Temi API

Setup

Wiring the Temi API by hand means setting up its bearer token, attaching it to every call against api.temi.com/v1, and building the job polling and retry handling for transcription jobs yourself. Through Jentic you install once, import the Temi API from the API Directory, store the token once, and your agent calls it.

Permission scoping

The Temi API puts the job id in the URL path (/jobs/{jobId}), so a rule can pin your agent to one job: it can read that job and its transcript and nothing else. You choose the operations it may call, so ones like deleting a job are not included unless you add them.

Credential isolation

Your Temi token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'submit a transcription job' or 'get a job transcript', and Jentic returns the matching Temi API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.