Skip to main content
POST
Transcribe task

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Headers

Idempotency-Key
string | null

Body

application/json
source_url
string<uri>
required
Required string length: 1 - 2083
metadata
Metadata · object

Arbitrary key-value pairs echoed back in all webhook payloads.

Example:
webhook_url
string<uri> | null

Per-request webhook URL. Overrides workspace-level webhooks for this job only. Receives task.completed, task.failed, and progress events.

Required string length: 1 - 2083
Example:

"https://app.example.com/hooks/framelane"

language
string | null

BCP-47 language code (e.g. 'en'). Auto-detected when omitted.

speech_model
enum<string>
default:universal-2

AssemblyAI speech model to use.

Available options:
universal-2,
universal-3-pro,
nano
word_timings
boolean
default:true

Include word-level timestamps in the output.

speaker_labels
boolean
default:false

Enable speaker diarisation (who spoke when).

speakers_expected
integer | null

Hint for the expected number of speakers (used when speaker_labels=true).

Required range: 1 <= x <= 10
sentiment_analysis
boolean
default:false

Detect positive / neutral / negative sentiment per sentence.

entity_detection
boolean
default:false

Identify named entities (people, organisations, places, etc.).

auto_highlights
boolean
default:false

Extract the most important phrases automatically.

content_safety
boolean
default:false

Flag sensitive content categories.

iab_categories
boolean
default:false

Classify content into IAB taxonomy topics.

word_boost
string[]

Domain-specific terms to boost recognition accuracy (max 200).

Response

Idempotent replay.

A render job or AI task.

id
string
required

Unique job ID. Prefix indicates type: render_ or task_.

Example:

"render_01J8QR2K5VKDGN2T4FBM3CZYX7"

kind
enum<string>
required

Whether this is a render or a task.

Available options:
render,
task
Example:

"render"

workspace_id
string
required

ID of the workspace that owns this job.

Example:

"ws_01J8QR2K5VKDGN2T4FBM3CZYX8"

status
enum<string>
required

Current lifecycle state: queuedprocessingcompleted / failed / cancelled.

Available options:
ingesting,
queued,
processing,
completed,
failed,
cancelled
Example:

"queued"

created_at
string<date-time>
required

ISO-8601 UTC timestamp when the job was created.

updated_at
string<date-time>
required

ISO-8601 UTC timestamp of the last status change.

is_preview
boolean
default:false

True for a cheap preview render. Previews are not billed and are excluded from the renders list.

Example:

false

task_type
enum<string> | null

For task jobs only — the specific AI operation.

Available options:
transcribe
Example:

"transcribe"

progress_percent
integer
default:0

0–100 progress indicator updated by the render engine.

Required range: 0 <= x <= 100
Example:

0

progress_stage
enum<string> | null

Current processing phase within a job.

Available options:
downloading,
compositing,
encoding,
uploading
Example:

"compositing"

output
JobOutput · object | null

Populated once status == completed. Contains the signed artifact URL.

result
Result · object | null

Structured JSON result for tasks that return data rather than a file — transcribe returns the transcript here (text, words, utterances, and any requested analysis). Populated once status == completed; null for renders and for any job whose only artifact is the file at output.url.

Example:
error
JobError · object | null

Populated when status == failed. Contains a structured error code.

metadata
Metadata · object

Caller-supplied key-value pairs echoed back on every webhook and response.

Example:
completed_at
string<date-time> | null

ISO-8601 UTC timestamp when the job reached a terminal state.