---
title: "Check a translated video (meaning, punchline, pronunciation)"
method: POST
path: "/v1/video/review"
tags: ["Translation"]
---

# Check a translated video (meaning, punchline, pronunciation)

`POST /v1/video/review`

## Request

- Base URL: `https://apihub.co.il`
- URL: `https://apihub.co.il/v1/video/review`
- Auth: HTTP bearer

A native editor's check of any translated or dubbed video, the same one every /v1/video/translate runs by itself: Gemini 3.1 Pro watches the original and the translation and reports wrong meaning, a punchline that no longer works, wrong names or numbers, unnatural or word-for-word wording, mispronounced words and a robotic voice — each with its time and a fix — scores 1–10, a verdict (passed / warnings / failed) and a corrected script written so a voice cannot misread it. Send `source_sentences` to get the script back one line per sentence of the original, ready to re-voice and place where each sentence was said (/skills/full-translate-fix.md). Videos up to 5 minutes; the answer comes in the same request (≈ 30–90 s — send x-wait-ms: 110000).

**Billing:** The model's own cost of the call (two videos watched), at our usual markup — typically 10–30 credits. A review that fails is not charged. · **Rate limit:** 10/min

## Headers

- `Idempotency-Key` string
- `X-Tag` string

## Request body

- object
  - `original_url` string, uri, required: The original video, in the language it was recorded in (public https link — upload it first if needed)
  - `subtitles_url` string, uri: The translation's subtitle file (SRT), if you have one — the review then reads it as well as listening
  - `translated_url` string, uri, required: The translated or dubbed video to check (e.g. versions[].url of /v1/video/translate, or a /v1/video/lipsync result)
  - `review_language` 'he' | 'en' | 'ru' | 'uk': The language of the notes and the summary
  - `source_language` string: The original's language (code, e.g. he)
  - `target_language` string, required: The translation's language (code, e.g. ru)
  - `source_sentences` string[]: The original's sentences in order (GET /v1/speech/transcripts/{id}/sentences): the corrected script then has exactly one line per sentence, ready to re-voice and place where each sentence was said

## Response `200`

Completed

- 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`
  - `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

- `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)