Retell AI Outage History
Retell AI is up right nowPingoru has recorded 51 incidents for Retell AI: 28 in the last 12 months and 4 in the last 90 days.
Show as a table
| Month | Incidents | Hours with an open incident |
|---|---|---|
| April 2026 | 1 | 1 of 720 (0%) |
| May 2026 | 4 | 4 of 744 (0%) |
| June 2026 | 3 | 13 of 720 (2%) |
| July 2026 | 3 | 4 of 744 (0%) |
| August 2026 | 1 | 0 of 744 (0%) |
| September 2026 | 2 | 2 of 720 (0%) |
| October 2026 | 0 | 0 of 592 (0%) |
Incidents, newest first
Notice December 10, 2025 Transcription error for non English traffic 20m
Started Dec 10, 2025, 07:30 PM UTC· resolved Dec 10, 2025, 07:50 PM UTC
- resolved Dec 10, 2025, 08:41 PM UTC
For around 20 minutes, there was a spike of transcription error for certain non English traffic (notably multilingual, Spanish, etc). English traffic was not impacted. This has been identified as outages from underlying providers. We are working on adding more fallback routes to improve the stability of the platform.
Minor November 26, 2025 Telnyx calls encountering telephony provider permission denied 3m Phone Call
Started Nov 26, 2025, 06:48 PM UTC· resolved Nov 26, 2025, 06:52 PM UTC
- investigating Nov 26, 2025, 06:48 PM UTC
We have observed that calls through retell Telnyx numbers are having issues.
- resolved Nov 26, 2025, 06:52 PM UTC
This has been resolved now. This is related to an elastic IP issue, which is mitigated now.
Notice October 28, 2025 Intermittent Call Connection Failures 24m Phone Call
Started Oct 28, 2025, 07:10 PM UTC· resolved Oct 28, 2025, 07:34 PM UTC
- resolved Oct 28, 2025, 07:28 PM UTC
From 11:10 AM – 11:34 AM PST, we observed that inbound calls were experiencing connection issues and timeouts. We have identified the issue as being caused by a brief outage with our telephony provider. The issue has since been resolved and all services are operating normally.
Minor October 20, 2025 AWS outage causing some login issues, and history and analytics issue. Calls are NOT impacted. 5h 40m Dashboard
Started Oct 20, 2025, 07:02 PM UTC· resolved Oct 21, 2025, 12:42 AM UTC
- identified Oct 20, 2025, 07:02 PM UTC
Starting from Oct 20 1am PST, the AWS outage has caused some login issues, and call history and analytics issues. Regular calls are NOT impacted. Once the AWS outage is over, we will backfill the analytics.
- monitoring Oct 20, 2025, 11:51 PM UTC
The AWS outage has been resolved. We are going to backfill analytics, and keep a close eye on it.
- resolved Oct 21, 2025, 12:42 AM UTC
This incident has been resolved.
Notice October 9, 2025 Connection issues with calls 33m Web Call, Phone Call
Started Oct 09, 2025, 09:14 PM UTC· resolved Oct 09, 2025, 09:47 PM UTC
- resolved Oct 09, 2025, 09:40 PM UTC
From 1:14pm - 1:47PM PST, we observed that some calls were running into connection issues, and experience timeouts on operations. We identified the issue to be AWS blocking the auto scaling of the instances, causing our call servers got overloaded for a while. We have been working with AWS team on identifying the root cause to ensure this gets fixed. This issue has been resolved now.
Notice October 2, 2025 7% calls got abnormally high latency –
Started Oct 02, 2025, 01:30 PM UTC· resolved Oct 02, 2025, 01:30 PM UTC
- resolved Oct 02, 2025, 08:27 PM UTC
Incident range: 6:30am - 11am PST impact: around 7% of the calls are having abnormally high latency post mortem: Some AWS automatic patches to our transcription clusters caused the container to lost GPU access, and used CPU for transcription, causing extra long latency there. Most calls are routed to the backup endpoint which was working fine, but around 7% did not trigger the fallback there. We are updating the containers to ensure it does not get impacted with the automatic patches.
Minor August 26, 2025 Temporary Outbound Call Issue 1h 30m
Started Aug 26, 2025, 03:00 PM UTC· resolved Aug 26, 2025, 04:30 PM UTC
- resolved Aug 26, 2025, 05:26 PM UTC
We experienced a temporary disruption where some outbound calls did not connect as expected. This was due to a telephony sip server provider issue related to elevated system load. The issue was transient and lasted from 8:00 AM to 9:30 AM PDT. The SIP server provider implemented a fix, and inbound calls have been operating normally since. We are going to roll out locally hosted SIP stack to boost reliability going onwards.
Notice August 25, 2025 Concurrency values were not resetting as expected. –
Started Aug 25, 2025, 07:15 PM UTC· resolved Aug 25, 2025, 07:15 PM UTC
- resolved Aug 25, 2025, 07:15 PM UTC
Starting from 10:25am to 11:23am, for some customers concurrency was not resetting correctly, causing some calls to fail to connect. We are mitigating the issue by manually resetting concurrency, so the dashboard may not reflect the actual current value. We identified the root cause to be a case where audio file manipulation led to a full disk usage under a corner case scenario, and a fix is deployed.
Notice August 8, 2025 Single / multi prompt agent function parameter empty 26m
Started Aug 08, 2025, 04:40 AM UTC· resolved Aug 08, 2025, 05:07 AM UTC
- identified Aug 08, 2025, 04:40 AM UTC
19:42: there start to be reports on single / multi prompt agents having issues with function parameter being empty. 21:25: issue was identified and a hotfix is being rolled out. We are keep monitoring the issue.
