Skip to main content

Changelog

Keeping track of changes​

All changes are documented here. The following sections are not necessarily API version codes, most changes come without a new API version unless it is necessary for backward compatibility.

January 31, 2025​

  • Dictate Websocket must now be used with new protocol "dictate-protocol". (Previous protocol "copilot-dictate-protocol" remains supported for backward compatibility).
  • The new protocol includes the following changes compared to previous one, with the aim of following the same conventions as transcription Websocket:
    • New screaming snake case frame types:
      • dictate_config -> CONFIG
      • audio_chunk -> AUDIO_CHUNK
      • end -> END
      • dictation_item -> DICTATION_ITEM
      • error_message -> ERROR_MESSAGE
    • More conventional configuration options:
      • Audio encoding enum with capital letters (pcm_s16le -> PCM_S16LE)
      • Specify minimum value of 8000 and maximum value of 192000 for sample_rate
      • Rename locale property locale to speech_locale and add support for 35 values including various languages with regional dialects.

January 23, 2025​

  • Add four new templates: GENERIC_SOAP_AP_MERGED, PSYCHIATRY_SOAP, GENERIC_APSO_AP_MERGED, GENERIC_SOAP_PLUS_EXAM_TESTS_AP_MERGED.

January 7, 2025​

  • New 2025-01-07 API version.
  • All API endpoints must now be accessed with a regionalized URL (us.api.nabla.com or eu.api.nabla.com). The default api.nabla.com is no longer supported. The usage of region specific host ensures optimal API response time.

December 23, 2024​

  • New 2024-12-23 API version.
  • All API endpoints must now be accessed through the new "core/server" or "core/user" paths.

December 3, 2024​

November 22, 2024​

  • Add custom_instruction customization option to note generation endpoints.

November 18, 2024​

November 13, 2024​

November 8, 2024​

  • New 2024-11-08 API version.
  • Fixed case for server-to-client frames in Transcribe Websocket. It is now SCREAMING_SNAKE_CASE for all the frames, e.g. transcript_item becomes TRANSCRIPT_ITEM.

November 7, 2024​

October 1, 2024​

June 12, 2024​

  • Feedback Report endpoint now takes an expected_output field, so you can pass a structured version of what you expected the endpoint to give as output.

June 3, 2024​

  • /generate_normalized_data endpoints now also return vitals, along with their LOINC codes, in the observations array.

May 25, 2024​

May 16, 2024​

May 13, 2024​

  • Add a new endpoint to fetch a user with a unique external ID from another system.

May 6, 2024​

  • Add a content_auto_update_enabled property on dot phrases in create, read and update user dot-phrases endpoints to automatically adapt dot-phrase replacement text to the context of the encounter.

May 2, 2024​

April 23, 2024​

April 18, 2024​

  • Add new endpoints to manage Dot Phrases for a user.
  • Suggest user's matching Dot Phrases alongside the generated note in the Digest endpoint.

April 11, 2024​

  • Add four new templates: GENERAL_MEDICINE_WCC, SOAP_WCC, GENERAL_MEDICINE_EMERGENCY, SOAP_EMERGENCY.

April 3, 2024​

March 27, 2024​

  • Add a patient_context property in digest and digest_async requests body

March 25, 2024​

February 27, 2024​

  • New API version: 2024-02-27.
  • Remove note generation feature from Listen Websocket API (no more usage of this deprecated feature).

January 31, 2024​

  • Add new endpoints to fetch a single user or all users using filters and pagination.
  • Add split_by_problem to digest & listen-from-file endpoints.

January 24, 2024​

  • Deprecate note generation feature in Listen Websocket API (recommend using the dedicated endpoint).

January 17, 2024​

  • Add new endpoints: activate-user & deactivate user.

December 1, 2023​

  • Deprecate [es-ES, es-MX] as note generation languages in Core API for digest and listen endpoints.

November 14, 2023​

  • Add optional client_request_id parameter to /digest and /digest_async endpoints.