---
title: "Transcribe audio or video"
method: POST
path: "/v1/speech/transcripts"
tags: ["Transcripts"]
---

# Transcribe audio or video

`POST /v1/speech/transcripts`

## Request

- Base URL: `https://apihub.co.il`
- URL: `https://apihub.co.il/v1/speech/transcripts`
- Auth: HTTP bearer

Speech to text with word-level timestamps, automatic language detection, speaker labels and optional audio intelligence. Asynchronous — wait with `x-wait-ms` or poll the execution; the result includes `text`, `words` (start/end in ms) and `utterances` when speaker labels are on.

**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**

## Headers

- `Idempotency-Key` string
- `X-Tag` string
- `x-wait-ms` integer

## Request body

- object
  - `prompt` string: Free-text context for universal-3-5-pro · add-on
  - `audio_url` string, uri, required: Public URL of the audio or video file (mp3, wav, m4a, mp4, mov, webm…)
  - `punctuate` boolean
  - `redact_pii` boolean: Remove personal data (names, phone numbers…) from the text · add-on
  - `format_text` boolean: Casing and number formatting
  - `audio_end_at` integer: Stop at this millisecond
  - `disfluencies` boolean: Keep filler words (um, uh)
  - `language_code` string: Language of the audio, e.g. `he`, `en`, `ar`, `ru`. Omit for automatic detection.
  - `speech_models` string[]: 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_safety` boolean: Sensitive-content labels · add-on
  - `iab_categories` boolean: Topic detection · add-on
  - `speaker_labels` boolean: Who said what (speaker diarization) · add-on
  - `auto_highlights` boolean: Key phrases · add-on
  - `custom_spelling` object[]
    - `to` string
    - `from` string[]
  - `keyterms_prompt` string[]: Names and terms to recognise correctly (brands, people, jargon) · add-on
  - `audio_start_from` integer: Start at this millisecond (only this part is billed)
  - `entity_detection` boolean: Detect people, places, organisations… · add-on
  - `filter_profanity` boolean: Mask profanity · add-on
  - `speakers_expected` integer
  - `language_detection` boolean: Detect the language automatically (default when language_code is omitted)
  - `sentiment_analysis` boolean: Sentiment per sentence · add-on
  - `redact_pii_policies` string[]

## Response `200`

Completed (or 202 while processing)

- object
  - `id` string: Execution id — stable across internal retries; use it with GET /v1/executions/{id}
  - `status` 'pending' | 'processing' | 'completed' | 'partial' | 'failed' | 'cancelled' | 'timeout'
  - `operation` string
  - `tag` string, nullable: Your X-Tag, if sent
  - `created_at` string, date-time
  - `completed_at` string, date-time, nullable
  - `output` object: 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`
    - `text` string, nullable
    - `words` object[], nullable
      - `end` integer: ms
      - `text` string
      - `start` integer: ms
      - `speaker` string, nullable
      - `confidence` number
    - `status` string
    - `language_code` string, nullable
    - `transcript_id` string
    - `duration_seconds` number, nullable
  - `error` string, nullable
  - `usage` object
    - `credits_charged` number, nullable
    - `credits_reserved` number
    - `estimated_credits` number
    - `cost_source` 'provider_reported' | 'calculated' | 'estimated' | 'null', nullable
    - `provider_usage` object, nullable: Normalised consumption, e.g. { VIDEO_SECOND: 22.4 }
  - `balance` object
    - `available` number
    - `reserved` number

## Other responses

- `202`: Processing — poll GET /v1/executions/{id}
- `400`: Invalid input
- `402`: Insufficient credits / project budget
- `404`: Resource not found (or not yours)
- `429`: Rate limited
- `503`: Service temporarily paused

---

[API](https://skmtc.dev/apihub/apis/apihub-one-api-for-chat-image-video-ai.md) · [All operations](https://skmtc.dev/apihub/apis/apihub-one-api-for-chat-image-video-ai/llms.txt) · [OpenAPI document](https://skmtc.dev/apihub/apis/apihub-one-api-for-chat-image-video-ai/revisions/a8caa42835ce?raw)