Skip to main content
POST

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

Transcription job created successfully

​
id
string

Unique transcription job ID

​
status
enum<string>

Current status of the transcription job

Available options:
queued,
preprocessing,
processing,
completed,
error
​
vault_id
string

Vault ID (only for vault-based transcription)

​
source_object_id
string

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

​
input_object_id
string

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