AssemblyAI launches Dictation API with 134ms p50 latency

AssemblyAI · x · 2026-09-16

AssemblyAI has launched the Dictation API, built for the hold-hotkey-talk-release loop and for apps where users trigger dictation hundreds of times a day.

Key specs: 134ms p50 latency so text lands about as fast as typing; punctuation and casing are already applied on return; a single endpoint to integrate, which the company says lets teams ship dictation within one sprint.

Related event: AssemblyAI Launches Dictation API With 134ms Latency(2 posts)→

Original post →

More from Apps

Apps channel →