CAcasemark
Voice

Create transcription job

Changed on

Creates an asynchronous transcription job for audio or video files. Supports two modes:

Vault-based (recommended): Pass vault_id and object_id to transcribe media from your vault. Large videos are converted to an internal MP3 derivative before transcription while the original video remains the transcript source. The transcript is automatically saved back to the vault when complete.

Direct URL (legacy): Pass audio_url for direct transcription without automatic storage.

post/voice/transcription

Request

  • Base URL
    https://api.case.dev
  • URL
    https://api.case.dev/voice/transcription
  • Auth
    HTTP bearer

Request body

vault_idstring

Vault ID containing the audio file (use with object_id)

object_idstring

Object ID of the audio file in the vault (use with vault_id)

format'json' | 'text'

Output format for the transcript when using vault mode

audio_urlstring

URL of the audio file to transcribe (legacy mode, no auto-storage)

language_codestring

Language code (e.g., 'en_us', 'es', 'fr'). If not specified, language will be auto-detected

speaker_labelsboolean

Enable speaker identification and labeling

speakers_expectedinteger

Expected number of speakers (improves accuracy when known)

auto_highlightsboolean

Automatically extract key phrases and topics

content_safetyboolean

Enable content moderation and safety labeling

language_detectionboolean

Enable automatic language detection

speech_modelsstring[]

Priority-ordered speech models to use

punctuateboolean

Add punctuation to the transcript

format_textboolean

Format text with proper capitalization

disfluenciesboolean

Preserve filler words such as um and uh in English transcription

keyterms_promptstring[]

Domain-specific words or phrases (max 6 words each) to improve recognition accuracy. Up to 1000 on universal-3-5-pro, 200 on universal-2.

word_booststring[]

Legacy alias for keyterms_prompt. Entries are merged into keyterms_prompt before submission.

boost_param'low' | 'default' | 'high'

Deprecated and ignored: current AssemblyAI models do not support boost strength.

Response

Transcription job created successfully

idstring

Unique transcription job ID

status'queued' | 'preprocessing' | 'processing' | 'completed' | 'error'

Current status of the transcription job

vault_idstring

Vault ID (only for vault-based transcription)

source_object_idstring

Original source media object ID (only for vault-based transcription)

input_object_idstring

Object submitted to the speech provider. For large videos, this is an internal audio derivative.

Changes

  • 9a3245c00044Revision changes
    • info

      added the new optional request property

    • info

      request property deprecated

    • info

      request property deprecated

  • a21d188f4b21Revision changes
    • warning

      added the new preprocessing enum value to the response property for the response status

    • info

      added the new optional request property

    • info

      the request property default value changed from universal-3-pro universal-2 to universal-3-5-pro

    • info

      added the non-success response with the status

    • info

      added the optional property to the response with the status