Listen — From audio file

POST 
/listen

Generate a transcript and a structured clinical note from an audio file. Only audio/* mime types are supported. The maximum duration is 10 minutes. If you have longer files, please use the asynchronous equivalent.

Request

multipart/form-data

Body

required

request_parameters objectrequired

The object containing all the information needed along with the audio file to transcribe and generate a note.

output_objects listen_output_object[]required

Possible values: [transcript_item, note]

Specifies which items you want us to send you back. In other words, which feature(s) you want to use, transcription and/or note generation.

language copilot_languagerequired

Possible values: [fr, en, en-US, en-GB, fr-FR, es-ES, es-MX]

Language spoken in the audio ('fr' and 'en' are deprecated, and correspond to 'fr-FR' and 'en-US' respectively).

split_by_sentence booleanrequired

Default value: false

Indicates whether to segment transcription results at sentence boundaries. Default is false, meaning that a single transcript item may encompass multiple sentences, provided they are not delineated by pauses (silence) in the audio.

note_generation_mode copilot_note_generation_mode

Possible values: [highest_quality, fastest]

Choose a generation mode:

• highest_quality: generates very high quality notes, might take up to one minute;

• fastest: quicker note generation (few seconds), but might not give the best possible output.

Default is highest_quality.

section_style copilot_section_style

Possible values: [auto, paragraphs, bullet_points]

Choose a desired style for note sections:

• paragraphs: Prioritizes generating paragraphs;

• bullet_points: Prioritizes structuring content using bullet points.

• auto: Automatically picks the most natural formatting option.

Default is auto.

note_template copilot_note_template

Possible values: [GENERAL_MEDICINE, CARDIOLOGY, PSYCHIATRY, DIET, PSYCHOLOGY, SOAP]

The desired template of the generated note. Default is GENERAL_MEDICINE. Check Note template for details.

file binaryrequired

Responses

200

Results of processing the audio file.

application/json

Schema

Schema

transcript object[]
Transcript items from the audio file.
Array [
text stringrequired
The transcribed text.
speaker copilot_speakerrequired
Possible values: [doctor, patient, unspecified]
Who said the text in this transcript item.
start_offset_ms integerrequired
Start time of this transcription item as the offset, in milliseconds, from the start of the audio file.
end_offset_ms integerrequired
End time of this transcription item as the offset, in milliseconds, from the start of the audio file. Equals the start_time_ms plus the duration of the related transcribed audio portion.
]
note object
The generated note.
sections object[]required
Content of the note structured in multiple sections.
Array [
key stringrequired
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.
]

Example (from schema)

{
  "transcript": [
    {
      "text": "Also, I’m allergic to peanuts.",
      "speaker": "doctor",
      "start_offset_ms": 65100,
      "end_offset_ms": 69300
    }
  ],
  "note": [
    {
      "key": "CHIEF_COMPLAINT",
      "title": "Chief complaint",
      "text": "Fatigue and headaches"
    },
    {
      "key": "SYMPTOMS",
      "title": "Symptoms",
      "text": "- Tiredness all day long\n- Mild headaches on the right side"
    }
  ]
}

Loading...