There are two levels of transcription on Plotto. All transcriptions are time-coded.


Auto-transcription is offered as standard. All video content submitted will get the transcription automatically, including keyword analysis and sentiment analysis. This happens within 1-2 minutes of the video being submitted. As a business user, you can manually edit these transcriptions in the video response page, with the Transcription Editor.

We are using different AI engines for speech-to-text and auto-transcription:

  • Engine W with language auto-detect supports the following languages:
    • English [GB]
    • English [US]
    • Brazilian Portuguese
    • Japanese, Mandarin Chinese
    • Modern Standard Arabic
    • Spanish
    • Italian
    • German
  • Engine B can work only if you specify the language on Survey definition and support the following languages;
    • English [GB]
    • English [US]
    • Chinese [CN]
    • French [FR]
    • German [DE]
    • Italian [IT]
    • Spanish [ES]

Every new version will bring more engines and speech-to-text capabilities and you should use the one which provides the best fit for your project.

You can select the engine in the <View Result> page, using the Transcription Editor.

Human transcription

We also offer a manual transcription service if greater accuracy is required. The turn around time is subject to a brief but usually 2-3 days.