Vapi is the Voice AI platform for developers.

Vapi AI

The assistant suddenly stopped speaking, and the call ended.
 
An error occurred in this call: pipeline-error-eleven-labs-500-server-error
callId: 0383fb6c-753c-42f4-8f24-2213de5ca510

**Your call ended due to a voice provider failure (`pipeline-error-eleven-labs-500-server-error`).**  
To prevent this in the future, configure a voice fallback plan so your assistant can switch to a backup voice if the primary provider fails. Here’s an example of how to set this up via the API:

```json
{
  "voice": {
    "provider": "elevenlabs",
    "voiceId": "your-primary-voice-id",
    "fallbackPlan": {
      "voices": [
        { "provider": "openai", "voiceId": "shimmer" },
        { "provider": "playht", "voiceId": "jennifer" }
      ]
    }
  }
}
```
*This ensures your calls continue even if Eleven Labs has an outage.*  
[Learn more in the Voice Fallback Plan docs.](https://docs.vapi.ai/voice-fallback-plan)

Sources:
- [Voice Fallback Plan](https://docs.vapi.ai/voice-fallback-plan)
- [Call Ended Reasons](https://docs.vapi.ai/calls/call-ended-reason)

Same issue.. it would perhaps help to raise this as a critical thing to Vapi team by submitting outage notice in <#1293690685781839933>

🔵 08:40:17:742 ElevenLabs (WebSocket #7) Error: {   "message": "We are sorry, something went wrong. You are not charged for this request.",   "error": "something_went_wrong",   "code": 1011 }.

Hey David,

This is from the 11Labs side. When they experience a significant surge in requests, some text-to-speech requests are returned to them, and there was no fallback plan in place.

This situation resulted in the 11Labs fault error. Please let me know if this issue occurs frequently for you. If so, please share more call IDs, and I will report it to the 11Labs team.