Auto Captions

Overview

Zencoder can automatically generate captions of the audio track for your videos. The job may also include transcoding by including video outputs, but does not have to.

Currently, auto captions are limited to the following languages

Australian English (en-AU)
Afrikaans (af-ZA)
Brazilian Portuguese (pt-BR)
British English (en-GB)
Canadian French (fr-CA)
Danish (da-DK)
Dutch (nl-NL)
Farsi Persian (fa-IR)
French (fr-FR)
German (de-DE)
Gulf Arabic (ar-AE)
Hebrew (he-IL)
Indian English (en-IN)
Indian Hindi (hi-IN)
Indonesian (id-ID)
Irish English (en-IE)
Italian (it-IT)
Japanese (ja-JP)

Korean (ko-KR)
Malay (ms-MY)
Mandarin Chinese – Mainland (zh-CN)
Mandarin Chinese (Taiwan) (zh-TW)
Modern Standard Arabic (ar-SA)
New Zealand English (en-NZ)
Portuguese (pt-PT)
Russian (ru-RU)
Scottish English (en-AB)
South African English (en-ZA)
Spanish (es-ES)
Swiss German (de-CH)
Tamil (ta-IN)
Telugu (te-IN)
Thai (th-TH)
Turkish (tr-TR)
US English (en-US)
US Spanish (es-US)
Welsh English (en-WL)

Output formats supported for captions (set using format ):

mp4 files, with caption track in CEA-608 format
m3u8 outputs (segmented outputs with H.264 video in TS format)
SCC, WebVTT, VTT, and DFXP formats are also supported with captions type output

In addition to the settings described below, you will need to use the following settings:

Enabling auto captions

If you are a credit card customer, you can enable auto captions by going to Account > Subscription and clicking on the button shown in the image below:

If you are a premium customers need to contact your Customer Success Manager to have auto captions enabled.

caption_from_audio_transcription

caption_from_audio_transcription:Boolean

API Versions: V2

Parent: outputs

Default: false

Compatible Job Types: VOD

Description:

Uses audio transcription to generate captions when captions are not available in the source file.

{
  "input": "s3://zencodertesting/test.mov",
  "outputs": [
    {
      "type": "captions",
      "caption_from_audio_transcription": true
    }
  ]
}

include_transcription_json

include_transcription_json:Boolean

API Versions: V2

Parent: outputs

Default: false

Compatible Job Types: VOD

Description:

Whether a JSON version of the transcription should be included along with the captions. caption_from_audio_transcription must also be set to true.

{
  "input": "s3://zencodertesting/test.mov",
  "outputs": [
    {
      "type": "captions",
      "caption_from_audio_transcription": true,
      "include_transcription_json": true
    }
  ]
}

Sample JSON output

{
  "results": {
    "language_code": "en-US",
    "transcripts": [
        {
            "transcript": "funny woman Tina Fey is about to team up with Steve Carell and "
        }
    ],
    "items": [
        {
            "start_time": "3.64",
            "end_time": "3.94",
            "confidence":"1.0",
            "content": "funny"
        },...

transcription_filename

transcription_filename:String

API Versions: V2

Parent: outputs

Default: none

Compatible Job Types: VOD

Description:

Specify a filename for the JSON transcription file. If not included, a default name will be used. If included, it must have a value, or an error will be returned.

{
  "input": "s3://zencodertesting/test.mov",
  "outputs": [
    {
      "type": "captions",
      "caption_from_audio_transcription": true,
      "include_transcription_json": true,
      "transcription_filename": "stc-episode-3-transcript.json"
    }
  ]
}

audio_language

audio_language:String

API Versions: V2

Parent: outputs

Default: auto (same as the audio_language value)

Compatible Job Types: VOD

Description:

The language of the input audio for using on transcription.

This value is a BCP-47 style language code, for instance “en-US”, “en-GB”.

Valid values: af-ZA, ar-AE, ar-SA, cy-GB, da-DK, de-CH, de-DE, en-AB, en-AU, en-GB, en-IE, en-IN, en-NZ, en-US, en-WL, en-ZA, es-ES, es-US, fa-IR, fr-CA, fr-FR, ga-IE, gd-GB, he-IL, hi-IN, id-ID, it-IT, ja-JP, ko-KR, ms-MY, nl-NL, pt-BR, pt-PT, ru-RU, ta-IN, te-IN, th-TH, tr-TR, zh-CN, zh-TW

{
  "input": "s3://zencodertesting/test.mov",
  "outputs": [
    {
      "type": "captions",
      "audio_language": "es-ES"
    }
  ]
}