Video Transcript is a universal video-to-text API for automation. Submit one supported public URL or an audio/video upload up to 8 GB; receive detected-language text, ordered timestamped segments, source metadata, and optional translation into 133 languages. Transcript pricing begins at $0.3483.
At a glance
| Store brand | AgentX — apify.com/agentx |
|---|---|
| Pricing model | pay per event |
| Price per result row | $0.39 on the Free plan |
| 1,000 rows (Free plan) | $387.00 |
| 1,000 rows (Gold plan) | $348.30 |
| Default / max memory | 8192 MB / 16384 MB |
| Run timeout | 1 h |
| Public runs, last 30 days | 212 · 95.3% succeeded |
| Users | 36 in 30 days · 833 all time |
| First published | August 5, 2025 |
| Last build | 1.0.23 on August 25, 2026 |
What you have to give it
None of the 3 input fields are required — every one has a default.
| Field | Type | Required | Accepted values | What it does |
|---|---|---|---|---|
video_url | string | no | https://www.youtube.com/watch?v=jNQXAC9IVRw | Paste a public video URL to download and transcribe. Leave this empty when you only want to upload a file |
video_file | string | no | — | Upload a video/audio file up to 8 GB or provide a direct file URL. If both Video File and Video URL are provided, this file is used |
translate | string | no | afrikaans, albanian, amharic … | Optional target language for translating the transcript. Leave empty to return only the original transcript |
A run that works
The values below are the Actor's own prefills, so this input is valid as written:
{
"video_url": "https://www.youtube.com/watch?v=jNQXAC9IVRw"
}What comes back
Every dataset row carries the 22 fields below. The examples are the ones declared in the Actor's own output schema.
| Field | Type | Example | Meaning |
|---|---|---|---|
platform | string | null | Youtube | Source platform name |
title | string | null | How to Build an AI Agent in 10 Minutes | Original title of the video |
description | string | null | In this tutorial we explore how to build AI agents using the latest tools and frameworks. | Video description |
author | string | null | TechChannel | Video creator or uploader username/name |
author_id | string | null | UCexampleChannelId123 | Author's channel or user ID |
author_url | string | null | https://www.youtube.com/@TechChannel | URL to the author's channel or profile page |
duration | number | null | 623 | Video duration in seconds |
audio_title | string | null | Original Sound | Track name if the video contains music |
audio_artist | string | null | TechChannel | Artist name if the video contains music |
view_count | integer | null | 152000 | Number of views on the video |
like_count | integer | null | 8500 | Number of likes on the video |
shares_count | integer | null | 120 | Number of shares/reposts |
dislike_count | integer | null | 45 | Number of dislikes on the video |
comment_count | integer | null | 340 | Number of comments on the video |
categories | array | null | Education, Technology | Video categories |
tags | array | null | AI, machine learning, tutorial | Video tags |
published_at | string | null | 2024-03-15T14:22:00+00:00 | ISO formatted timestamp when the video was published |
thumbnail | string | null | https://i.ytimg.com/vi/uZ_BMwB647A/maxresdefault.jpg | Video thumbnail image URL |
transcript | object | null | {"language":"English","text":"Hello and welcome to this tutorial.","segments":[{ | AI-generated transcript with speech recognition and timestamped subtitles in original language |
translation | object | null | {"language":"Spanish","text":"Hola y bienvenido a este tutorial.","segments":[{" | AI-translated transcript with timestamped subtitles in the target language. Segments the translator could not return keep their source text, and untranslated_segments counts them, so the segment list always aligns with the transcript. |
processor | string | null | https://apify.com/agentx/video-transcript | URL of the Apify actor that processed this data |
processed_at | string | null | 2025-01-15T10:30:00.000Z | ISO 8601 formatted timestamp (UTC) when the data was processed |
What it costs
| Charged event | Price | When |
|---|---|---|
| Transcript | $0.39 – $0.35 | One timestamped transcript in the default dataset. |
| Actor Usage | $0.00001 | Charged for Actor runtime, proxy and storage. Cost depends on resource consumption during execution |
| Translation | $0.15 – $0.14 | One complete segment-aligned translation in the default dataset when requested. |
| Actor Start | $0.001 | Charged when the Actor starts running. Number of events charged depends on Actor memory (one event per GB, minimum one event). |
Per 1,000 rows, by Apify plan
| Plan | Per row | 1,000 rows | 10,000 rows |
|---|---|---|---|
| Free | $0.39 | $387.00 | $3870.00 |
| Bronze | $0.37 | $374.10 | $3741.00 |
| Silver | $0.36 | $361.20 | $3612.00 |
| Gold | $0.35 | $348.30 | $3483.00 |
| Platinum | $0.35 | $348.30 | $3483.00 |
| Diamond | $0.35 | $348.30 | $3483.00 |
Every total includes the $0.001 start fee once. Apify charges that fee per gigabyte of memory, so a 8192 MB run pays it a single time.
When not to use it
- The dataset carries 22 fields and nothing else; if your analysis needs a field that is not in the table above, no input setting will add it.
- It reads what is public at run time. There is no archive behind it, so a question about last quarter has to be answered from data you already collected.
Closest Actors in the catalog
Same categories, ordered by how many people run them. Compare the field tables before choosing.
| Actor | Brand | Fields | 1k rows (Free) | Users / 30 d |
|---|---|---|---|---|
| YouTube Transcript | AgentX | 22 | $387.00 | 27 |
| Bilibili Transcript ↗ | AgentX | 22 | $387.00 | 1 |
| 𝕏 (twitter) Transcript ↗ | AgentX | 22 | $288.00 | 1 |
| Dailymotion Transcript ↗ | AgentX | 22 | $351.00 | 1 |
| Rutube Transcript ↗ | AgentX | 22 | $351.00 | 1 |
| Facebook Transcript ↗ | AgentX | 22 | $351.00 | 0 |
Field guides that use this data
- Transcribing Podcasts and Recordings You Already Host — Most transcript APIs want a platform link. When the audio is your own — a podcast, a recorded call, an archive in S3 — you need the direct-file path instead.
- Instagram Reel Transcript API: From Public URL to Text — Turn a public Instagram reel into timestamped text with one API call: what you get back, what qualifies as input, and how translation into 133 languages works.
- Video Transcript API Guide: From Public URL to Searchable Knowledge — A production guide to video transcription workflows: source validation, language, timestamps, speaker limits, exports, quality checks, and AgentX Actor selection.
Prove it on a narrow run
Open the live contract.
Pricing, availability and schema can change between snapshots. The Apify Actor page is the current source of truth.
Catalog snapshot 2026-09-04; Actor contract, pricing and run statistics read 2026-09-04.