Hume AI

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. identified 2026-10-12 17:16 UTC

   Our documentation pages are down because one of our providers, Fern, is having an outage.

2. resolved 2026-10-12 18:00 UTC

   Issue upstream appears to be fixed.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: A code release introduced the failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-09-19 02:10 UTC

   TTS is currently down. We have identified the issue and working on a fix.

2. investigating 2026-09-19 02:15 UTC

   TTS is back up. An underlying deployment issue prevented this service from starting correctly. The issue has been resolved.

3. resolved 2026-09-19 02:16 UTC

   The issue has been resolved.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. identified 2026-07-24 13:29 UTC

   We're seeing increase error rates on EVI. We're investigating.

2. monitoring 2026-07-24 16:08 UTC

   Seeing chats recover. Monitoring over the next few hours

3. resolved 2026-07-27 21:54 UTC

   Issue was resolved.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: Not enough capacity for the load. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-07-11 10:47 UTC

   EVI appears to be down in a majority of cases, and TTS also appears impacted.

2. resolved 2026-07-11 17:14 UTC

   Issue seems to be resolved. We mitigated the issue by increasing capacity and adjusting timeout/retry handling to improve reliability under load. Service health was confirmed once automated checks and live sessions were consistently succeeding.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2026-06-08 22:05 UTC

   A third-party integration experienced issues, leading to failures and timeouts in our APIs.

2. resolved 2026-06-08 23:09 UTC

   We worked with the third-party provider to resolve the integration issue, restoring API availability.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. identified 2026-06-08 22:40 UTC

   We identified an issue with a third-party integration and are actively working with them to remedy the issue.

2. resolved 2026-06-08 23:09 UTC

   Integration issue has been fixed.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2026-02-15 23:26 UTC

   Seeing high error rates on TTS and EVI, seemingly due to an upstream inference provider. We are actively investigating.

2. monitoring 2026-02-15 23:53 UTC

   Service has fully recovered. The engineering team is continuing to monitor.

3. resolved 2026-02-15 23:56 UTC

   Issue was resolved

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: A bug in the vendor's own code. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. identified 2026-02-11 21:05 UTC

   Certain voices are requiring data to be backfilled, which is causing excessive load on the system. A fix is currently in the works.

2. monitoring 2026-02-12 18:22 UTC

   A fix has been deployed. We're monitoring to make sure it's working as intended.

3. resolved 2026-02-12 21:31 UTC

   Everything is operating normally again. Monitoring will continue throughout the day.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-02-09 02:17 UTC

   Multilingual transcription for EVI is currently down. Root cause is being investigated.

2. resolved 2026-02-09 19:21 UTC

   Multilingual transcription has been re-enabled. Service fully restored.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: Login, tokens, certificates or credentials failed. Root cause: A human mistake during operations. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-02-08 19:41 UTC

   Our Speech-To-Speech API is currently experiencing timeouts, resulting in failed calls. Other services appear to be unaffected.

2. resolved 2026-02-08 21:10 UTC

   An API key had expired and has been rotated. EVI appears functional again.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2026-01-28 16:00 UTC

   Due to an upstream inference provider we're seeing some failed requests on EVI and TTS.

2. resolved 2026-01-28 16:27 UTC

   Issue was resolved.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-11-25 14:59 UTC

   Degraded performance for TTS-related products

2. resolved 2025-11-25 16:47 UTC

   Issue was resolved

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. identified 2025-11-18 11:32 UTC

   Service outage for web applications identified

2. resolved 2025-11-18 14:39 UTC

   Issue was resolved

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: Cloudflare.

1. investigating 2025-11-18 12:10 UTC

   Most if not all Hume services are down currently due to a Cloudflare outage.

2. resolved 2025-11-18 12:21 UTC

   Cloudflare back up and Hume services are back up

3. monitoring 2025-11-18 15:12 UTC

   APIs down due to Cloudflare outage.

4. resolved 2025-11-18 21:59 UTC

   Services back up with cloudflare outage resolution.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. identified 2025-11-08 20:28 UTC

   Internal issue found which caused requests to TTS to fail.

2. resolved 2025-11-08 20:36 UTC

   Internal issue was fixed.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. identified 2025-11-06 20:30 UTC

   Timeout issue in model inference causing degraded performance.

2. identified 2025-11-06 20:32 UTC

   Issue has been identified and currently being worked on.

3. monitoring 2025-11-06 21:26 UTC

   Monitoring the latency issue.

4. resolved 2025-11-06 21:43 UTC

   Issue has been resolved.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. monitoring 2025-11-05 04:52 UTC

   EVI and Octave services were timing out connecting to models from approximately 11 - 11:35pm EST. Issue seems resolved now, and team is monitoring

2. resolved 2025-11-05 05:06 UTC

   Latencies have returned to their normal levels and APIs operating normally.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. resolved 2025-10-24 21:51 UTC

   Issue was resolved.

2. investigating 2025-10-24 21:51 UTC

   Discovered an issue related to our payments service for users that have organizations enabled.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: AWS.

1. resolved 2025-10-20 08:20 UTC

   Application website was down as some services were impacted by a global AWS outage.

2. resolved 2025-10-23 16:03 UTC

   Issue was resolved

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: AWS.

1. investigating 2025-10-20 22:00 UTC

   TTS API currently impacted due to the AWS outage: https://health.aws.amazon.com/health/status We are working on bringing services back up.

2. monitoring 2025-10-20 22:54 UTC

   Actively monitored

3. monitoring 2025-10-20 23:51 UTC

   Issue resolved.

4. resolved 2025-10-21 00:20 UTC

   This has been resolved and Octave is operational.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: A code release introduced the failure. Root cause: A bug in the vendor's own code. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-10-10 15:15 UTC

   We are investigating transient failures on the TTS service

2. resolved 2025-10-10 15:30 UTC

   The team identified the issue related to audio decoding from the Octave model and has deployed a fix.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-10-09 17:52 UTC

   We're actively investigating an outage affecting both EVI and Octave

2. resolved 2025-10-09 20:15 UTC

   High load on the service caused high queue times and failures for both EVI and Octave models. This has been resolved and the team is monitoring the fix.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2025-10-07 01:10 UTC

   An outage with a downstream provider is impacting Octave and EVI.

2. resolved 2025-10-07 01:33 UTC

   EVI and Octave are operational.

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-09-30 04:26 UTC

   We're seeing increased error rates on Voice Cloning

2. resolved 2025-09-30 04:51 UTC

   False Alarm: no downtime

Excerpts are shortened. Read the full incident on Hume AI's status page.

Failure mode: Traffic surge or denial-of-service attack. Root cause: Not enough capacity for the load. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. identified 2025-09-26 01:07 UTC

   Long wait times on expression measurement due to load.

2. resolved 2025-09-26 09:08 UTC

   Issue was resolved.

Excerpts are shortened. Read the full incident on Hume AI's status page.