Amazon S3
AssayWhat you get
- Each .txt or .json file in the folder becomes one conversation, and a file is never imported twice.
- Plain text files use one “Speaker: text” line per turn. JSON files use the same shape as the Assay API and can name their own channel.
- Read-only access is enough: the keys only need to list the folder and read files.
How it works
- Step 1
Connect Amazon S3
An admin pastes a key in Assay. We check it with Amazon S3 before saving it, and it’s stored encrypted.
- Step 2
Conversations arrive
Every 15 minutes, finished conversations are imported and checked against your rules, line by line.
- Step 3
People decide the unclear ones
Clear results are recorded with the line behind them. Anything uncertain goes to your review queue.
Set up in a few minutes
An owner or admin connects Amazon S3 from Settings, then Integrations. Integrations are included in the Team and Business plans.
- Save each conversation as its own .txt file, one “Speaker: text” line per turn, or as a .json file in the same shape as our API.
- In AWS, create an IAM user that can list the bucket and read the folder (s3:ListBucket and s3:GetObject).
- Create an access key for that user and copy both parts.
Works alongside
All integrationsTry it on your own calls
Tell us about your team. We’ll reply within two working days to set up a trial with 50 of your transcripts and your current scorecard.
- No card or contract for the trial
- Your conversations are never used to train models
- We go through the results with you
Thanks, we’ve got it.
We’ll be in touch within two working days.