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)→
More from Apps
- Polyphonic beta: a Mac 'home' where Claude Code, Codex and other agents share memory and collaborate — RileyRalmuto · 2026-09-16
- Dev builds astra atlas: browsable gallery of 366 things people made with gpt-6 astra — OpenAIDevs · 2026-09-16
- Podcast: AI agents spotted a rare disease top labs missed, frontier models beat old workflows — danielmckinn0n · 2026-09-16
- Obsidian 1.14.2 lets you edit any Markdown file without moving it into your vault — JeremyNguyenPhD · 2026-09-16
- Gemini Notebook Realtime Voice Mode rolls out to Ultra subscribers this week, Pro 'soon' — testingcatalog · 2026-09-16
- Meta's Muse agent auto-sourced components across 14 suppliers with per-purchase approval — armand_ruiz · 2026-09-16