Gradium launches TTS beta with sub-50ms TTFA, roughly half the latency of most models

mattturck · x · 2026-09-23

Gradium released its TTS beta model claiming under 50ms time-to-first-audio at comparable quality, versus the >100ms TTFA typical of most models. The model is available to try now, targeting real-time voice use cases where latency is the deciding factor.

Related event: Gradium TTS Beta Delivers Sub-50ms Time-to-First-Audio(2 posts)→

Original post →

More from Multimodal

Multimodal channel →