is used. Check Note template for possible values.

    title stringrequired

    The section title.

    text stringrequired

    Content of the note section.

  • ]
  • patient_context string

    Possible values: <= 700 characters

    Some contextual information that will be used to generate the note (for example name, gender, age, pronouns, medical history) [BETA].

    client_request_id copilot_client_request_id (string)

    Possible values: <= 128 characters

    An optional unique client-made id for this request. When specified, this id is included in the Json payload that will be sent asynchronously. This can help clients both guarantee idempotency and correlate asynchronous responses with their requests.

    Note: this id must be different for every request. It is recommended to use a randomly generated UUID.

Responses​

Request received and processing started.

Schema
    oneOf
    id uuidrequired

    The id of the asynchronous request.

    client_request_id copilot_client_request_id (string)

    Possible values: <= 128 characters

    An optional unique client-made id for this request. When specified, this id is included in the Json payload that will be sent asynchronously. This can help clients both guarantee idempotency and correlate asynchronous responses with their requests.

    Note: this id must be different for every request. It is recommended to use a randomly generated UUID.

    status async_request_status (string)required

    Possible values: [ONGOING, FAILED, SUCCEEDED]

Loading...