Rev.ai is an accurate automated speech recognition service. You can use Rev.ai as a step to get back a transcript, to get back an SRT subtitle/caption file, or to burn-in subtitles onto your video.
Here's how to use the Rev.ai step.
Assume you want all videos that upload to a specific AWS S3 bucket/folder to be transcribed. The first step will be the S3 trigger step.
1. Then add Rev.AI Transcription step to the Flow
2. Select "Transcribe" as the action
3. Setup the Transcript Options such as entering the correct language code
Source: the input video
Language code: language code associated with the video
Dictionary: array of phrases to help the AI transcribe more accurate (optional). Each phrase should be in string format (accept double quotes only)
Rev.ai Access Token
4. Add "Transfer to Storage" step to save the results/output of the Rev.ai step back to your file hosting service like S3.
Source: the source file which will be uploaded
Host: hosting providers: s3 (we support Amazon S3 for now; more options to be added in the future)
Access Key, Secret Key: the AWS credential that has write access to your S3 bucket
Bucket Name, File Name: the destination where the file will be saved. You can save the file to a specific folder and subfolder by using / (as in the example screenshot above). If you leave the name empty or specify the folder only, a unique file name will be used for the uploaded file.
5. Save, Enable then trigger the flow and check the log for the result.
Valid language codes:
ISO 639 Language Code