Model provider failures ongoing across Cartesia, Deepgram and Elevenlabs

Resolved

Started

Lasted 3h 20m

View official incident ↗

Updates

  1. Resolved

    Model issues appear to be resolved according to each provider and latency monitoring internally.

  2. Unknown

    Per ElevenLabs, systems are now operational across all products. We are still monitoring Deepgram status for full recovery.

  3. Unknown

    ElevenLabs latency is back to normal levels and we’re seeing a reduction in error rates. ElevenLabs is currently still monitoring to confirm resolution.

  4. Unknown

    Deepgram updated status that a fix has been implemented and is monitoring results.

  5. Unknown

    We are seeing improvement for Cartesia voices. Deepgram and ElevenLabs issues are still ongoing.

  6. Unknown

    See status pages for Deepgram and Elevenlabs for updates. https://status.elevenlabs.io/united-states/incidents/01M7QMQH05JXV3SKSM1H6PJZD2 https://status.deepgram.com/ Potential get out of trouble alternatives: Voice: Use Vapi V2 voices (such as Elliot or Clara), xAI, or MiniMax. ElevenLabs pronunciation dictionaries do not carry over and should not be added back after switching else, voice will default back to ElevenLabs. Transcriber: use AssemblyAI or Soniox for English, or Soniox for multilingual. If you have HIPAA or other data handling requirements, we recommend Cartesia or xAI voices.