Video & Audio to Translated Subtitles

Turn video or audio into clean, timed subtitle files and translate them into multiple languages.

Upload a media file or provide a direct media URL. The Actor automatically detects the spoken language by default, transcribes the audio, formats readable subtitles, and optionally translates them into the selected output languages.

The result is delivered as SRT, WebVTT, TXT, and structured JSON files. This Actor creates subtitle files only; it does not render subtitles into a final video.

Machine translations are not human-reviewed. Linguistic review is recommended before professional publication.

Which Actor should I use?

• Media to translated subtitle files, without a rendered video: use this Actor.
• An existing SRT or VTT file that needs checking or correction: Professional Subtitle QC
• The complete workflow, including transcription, translation, quality control, and an optional subtitled video: Professional Subtitle Translator & Video Captioner

Each Actor covers a different stage of the subtitle workflow, so you only pay for the processing you actually need.

What this Actor does

Use this Actor to:

• transcribe audio and video into timed subtitles;
• detect the spoken language automatically;
• translate subtitles into one or more selected languages;
• preserve subtitle timing and speaker information;
• format subtitles with no overlaps and a maximum of two lines per cue;
• export original-language and translated subtitle files;
• process an uploaded file or a direct public media URL;
• retrieve individual download links from the Apify Dataset and OUTPUT record.

Common uses

• Create subtitles for interviews, podcasts, courses, and presentations
• Translate video content for international audiences
• Prepare subtitle files for Premiere Pro, DaVinci Resolve, CapCut, Final Cut Pro, or another video editor
• Generate transcripts and structured timing data for automated workflows
• Integrate transcription and translation into Make, Zapier, API, or agent workflows

Supported inputs

Video

• MP4
• MOV
• MKV
• WEBM

Audio

• MP3
• WAV
• M4A
• AAC
• OGG
• FLAC

You can use:

• a file uploaded through the Apify Console;
• a direct public HTTP or HTTPS media-file URL.

Not supported

YouTube, TikTok, Instagram, and similar webpage URLs are not direct media files and are refused. Download the media first, then upload it or provide a direct file URL.

Media without a usable audio stream cannot be transcribed.

Processing workflow

The Actor performs the following steps:

1. Downloads or receives the media file.
2. Verifies the real media format, size, duration, and audio stream.
3. Extracts the selected audio stream.
4. Transcribes it with word-level timing.
5. Formats the transcript into readable subtitle cues.
6. Translates the cues into each selected target language.
7. Exports and stores all successful files.

A translation failure for one language does not remove the original transcript or successful translations in other languages.

Language detection and translation

The source language is detected automatically by default.

Translation is optional. If no target language is selected, the Actor returns only the original-language subtitle files.

The Translate into menu provides 10 validated output languages:

• English (American) — EN-US
• Spanish — ES
• French — FR
• German — DE
• Italian — IT
• Portuguese (Brazilian) — PT-BR
• Arabic — AR
• Chinese (Simplified) — ZH-HANS
• Japanese — JA
• Korean — KO

Translated text keeps the source timing boundaries whenever possible. Longer translations can be split into additional cues inside the available source interval. If the available time is insufficient for the target reading speed, the result remains synchronized and includes a readability warning.

Subtitle formatting

The formatting engine:

• creates strictly positive cue durations;
• keeps cues in chronological order;
• prevents overlapping subtitles;
• limits subtitles to two lines;
• preserves the end of the final spoken word;
• uses millisecond-accurate timestamps;
• keeps speaker changes when available;
• handles Chinese and Japanese text without forcing spaces.

Output files

For the original language and each successful translation, the Actor can generate:

• .srt — SubRip subtitles;
• .vtt — WebVTT subtitles;
• .txt — plain-text transcript;
• .json — structured metadata, timings, speaker data, and subtitle metrics.

Generated files are stored in the run's Key-Value Store.

The Dataset contains one flat row for the original-language files and one row for each successful translation, with direct download links for SRT, WebVTT, TXT, and JSON.

The OUTPUT record contains the complete run summary, including detected language, media duration, billable minutes, generated files, successful translations, failed translations, charged events, and safe error messages.

Example input

Translate a French video into English, Spanish, and German:

{
  "mediaUrl": "https://example.com/interview.mp4",
  "targetLanguages": [
    "EN-US",
    "ES",
    "DE"
  ]
}

The Apify Console also allows you to upload the media file directly instead of using mediaUrl.

Example output summary

{
  "status": "success",
  "sourceFilename": "interview.mp4",
  "sourceLanguage": "fr",
  "mediaDurationSeconds": 125.424,
  "billableMinutes": 3,
  "successfulLanguages": [
    "EN-US",
    "ES",
    "DE"
  ],
  "failedLanguages": [],
  "billing": {
    "events": {
      "actor-start": 1,
      "transcribed-minute": 3,
      "translated-minute": 9
    }
  }
}

Pricing

This Actor uses pay-per-event pricing.

Event	Price	Charged when
actor-start	$0.05	Once for a valid processing run
transcribed-minute	$0.03	Per started audio minute sent for transcription
translated-minute	$0.04	Per started audio minute and successful target language

Examples:

• A 2-minute file transcribed without translation: $0.11
• A 2-minute file transcribed and translated into one language: $0.19
• A 2-minute file transcribed and translated into three languages: $0.35

Translation is charged only after the translation provider returns a successful result. Provider authentication or quota failures do not charge a successful translation event.

The Apify Console displays the maximum permitted run cost before execution.

Free readiness check

Running the Actor without a media source performs a zero-cost readiness check.

It does not call transcription or translation providers and does not charge pay-per-event events. Upload a file or provide a direct media URL for real processing.

Limits

Limit	Value
Media size	500 MB
Default media duration	60 minutes
Absolute media duration	180 minutes
Subtitle lines	2 maximum

Media is inspected before paid processing whenever possible. Files above the configured limits, corrupt media, and media without audio are rejected before transcription.

Billable duration is based on the usable audio stream and rounded up to the next started minute.

Privacy and external processing

Media is downloaded into temporary storage inside the Actor run and removed when processing ends.

Audio is sent to the configured transcription provider. Subtitle text is sent to the configured translation provider only when translation is requested.

Credentials, signed URLs, complete provider responses, and raw media content are not intentionally written to logs or result metadata.

Limitations

This Actor does not:

• burn subtitles into a video;
• accept social-platform webpage URLs;
• review translation meaning or cultural accuracy;
• perform human linguistic review;
• guarantee that every translation meets a specific broadcaster's reading-speed rules.

Use Professional Subtitle QC for dedicated SRT/VTT compliance checking and conservative correction.

Use Professional Subtitle Translator & Video Captioner when you need the complete workflow and optional final MP4 rendering.

Recommended workflow

1. Upload the media file or provide a direct media URL.
2. Leave source-language detection on automatic unless you know the language.
3. Select only the output languages you need.
4. Download and review the SRT or VTT files.
5. Use the dedicated QC Actor when formal subtitle compliance is required.
6. Import the reviewed files into your video editor.

Support

Include the Apify run ID and a minimal reproducible input when reporting a problem.