AssemblyAI documents a capability change: “# Fix: Word Timestamps Returning Uniform 80ms Durations A regression introduced on July 15 caused most words on Universal-3 Pro and Universal-3.5 Pro to…”
# Fix: Word Timestamps Returning Uniform 80ms Durations
A regression introduced on July 15 caused most words on Universal-3 Pro and Universal-3.5 Pro to return end timestamps exactly 80 ms after start, regardless of actual word duration…
Read more
A regression introduced on July 15 caused most words on Universal-3 Pro and Universal-3.5 Pro to return end timestamps exactly 80 ms after start, regardless of actual word duration. This has been fixed; word-level timestamps again reflect true spoken durations.
Transcripts created between July 15 and July 29 may show the compressed durations — re-transcribe if precise word timing matters for those files.
Show less
Fix Pre-recorded Speech-to-Text
Entry date: 2026-07-24
Read from the provider's text; the quote is the provider's exact lines.
AssemblyAI documents a capability change: “# Breaking: Async Default Model Changes to Universal-3.5 Pro on August 7 Update (August 1, 2026): This change has been rescheduled to September 2, 2026, and…”
# Breaking: Async Default Model Changes to Universal-3.5 Pro on August 7
Update (August 1, 2026): This change has been rescheduled to September 2, 2026, and the migration behavior has changed — requests pinned to universal-3-pro will return an error instead of being auto-routed…
Read more
Update (August 1, 2026): This change has been rescheduled to September 2, 2026, and the migration behavior has changed — requests pinned to universal-3-pro will return an error instead of being auto-routed. See the updated announcement for current details. The original entry follows below.
Requests that omit speech_models (or pass a legacy speech_model name) route to the default model. The default is universal-2 today and switches to universal-3-5-pro on August 7, 2026. On the same date, requests pinned to universal-3-pro are auto-routed to universal-3-5-pro.
If you rely on the default, your requests switch automatically that day, so set speech_models explicitly to pin your current model.
Read the docs on selecting a speech model →
Read from the provider's text; the quote is the provider's exact lines.
AssemblyAI documents a capability change: “# Universal-3-Pro Now Available for Streaming Universal-3-Pro is now available for real-time streaming — bringing our most accurate speech model to live…”
Universal-3-Pro is now available for real-time streaming — bringing our most accurate speech model to live transcription for the first time…
Read more
Universal-3-Pro is now available for real-time streaming — bringing our most accurate speech model to live transcription for the first time. Developers building voice agents, live captioning tools, and real-time analytics pipelines can now combine Universal-3-Pro's state-of-the-art accuracy with the low latency of AssemblyAI's streaming API.
Read from the provider's text; the quote is the provider's exact lines.
