Rev.ai accepts pretty much any accepted audio and video file format.
To test streaming accuracy and latency without writing any code, go to https://www.rev.ai/streaming, click on the red microphone, and talk. No login required. Or, if you have registered (see below), you can go to https://www.rev.ai/account/livestreaming and try out our profanity filter and custom vocabulary as well as streaming transcription. When finished, you can go to your dashboard https://www.rev.ai/jobs and download a txt, json, or srt or vtt caption files.
Notice: the 1st pass is light gray and becomes black as the final word choice is done (demonstrating the context based transcription). Also notice capitalization and punctuation.
The following 3 testing methods require registering for an account.
2) To test streaming via the API:
Here is a repository for examples on how to use the node SDK, python SDK or just pure JS.:
3) To test async (file based batch/pre-recorded) by uploading a file via the dashboard, go here and click on UPLOAD button.
4) To test async via the API:
In all cases, be sure to notice the punctuation and capitalization.
Be sure to check out our custom vocabulary - your chance to add your words to our dictionary.