Transcribing videos

Flowplayer offers AI-driven speech to text transcriptions that automatically add the transcript as a vtt subtitle to the video and displays it in the player.

This feature is only available for Enterprise subscriptions

There are three ways to start transcribing videos.

  • Configure the Workspace settings to automatically start transcribing on video asset uploads.
  • Manually start transcription by clicking "Manage Files" and then select transcription language for the video asset.
  • Using the API to start the transcription per video.

Manually starting transcriptions

Start by opening in the Manage Files dialog on the Video page

Transcriptions

Select the language to be used for the transcription

Transcriptions

If the transcription job successfully starts you should see a "Transcription in progress"

Transcriptions

When completed the transcription will be available as a WebVTT text track.

Transcriptions

Supported languages

Flowplayer can transcribe files in any of the following languages:

    • Language
    • Code
    • Detect from Metadata*
    • follow-input
    • English
    • en
    • French
    • fr
    • German
    • de
    • Spanish
    • es
    • Swedish
    • sv
    • Arabic
    • ar
    • Armenian
    • hy-AM
    • Bulgarian
    • bg
    • Catalan
    • ca
    • Croatian
    • hr
    • Chinese (Cantonese)
    • yue-Hant-HK
    • Chinese (Mandarin)
    • cmn-Hans-CN
    • Czech
    • cs
    • Danish
    • da
    • Dutch
    • nl
    • Finnish
    • fi
    • Greek
    • el
    • Hebrew
    • he-IL
    • Hindi
    • hi
    • Hungarian
    • hu
    • Indonesian
    • id-ID
    • Italian
    • it
    • Japanese
    • ja
    • Korean
    • ko
    • Latvian
    • lv
    • Lithuanian
    • lt
    • Malay
    • ms-MY
    • Norwegian, Bokmål
    • nb-NO
    • Polish
    • pl
    • Portuguese
    • pt
    • Romanian
    • ro
    • Russian
    • ru
    • Slovak
    • sk
    • Slovenian
    • sl
    • Thai
    • th-TH
    • Turkish
    • tr-TR
    • Vietnamese
    • vi-VN

* Detect from metadata uses the language meta data on the input file's audio track to determine the language. If that is not possible it will default to English.

Results