
Yandex SpeechKit
The six pillars
Each bar is the score; the bracket is its 95% range.
Can you see what it costs?
Can you see how much it's used?
Can you tie cost to one agent?
Can an agent on it report out?
Can you control spend and access?
Does it work on small plans?
Where the evidence comes from
Once three independent fleets report on a pillar, desk research counts for at most a third of it. FleetRegistry's own fleets never count.
Controls on record
Yandex Cloud budgets are notification-only ('Reaching a pre-set threshold does not affect subsequent resource utilization'); stopping resources needs a budget trigger + Cloud Function. Audit Trails tracks SpeechKit data-plane events (stt.RecognizeSpeechAsync, stt.RecognizeSpeechStream, stt.GetRecognition, tts.UtteranceSynthesis); delivery/API access to the log not confirmed on the page read. Auth via IAM tokens or service-account API keys; key scopes not documented on the page read.
History
Run agents on Yandex SpeechKit?
Give each one a permanent number, a named person who answers for it, and a record of what it can touch and what it costs. Free.