AssemblyAI incident

Requests failing for Slam-1 model

Major Resolved View vendor source →

AssemblyAI experienced a major incident on October 22, 2025 affecting Asynchronous API, lasting 6h 1m. The incident has been resolved; the full update timeline is below.

Started
Oct 22, 2025, 05:56 PM UTC
Resolved
Oct 22, 2025, 11:58 PM UTC
Duration
6h 1m
Detected by Pingoru
Oct 22, 2025, 05:56 PM UTC

Affected components

Asynchronous API

Update timeline

  1. identified Oct 22, 2025, 05:56 PM UTC

    We are currently seeing longer-than-usual turnaround times for pre-recorded audio transcriptions that are using our Slam-1 model. Requests using the Universal model are unaffected. We are working to address this issue and will provide an update here as soon as possible.

  2. identified Oct 22, 2025, 06:01 PM UTC

    We are now seeing increased error rates and failures for requests using the Slam-1 model so we are elevating this issue to a partial outage. Requests using Universal are working normally, so consider using that model as a short-term workaround if needed. Our team is working to resolve this issue as quickly as possible.

  3. identified Oct 22, 2025, 07:03 PM UTC

    We are once again starting to see requests using Slam-1 succeed, but we are still working to fully resolve the issue. We will follow up with another update once the issue has been fully mitigated.

  4. identified Oct 22, 2025, 07:20 PM UTC

    We are still seeing good success rates for requests using the Slam-1 model, but we are still seeing occasional slower-than-usual processing times, which we are working to address.

  5. monitoring Oct 22, 2025, 07:37 PM UTC

    Success rates and turnaround times for requests using Slam-1 have returned to normal ranges, but we are continuing to monitor traffic to ensure continued good performance.

  6. resolved Oct 22, 2025, 11:58 PM UTC

    We have continued to see good performance for requests using Slam-1 and are now marking this issue as resolved.