Subtitles

Subtitles from a video/audio URL (SRT / VTT)

One call: a public media URL in, a ready subtitle file out (subtitles holds the SRT/VTT text). Word-exact timing, 99 languages including Hebrew. Asynchronous — wait with x-wait-ms or poll the execution. The transcript stays available under transcript_id.

Billing: Per second of audio, by the model used (Pro or Universal-2; the estimate prices it) + selected add-ons. Failed transcripts are not charged. · Rate limit: 30/min · Asynchronous

post/v1/speech/subtitles

Request

  • Base URL: https://apihub.co.il
  • URL: https://apihub.co.il/v1/speech/subtitles
  • Auth: HTTP bearer

Headers

Idempotency-Keystring

Replay-safe: the same execution is returned instead of charging twice

X-Tagstring

Group calls into one job (e.g. one video) — see GET /v1/usage?tag=…

x-wait-msinteger

Wait for the job inside this call (ms)

Request body

format'srt' | 'vtt'
promptstring

Free-text context for universal-3-5-pro · add-on

audio_urlstring uri required

Public URL of the audio or video file (mp3, wav, m4a, mp4, mov, webm…)

punctuateboolean
redact_piiboolean

Remove personal data (names, phone numbers…) from the text · add-on

format_textboolean

Casing and number formatting

audio_end_atinteger

Stop at this millisecond

disfluenciesboolean

Keep filler words (um, uh)

language_codestring

Language of the audio, e.g. he, en, ar, ru. Omit for automatic detection.

speech_modelsstring[]

Models in order of preference. Default: universal-3-5-pro, falling back to universal-2 for languages Pro does not support (e.g. Hebrew). Billed by the model actually used.

content_safetyboolean

Sensitive-content labels · add-on

iab_categoriesboolean

Topic detection · add-on

speaker_labelsboolean

Who said what (speaker diarization) · add-on

auto_highlightsboolean

Key phrases · add-on

keyterms_promptstring[]

Names and terms to recognise correctly (brands, people, jargon) · add-on

audio_start_frominteger

Start at this millisecond (only this part is billed)

entity_detectionboolean

Detect people, places, organisations… · add-on

filter_profanityboolean

Mask profanity · add-on

chars_per_captioninteger

Max characters per caption line group (default: provider default ~32)

speakers_expectedinteger
language_detectionboolean

Detect the language automatically (default when language_code is omitted)

sentiment_analysisboolean

Sentiment per sentence · add-on

redact_pii_policiesstring[]

Example request

{
  "language_code": "he"
}

Response

Completed (or 202 while processing)

idstring

Execution id — stable across internal retries; use it with GET /v1/executions/{id}

status'pending' | 'processing' | 'completed' | 'partial' | 'failed' | 'cancelled' | 'timeout'
operationstring
tagstring nullable

Your X-Tag, if sent

created_atstring date-time
completed_atstring date-time nullable
outputobject

Operation result (see each operation). While a Studio render is processing: stage (queued · transcribing · downloading · preparing · cleaning_voice · mixing_audio · rendering · finishing), phase (the engine's: download · prepare · voice · audio · encode · qa · upload, or null), progress (a percent, 0–100) and progress_fraction (0–1), eta_seconds (seconds left, never below 0) and estimate_seconds

errorstring nullable

Changes

No recorded changes to this operation across all 2 revisions of this API.