---
title: "Subtitles from a video/audio URL (SRT / VTT) — estimate"
method: POST
path: "/v1/speech/subtitles/estimate"
tags: ["Subtitles"]
---

# Subtitles from a video/audio URL (SRT / VTT) — estimate

`POST /v1/speech/subtitles/estimate`

## Request

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

Price the request without executing it. Same body as `POST /v1/speech/subtitles`.

## Request body

- object
  - `format` 'srt' | 'vtt'
  - `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
  - `chars_per_caption` integer: Max characters per caption line group (default: provider default ~32)
  - `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`

Estimate

- Estimate
  - `operation` string
  - `estimated_credits` number
  - `credits_to_reserve` number
  - `estimated_usage` object
  - `note` string, nullable
  - `balance` object
    - `available` number
  - `sufficient` boolean

---

[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)