/audio/transcriptions endpoint returns error for audio files with unexpected sampling rate

What to do

• Check whether your product depends on Cohere. Check your stack

  Paste a package.json, lockfile, Terraform or a list of domains at down.guide/stack to see every provider you depend on.

• Confirm your retries, queues and scheduled jobs caught up after the 2h 54m it lasted.

  Anything that failed between 2026-06-01 13:51 UTC and 2026-06-01 16:46 UTC may need a replay.

• Subscribe to Cohere's feed to hear about the next one first. RSS feed

  https://down.guide/feed?provider=cohere works in Slack (/feed subscribe), Discord feed bots and any RSS reader.

Updates from Cohere 2

1. identifiedJun 1, 2026, 1:51 PM UTC

   /audio/transcriptions endpoints availability is affected now due to the Cohere ASR model backing the endpoint throws error for any audio inputs that are in the expected sampling rate. Previously these sampling rate audio files were accepted and processed, marking this as a regression type incident. :hammer_and_wrench: We have identified the root cause of the incident, and are working diligently to fix.

   provider

2. resolvedJun 1, 2026, 4:46 PM UTC

   🎉 The issue has been resolved and we are back to normal.

   provider

Corrections

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.