Gladia - Notice history

All systems operational

API - Operational

100% - uptime
Jan 2025 · 99.98%Feb · 100.0%Mar · 100.0%

Previous page

Next page

Jan 2025
Feb 2025
Mar 2025

Pre-Recorded v2 - Operational

99% - uptime
Jan 2025 · 99.89%Feb · 99.54%Mar · 98.62%

Previous page

Next page

Jan 2025
Feb 2025
Mar 2025

Real-Time v1 - Operational

100% - uptime
Jan 2025 · 99.96%Feb · 99.98%Mar · 99.98%

Previous page

Next page

Jan 2025
Feb 2025
Mar 2025

Real-Time v2 - Operational

99% - uptime
Jan 2025 · 98.57%Feb · 99.97%Mar · 99.83%

Previous page

Next page

Jan 2025
Feb 2025
Mar 2025

App - Operational

100% - uptime
Jan 2025 · 100.0%Feb · 100.0%Mar · 100.0%

Previous page

Next page

Jan 2025
Feb 2025
Mar 2025

Addons - Operational

100% - uptime
Jan 2025 · 100.0%Feb · 100.0%Mar · 98.73%

Previous page

Next page

Jan 2025
Feb 2025
Mar 2025

Notice history

Mar 2025

API (status page) is down
  • Resolved
    Resolved
  • Identified
    Identified
    We are continuing to work on a fix for this incident.
  • Investigating
    Investigating
slow down in callback due to cloud provider issues
  • Resolved
    Resolved

    OVHcloud had a major outage regarding their object storage leading to callback issues on gladia:
    https://public-cloud.status-ovhcloud.com/incidents/9myc4g6tfvlb
    This incident has been resolved.

    We are working to have fallback strategy for future similar events.

Latencies on Pre-Recorded v2
  • Resolved
    Resolved
    This incident has been resolved.
  • Monitoring
    Monitoring
    We implemented a fix and are currently monitoring the result.

Feb 2025

Latencies on Pre-Recorded v2
  • Resolved
    Resolved
    This incident has been resolved.
  • Monitoring
    Monitoring
    We implemented a fix and are currently monitoring the result.
  • Investigating
    Investigating
    We are currently investigating this incident.
  • Monitoring
    Monitoring
    We implemented a fix and are currently monitoring the result.
  • Investigating
    Investigating
    We are currently investigating this incident.
API Service is down
  • Resolved
    Resolved
  • Identified
    Identified

    Problem has been identified and a fix is being rolled out

  • Investigating
    Investigating
Pre-Recorded v2 (status page) is down
  • Resolved
    Resolved
  • Identified
    Identified

    Issue has been identified and we are deploying a fix.

  • Investigating
    Investigating
Pre-recorded V2 Slowdowns
  • Resolved
    Resolved

    This incident has been resolved.

    The issue was introduced by another fix resulting in some GPUs to be slightly overloaded when certain languages were used, resulting in diarization to be way slower than usual.

  • Investigating
    Investigating
    We are currently investigating this incident.

Jan 2025

API unreachable
  • Resolved
    Resolved

    This incident has been resolved.

    We had a query that locked our database resulting in our API marked as unavailable resulting in 503 errors for few minutes.
    We found the faulty query and making sure this does not happen again.

    Thanks for your understanding.

  • Monitoring
    Monitoring

    The issue have been fix and we're currently monitoring.

  • Identified
    Identified
    We are continuing to work on a fix for this incident.
Real-time V2 slowdowns
  • Resolved
    Resolved
    This incident has been resolved.
  • Monitoring
    Monitoring
    We implemented a fix and are currently monitoring the result.
  • Investigating
    Investigating
    We are currently investigating this incident.
Real-Time V2 API outage
  • Update
    Update

    Starting around 17:40 UTC+1, our GPU instances became unavailable following a controller migration. The issue was immediately identified and we began restarting the affected components. Due to the time required to relaunch the infrastructure, the process took approximately 30 minutes to complete. By 18:15 UTC+1, all services were back online.

  • Resolved
    Resolved

    This incident has been resolved.

    We'll update with a post-mortem soon.

  • Identified
    Identified

    The Real-time V2 API is currently unavailable. We have identified the issue and are actively working on a resolution. Deployment is expected to take at least 30 minutes.

Real-Time V2 slight increase in latency
  • Resolved
    Resolved

    This incident has been resolved.

    Some transcription servers were prevented from starting because of a disk storage issue.

  • Monitoring
    Monitoring
    We implemented a fix and are currently monitoring the result.
  • Identified
    Identified
    We are continuing to work on a fix for this incident.
API is unreachable via Recall.ai
  • Resolved
    Resolved

    Starting at around 15:30 UTC+1, all requests coming from Recall.ai began failing. The issue was traced to a specific edge case involving file uploads where a filename is not provided by the client, requiring our system to generate one. While most HTTP clients and browsers include a filename by default—making the issue rare—Recall.ai’s integration did not, triggering the problem.

    This behavior was caused by a recent change deployed at 15:00 UTC+1 to support JSON-formatted logs. As part of that change, the request ID, which is used to generate a filename in the absence of one, was no longer accessible. This resulted in 400 Bad Request errors for affected uploads.

    The issue was identified at 15:30 UTC+1. A fix was reviewed by 16:30 UTC+1 and deployed by 17:00 UTC+1, resolving the problem.

    We are updating our test coverage to include this specific edge case to prevent similar incidents in the future.

  • Monitoring
    Monitoring

    A fix has been deployed. Upload are working again. We are monitoring the situation.

  • Investigating
    Investigating

    Gladia API is currently unavailable via Recall.ai. We reached out to their team to find a solution.

Jan 2025 to Mar 2025

Next