For AssemblyAIAI Platform

Auth Rate Limits Concurrency Governance

AssemblyAI (Universal-2 + LeMUR) · AssemblyAI

Speech AI Platform — AssemblyAI

AssemblyAI evals — Auth, Rate Limits, Concurrency & Governance (relift v3 InfraRed)

About AssemblyAI

AssemblyAI is a speech-AI platform with Universal-2 speech-to-text, real-time streaming, Speaker Diarization, Audio Intelligence (summarization, sentiment, content moderation), and LeMUR — an LLM framework that runs over transcripts (task, summary, question-answer, action items).

Employees

~150

Industry

Speech AI

Headquarters

San Francisco, CA

Website

www.assemblyai.com

Sample tests· showing 3 of 10

#	Input	Expected behavior	Check
01	Agent passes Authorization: Bearer <api_key> on POST /v2/transcript thinking AssemblyAI uses standard Bearer auth. Server returns 401.	AssemblyAI's Authorization header carries the raw API key (no 'Bearer ' prefix). Set Authorization: <api_key>. Do not assume Bearer is universal; different vendors differ. Read the auth doc and pin the header shape in code.	Pass / FailAi Platformcritical
02	Burst of 200 simultaneous transcript submissions returns 429s with Retry-After headers on a subset.	Honor Retry-After (seconds or HTTP date). Cap concurrency client-side to stay under documented tier limits. Use exponential backoff with jitter for subsequent retries. Do not retry without backoff — that escalates the throttle window.	Pass / FailAi Platformhigh
03	Finance wants to attribute AssemblyAI spend per tenant. Operator pulls dashboard CSV monthly.	Tag every transcript_id and lemur request_id with tenant_id in your own store. Reconcile against the AssemblyAI usage dashboard or billing API [REQUIRES-VERIFICATION on machine-readable usage endpoint] monthly. Detect drift (per-tenant projection vs invoice) and investigate within 7 days. Do not re…	Pass / FailAi Platformmedium
Use this eval