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
[alt: Illustration representing multilingual code-switching for the Speechmatics Melia 1 speech-to-text model.]
Technical

Melia 1 leads speech-to-text code-switching in Arabic, Mandarin and Tamil

Speechmatics
SpeechmaticsEditorial Team
[alt: Dark grid background with a circular symbol on the left and a pixelated "K" on the right connected by a cyan line.]
Product

Speechmatics & LiveKit Inference target the accuracy gap that breaks voice agents in production

Speechmatics
SpeechmaticsEditorial Team
Carousel slide image
Product

Speechmatics on Zapier: No-Code Speech-to-Text Automation

Speechmatics
SpeechmaticsEditorial Team
[alt: Medical model header asset]
Product

Speechmatics launches Medical Model for real-time clinical transcription

Speechmatics
SpeechmaticsEditorial team
Carousel slide image
News

Stenograph and Speechmatics Announce Industry-First On-Device Integration for CATalyst VP

Speechmatics
SpeechmaticsEditorial Team
[alt: Speaker lock blog image]
Product

Speaker Focus: Fixing Voice AI for the real world

Anthony Perera
Anthony PereraProduct Marketing Manager