Blog
Page 8 of 14
Deepgram STT: latency, diarization, and long-call stability
How fast is Deepgram STT, how many speakers can it tell apart, and does it hold up on long calls? Straight answers, plus how to verify them on your audio.
How to A/B test voice variations in Deepgram
A/B testing voices in Deepgram means comparing Aura voices on caller outcomes, not vibes. Learn how to set up the test and measure which voice wins.
How to load test Deepgram's Voice Agent API
Load testing Deepgram's Voice Agent API means proving latency and concurrency hold under real traffic. Learn what to measure and how to run the test.
How to build voice agents with GPT-Live (and what to do until the API ships)
GPT-Live changes how you architect a voice agent, not just which model you call. Learn what full-duplex changes and what to build until the API ships.
How to test GPT-Live voice agents: the new failure modes of full-duplex
GPT-Live is full-duplex, so it breaks the clean-turn assumption most tests rely on. Learn the new failure modes and how to test a GPT-Live voice agent.
Voice agent testing for food ordering: order accuracy, modifiers, and noise
Food ordering voice agents take orders over noisy lines full of modifications. Learn how to test one for order accuracy and noise robustness.
Voice agent testing for appointment scheduling: booking, dates, and tools
Scheduling voice agents book, reschedule, and cancel across calendars and timezones. Learn how to test an appointment scheduling voice agent for accuracy.
Voice agent testing for insurance: claims, quotes, and accuracy
Insurance voice agents handle claims, quotes, and policy questions. Learn how to test an insurance voice agent for accuracy and safe escalation.
Voice agent testing for financial services: authentication, fraud, and compliance
Financial services voice agents handle authentication, money movement, and disclosures. Learn how to test a banking voice agent for security.