Skip to content

2026.08.24

UpdateUnverifiedAdded Sep 25, 2026

Speech-to-Text requests now require a language in json_config . Our ASR gives its best results when the language is known, so set it whenever you can: en , fr , es , pt , or de . When the language is not known ahead of time, pass any and the model detects it from the audio. Requests that already set a language or any are unaffected.

's release notes

More releases

Every release
DateRelease
Aug 162026.09.24unverified
Beta
Aug 162026.09.22unverified
Beta
Aug 162026.09.16unverified
Update
Aug 162026.08.10unverified
Beta
Aug 162026.07.28unverified
Update
Aug 162026.07.22unverified
Update
Aug 162026.02unverified
Update
Sep 252026.09.15unverified
Preview

Also shipped on Aug 16, 2026

in August 2026

Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.

New releases by email

Tuesday mornings: the week's data, AI and developer-tools releases, only in weeks when something shipped.

Double opt-in. Unsubscribe any time.