Create transcription job

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

Vault-based (recommended): Pass vault_id and object_id to transcribe audio from your vault. The transcript will automatically be saved back to the vault when complete.

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

POST /voice/transcription

cURL

cURL

curl -X POST "https://api.case.dev/voice/transcription" \ -H "Authorization: Bearer $CASEDEV_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "vault_id": "<string>", "object_id": "<string>", "format": "json" }'

200

{
  "id": "tr_abc123def456",
  "status": "processing",
  "vault_id": "vault_xyz789",
  "source_object_id": "obj_audio_123"
}

Authorizations

Authorization · string · header · required

API key starting with sk_case_

Body

application/json

Transcription job configuration

vault_id · string

Vault ID containing the audio file (use with object_id)

object_id · string

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

format · enum<string> · default: json

Output format for the transcript when using vault mode

Available options: json, text

audio_url · string

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

language_code · string

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

speaker_labels · boolean · default: false

Enable speaker identification and labeling

speakers_expected · integer

Expected number of speakers (improves accuracy when known)

auto_highlights · boolean · default: false

Automatically extract key phrases and topics

content_safety · boolean · default: false

Enable content moderation and safety labeling

language_detection · boolean · default: false

Enable automatic language detection

speech_models · string[]

Priority-ordered speech models to use

punctuate · boolean · default: true

Add punctuation to the transcript

format_text · boolean · default: true

Format text with proper capitalization

word_boost · string[]

Custom vocabulary words to boost (e.g., legal terms)

boost_param · enum<string>

How much to boost custom vocabulary

Available options: low, default, high

Response

200

application/json

Transcription job created successfully

id · string

Unique transcription job ID

status · enum<string>

Current status of the transcription job

Available options: queued, processing, completed, error

vault_id · string

Vault ID (only for vault-based transcription)

source_object_id · string

Source audio object ID (only for vault-based transcription)