Skip to main content
AssemblyAI

Requests failing for Slam-1 model

Partial outage Lasted 6h 1m · started · AssemblyAI's page

Level
confirmed
Worst impact
Partial outage
Components
Asynchronous API
Down Index
43of 100

What to do

  • Check whether you use AssemblyAI Asynchronous API. 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 6h 1m it lasted.

    Anything that failed between 2025-10-22 17:56 UTC and 2025-10-22 23:58 UTC may need a replay.
  • Subscribe to AssemblyAI's feed to hear about the next one first. RSS feed

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

Updates from AssemblyAI 6

  1. identified

    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.

    provider

  2. identified

    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.

    provider

  3. identified

    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.

    provider

  4. identified

    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.

    provider

  5. monitoring

    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.

    provider

  6. resolved

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

    provider

Reports count in aggregate; nothing about you is shown.

Corrections

None so far.

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

Questions about DWN-0b81f1717d

Is AssemblyAI still down?

No, this incident was resolved 2025-10-22 23:58 UTC. For AssemblyAI's live state, see https://down.guide/assemblyai.

How long did it last?

6h 1m, from 2025-10-22 17:56 UTC to 2025-10-22 23:58 UTC, by the times AssemblyAI posted.

What was affected?

AssemblyAI named Asynchronous API.

What caused it?

AssemblyAI hasn't published a root cause. If it does, it shows here.

Where does this come from?

AssemblyAI's official status page, https://status.assemblyai.com, quoted verbatim. down.guide's own probes, reports and social counts are labeled as ours.