Amazon Transcribe
How it Works
Transcribe actions work in two steps: one action sends the job to AWS, and another retrieves the results later. AWS keeps the results for 7 days, so you can run the retrieval action anytime within that period without being charged again. If you try to retrieve the results after 7 days, the action will fail because the results are no longer available.
How you set up these actions will depend on your workflow, but here’s a simple example: you can trigger a transcription job using a checkbox or pick list in CatDV. A second worker action can then run every 2 minutes to check for results—usually it only needs to check once or twice before the results are ready. To monitor the progress of a job, you can use the field aws.ai.rekognition.job.status—if it says IN_PROGRESS, the job is still running. For more technical details, see the ‘Troubleshooting & Advanced Notes’ section.
The general process behind transcribing involves a few key steps:
Encode the input file.
Upload the encoded file to your remote S3 volume.
Submit the S3 file location to the appropriate Amazon AI service.
Retrieve and apply the results as clip markers in CatDV.
Finally, delete the temporary file from the S3 volume.
Import Worker Actions
While you're free to define your own workflows, pre-defined workflows are included in the WorkerActions folder to help you get started quickly. Simply drag and drop these files into the Worker GUI to import them. With minimal configuration, your workflow will be ready to use.
WorkerActions/Amazon AI - Submit Transcriptions.catdv
WorkerActions/Amazon AI - Retrieve Transcriptions.catdv
Worker Action Settings
The settings available in the Worker Plugin for Submit Transcription Job are:
S3 Volume | The S3 remote volume identifier is required to access the S3 bucket. If you haven't set up a remote volume yet, please refer to the Authentication section. Note: The identifier must be enclosed in square brackets []. |
AWS Access Key (optional) | Define only if you wish to use a different account to perform the operation. |
AWS Secret Key (required) | Used as part of the authentication. |
Action | Submit Transcription Job. Submit a transcription request to AWS. Retrieve Transcription Job. Get transcription result from AWS. |
Set Parameters | Define the request parameters using CatDV fields or set them manually on the worker. |
Source Language | When submitting a transcription job, the input language / dialect of the content must be identified. If you know the input language will be consistent, you can choose a specific language manually from the provided dropdown - otherwise you can specify ‘From Field Values’ and use a CatDV picklist/text field which contains the language name or language code - the plugin is “smart” and will recognize either one, or even a partial match (like ‘Scott’ for ‘Scottish’). |
The settings available in the Worker Plugin for Retrieve Transcription Job are:
S3 Volume | The S3 remote volume identifier is required to access the S3 bucket. If you haven't set up a remote volume yet, please refer to the Authentication section. Note: The identifier must be enclosed in square brackets []. |
AWS Access Key (optional) | Define only if you wish to use a different account to perform the operation. |
AWS Secret Key (required) | Used as part of the authentication. |
Action | Submit Transcription Job. Submit a transcription request to AWS. Retrieve Transcription Job. Get transcription result from AWS. |
Set Parameters | Define the request parameters using CatDV fields or set them manually on the worker. |
Output Field | where the raw transcript goes - in manual mode, use the clip[identifier] syntax |
Marker Category | which category to create markers in |
Isolate these words | Any words in this box get their own marker |
Show Speaker Labels | requires a minimum of 2 speakers, displays labels where chosen |
Advanced Properties
For system builders and power users, here are some additional plugin options which can be set in the Worker Node Advanced Properties box:
Property key | Valid range (default) | Description |
amazonAI.outputRawResponseDataToField | <field identifer> | Writes a JSON object to the field of your choosing e.g. clip[ai.json] - note these responses can be half a megabyte or larger which doesn’t sound like much but can crowd your database if you’re not careful, so it is recommended only to use this feature in a transient nature and then remove the extra data when finished. |
amazonAI.outputRawResponseDataToFile | <path> | Writes a JSON object to an external text file of your choosing (e.g. /Volumes/MyData/myResponse.txt) which you could parse separately and then toss away, rather than keeping all of the raw response data in the CatDV database. |
amazonAI.transcribe.markerSeparator | Any character (.) | change the default marker separator of “.” to something else |
amazonAI.transcribe.maxMarkerLength | Any numbers (160) | change the built-in marker length limit of 160 chars |
Usage Cost
With Amazon Translate, you pay-as-you-go based on the seconds of audio transcribed per month. It’s easy to get started with the Amazon Transcribe Free Tier. Upon signup, start analyzing up to 60 audio minutes monthly, free for the first 12 months.
Amazon AI USD pricing as of Summer 2020 is:
· 12 months free - 60 minutes of audio per month
· then $0.006 for up to 15 seconds + $0.0004 per additional second
For latest pricing information refer to Amazon official site https://aws.amazon.com/transcribe/pricing/ .
Please be mindful of the AWS service costs associated with each AI operation, especially as you scale up usage of the plugin. Quantum Corp. does not accept any liability for AWS service costs incurred as a result of using this software, regardless of if the usage incurred was intentional or not.
Supported Languages
Please find the current list of languages supported by Amazon Transcribe here:
https://docs.aws.amazon.com/transcribe/latest/dg/what-is-transcribe.html