Frequently Asked Questions


  1. What can I do with the API?
  2. All VoiceBase features are available through the API. See our features and pricing page for a full list of features.

  3. How do I get an API Key?
  4. You can request API access using this form:

  5. What if I'm not a developer?
  6. If you are a student or individual looking to transcribe less than 500 hours/month of content, visit our web app page to learn how VoiceBase can work for you.

  7. What languages are supported?
  8. For Machine Transcription the following languages are supported: English, US English, UK English, Southeast Asian English, Australian English, German, Spanish, Latin American Spanish, French, Italian, Dutch, and Indian English.
    For Human Transcription the follow languages are supported: English, German, Italian, French, and Spanish.


  9. How does the API accept media?
  10. The API can accept urls to the media or the actual media as form data attachments.

  11. What file formats can be uploaded?
  12. Our total list of accepted formats includes,
    *.mp3, *.mp4, *.flv, *.wmv, *.avi, *.mpeg, *.aac, *.aiff, *.au, *.ogg, *.3gp, *.flac, *.ra, *.m4a, *.wma, *.m4v, *.caf, *.cf, *.mov, *.mpg, *.webm, *.wav, *.asf, *.amr

  13. How will API usage be billed?
  14. The first 10 hours of audio and video content processed for machine transcription with keywords and topics are free.

    Additional usage will be billed per minute of content submitted. Each job can be queried to view its duration.

    Please contact support if you need an extended trial.

  15. How do I use the Predictions API?
  16. The prediction API is simple to use. At upload time reference your unique model ID, prediction results will be returned once processing is complete.

    To create a model please get in contact with your account manager or support –

  17. What is the maximum amount of volume I can send?
  18. VoiceBase is able to support any level of volume.
    Please contact an account manager to discuss best practices for your personal use case.

  19. What is included in the Web SDK?
  20. The VoiceBase Web SDK contains our player plugin which wraps around many popular video players to display click-to-navigate transcript, keywords, and topics. This is written primarily in javascript and css. All Web SDK contents may be used free and at your disposal.

  21. How do I retrieve processed data?
  22. VoiceBase offers both polling and callback options to check for processing completion. Data can be returned in the callback or retrieved in a separate API request. Responses are in JSON format.

Don’t see what you’re looking for?

Contact Us