Gladia - Notice history

All systems operational

API - Operational

100% - uptime
Jul 2025 · 99.97%Aug · 99.91%Sep · 99.64%

Previous page

Next page

Jul 2025
Aug 2025
Sep 2025

Pre-Recorded v2 - Operational

100% - uptime
Jul 2025 · 99.97%Aug · 99.90%Sep · 99.64%

Previous page

Next page

Jul 2025
Aug 2025
Sep 2025

Real-Time v1 - Operational

100% - uptime
Jul 2025 · 99.97%Aug · 99.91%Sep · 99.64%

Previous page

Next page

Jul 2025
Aug 2025
Sep 2025

Real-Time v2 - Operational

100% - uptime
Jul 2025 · 99.97%Aug · 99.91%Sep · 99.64%

Previous page

Next page

Jul 2025
Aug 2025
Sep 2025

App - Operational

100% - uptime
Jul 2025 · 99.97%Aug · 99.94%Sep · 100.0%

Previous page

Next page

Jul 2025
Aug 2025
Sep 2025

Notice history

Sep 2025

Pre-recorded V2 Slowdowns
  • Resolved
    Resolved
    This incident has been resolved.
  • Identified
    Identified
    We are continuing to work on a fix for this incident.
High latencies on diarization enchanced for pre-recorded
  • Resolved
    Resolved
    This incident has been resolved.
  • 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.
  • Investigating
    Investigating
    We are currently investigating this incident.
Api Down
  • Postmortem
    Postmortem

    One of our multiple providers had a global outage (https://public-cloud.status-ovhcloud.com/incidents/8cgynthz83pk) which resulted in our storage services and especially our Docker Registry service to be unusable during this time period.

    We mitigated the issue but were not able to have a fully up & running service during this outage so it had highly degraded performances during this time.

    We're getting in touch with our provider and will implement fallbacks on critical registry services in the next weeks.

  • Resolved
    Resolved
  • Monitoring
    Monitoring
    We implemented a fix and are currently monitoring the result.
  • Resolved
    Resolved
  • Update
    Update
    We are continuing to work on a fix for this incident.
  • Identified
    Identified
    We are continuing to work on a fix for this incident.
  • Monitoring
    Monitoring
    We implemented a fix and are currently monitoring the result.
  • Resolved
    Resolved
  • Monitoring
    Monitoring
    We implemented a fix and are currently monitoring the result.
  • Update
    Update
    We are currently investigating this incident.
  • Investigating
    Investigating

Aug 2025

Pre-recorded transcriptions slow-downs
  • Resolved
    Resolved
    This incident has been resolved.
  • Update
    Update
    We implemented a fix and are currently monitoring the result.
  • Monitoring
    Monitoring
    We implemented a fix and are currently monitoring the result.
Pre-recorded V2 POST Request latency
  • Postmortem
    Postmortem

    An issue with our docker registry resulted in our audio processing service to not scale accordingly, we are investigating with our provider to understand what happened and to make sure we have auto fallbacks for this part.

  • 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.
Unreachable Services
  • Postmortem
    Postmortem

    An issue with our database caused temporary latency and errors on the API between 13:27 and 15:33 UTC. The service recovered automatically after each disruption, and we have implemented mitigations to reduce the risk of recurrence. Additional improvements on storage capacity are also underway.

  • 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.
Pre-recorde transcriptions slow-downs
  • 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.
API is unreachable
  • Resolved
    Resolved
    This incident has been resolved.
  • Identified
    Identified

    We are continuing to work on a fix for this incident.

Jul 2025

Services unreachable
  • Resolved
    Resolved

    This incident has been resolved.

    One of our provider had a network issue for 10 minutes resulting in some of our services not being reachable for this time.
    We're currently in the process of a multi-region/network migration for critical services to ensure we're less affected by those kind of events.

    Target for this migration is end of Q4.

  • Monitoring
    Monitoring
    We implemented a fix and are currently monitoring the result.
  • Investigating
    Investigating
    We are currently investigating this incident.
Latencies on Enhanced Diarization (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.
Incomplete transcription results
  • Resolved
    Resolved
    This incident has been resolved.
  • Monitoring
    Monitoring
    We implemented a fix and are currently monitoring the result.
  • Identified
    Identified

    Some extra fields (e.g.subtitles) are missing from the translation result.
    We are currently investigating this incident.

Empty Enhanced Diarization
  • Resolved
    Resolved
    This incident has been resolved.
  • Investigating
    Investigating
    We are currently investigating this incident.

Jul 2025 to Sep 2025

Next