Speak Ai API

Setup

Wiring Speak Ai by hand means running its token exchange to get and refresh an Authorization key, then coordinating signed-url uploads and media, transcript, and folder operations yourself. Through Jentic you install once, import the Speak Ai API from the API Directory, store the key once, and your agent calls it.

Permission scoping

Speak Ai puts the media id in the URL path (/media/insight/{mediaId}, /media/transcript/{mediaId}), so a rule can pin your agent to one media item: it reads insights and transcripts for that item and nothing else. You choose the operations it may call, so destructive ones like deleting media or a folder are not included unless you add them.

Credential isolation

Your Speak Ai API key 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 'get a signed upload url' or 'read a media transcript', and Jentic returns the matching Speak Ai operation with its input schema so the agent calls the right endpoint without browsing the reference docs.