Updated: Apr 14, 2026 | Read time 7 min

Speed you can trust: The STT metrics that matter for voice agents

What “fast” actually means for voice agents — and why Pipecat’s TTFS + semantic accuracy is the clearest benchmark we’ve seen.
Pipecat-benchmarks-blog - Header (1200 × 900)
Archie McMullan
Archie McMullanSpeechmatics Graduate
Carousel slide image
Company

Better than Whisper: how Adobe Premiere's on-device speech engine got rebuilt

Andrew Innes
Andrew InnesChief Architect
Carousel slide image
Technical

The Adobe story: How we made cloud-grade AI work on your laptop

Andrew Innes
Andrew InnesChief Architect
Carousel slide image
Technical

De-risk your voice agent: The 11 best voice agent testing platforms in 2026

Speechmatics
SpeechmaticsEditorial Team
Carousel slide image
Technical

How to build a microbatching workflow with the Speechmatics API

Speechmatics
SpeechmaticsEditorial Team
Carousel slide image
Product

Alphanumeric speech recognition: why voice assistants mangle SKUs (and how to fix it)

Speechmatics
SpeechmaticsEditorial Team
Carousel slide image
Company

Adobe and Speechmatics deliver cloud-grade speech recognition on-device for Premiere

Speechmatics
SpeechmaticsEditorial Team