- resolved Aug 08, 2025, 05:07 AM UTC
This incident has been resolved.
Notice July 24, 2025 Voice agent switching voices during call 1h 58m
Started Jul 24, 2025, 03:15 PM UTC· resolved Jul 24, 2025, 05:14 PM UTC
- monitoring Jul 24, 2025, 03:15 PM UTC
Starting from around 6:30am, elevenlabs TTS is having a full scale outage: https://status.elevenlabs.io/incidents/01K0YAV1N4W7EZW1BMQCQJ4YJR Our platform traffic starts to fallback to other providers, and the volume of traffic started to break other TTS providers, and that's why you might have seen voice switching mid call, increased latency or even total silence. We're working with other TTS providers to bring in more capacity to support the fallback, and is monitoring closely on elevenlab's outage updates. Currently the error rate has returned back to normal. We will be actively following up on this.
- resolved Jul 24, 2025, 05:14 PM UTC
This incident has been resolved.
Notice July 14, 2025 Phone call not connecting 42m Phone Call
Started Jul 14, 2025, 10:20 PM UTC· resolved Jul 14, 2025, 11:03 PM UTC
- investigating Jul 14, 2025, 10:20 PM UTC
Our telephony SIP provider confirmed there's an ongoing outage that led to phone call not connecting. We are escalating now, and is trying potential workarounds.
- identified Jul 14, 2025, 10:23 PM UTC
Telephony provider confirmed that this is related to an outage with Cloudflare DNS, which they use in certain internal components. A change is being applied to mitigate. related incident: https://www.cloudflarestatus.com/incidents/28r0vbbxsh8f
- identified Jul 14, 2025, 10:25 PM UTC
We are continuing to work on a fix for this issue.
- monitoring Jul 14, 2025, 10:28 PM UTC
The fix has been applied and phone calls are back to normal at the moment, we are keep monitoring.
- monitoring Jul 14, 2025, 10:28 PM UTC
We are continuing to monitor for any further issues.
- resolved Jul 14, 2025, 11:03 PM UTC
This incident has been resolved.
Notice July 14, 2025 Conversation Flow agent potentially stay silent after function node –
Started Jul 14, 2025, 10:00 AM UTC· resolved Jul 14, 2025, 10:00 AM UTC
- resolved Jul 14, 2025, 03:38 PM UTC
3am: a culprit release was deployed, leading to some of the conversation flow agents stay silent after a function. It happens when a function and response is happening at same time, and is due to a message order issue before feeding to LLM. 8am: a fix is being deployed 8:30am: fix is fully deployed
Major June 25, 2025 User Sign-Up and Workspace Creation Failure 2h 52m Dashboard
Started Jun 25, 2025, 11:11 PM UTC· resolved Jun 26, 2025, 02:03 AM UTC
- identified Jun 25, 2025, 11:11 PM UTC
Users are currently unable to sign up or create new workspaces on our platform. This issue stems from reaching the organization creation limit in Auth0, which is blocking new account provisioning. We are actively working with Auth0 to increase the limit
- identified Jun 26, 2025, 02:02 AM UTC
We are continuing to work on a fix for this issue.
- resolved Jun 26, 2025, 02:03 AM UTC
The issue has been resolved, and new users can now sign up. Users who encountered sign-up issues today can proceed and log into the system without any problems.
Notice June 21, 2025 Agent not responding to users when interruption setting it low –
Started Jun 21, 2025, 04:30 PM UTC· resolved Jun 21, 2025, 04:30 PM UTC
- resolved Jun 21, 2025, 06:52 PM UTC
9:30am: Incident started, where agents are not proactively responding to users when it has a low interruption setting. The behavior seen can include - Custom LLM not requesting responses - Retell agents not responding to user response 10:48am: A fix is being pushed, we start to see the issue get mitigated. 11:50am: Fix fully rolled out.
Notice June 19, 2025 Transfer Phone Number and Custom Tool Issues – Phone Call
Started Jun 19, 2025, 02:09 AM UTC· resolved Jun 19, 2025, 02:09 AM UTC
- resolved Jun 19, 2025, 02:09 AM UTC
We have identified and fixed issues affecting transfer phone number with static number and missing call objects in custom tool invocations. Both issues have been fully resolved after 1 hour and 20 minutes of downtime.
Minor June 13, 2025 Telnyx inbound calls choppy 3h 59m Phone Call
Started Jun 13, 2025, 05:15 PM UTC· resolved Jun 13, 2025, 09:15 PM UTC
- investigating Jun 13, 2025, 05:15 PM UTC
We have identified that starting from 9:30am PDT, all Telnyx inbound calls are very choppy. With the current investigation, it indicates that this is a telephony issue, and we have escalated to our telephony carriers and partners, awaiting their response and fix. Telnyx outbound is working normally. Twilio inbound and outbound is working normally. If you are using Telnyx inbound, we recommend you to switch to a Twilio number in the meantime while the Telnyx and other telephony partners address this issue.
- monitoring Jun 13, 2025, 07:51 PM UTC
The choppy issue seems resolved. We will keep monitoring and will help telephony partners find the root cause to help them prevent this from happening again.
- resolved Jun 13, 2025, 09:15 PM UTC
This incident has been resolved.
Minor June 9, 2025 Concurrency not cleared up 21m Web Call, Phone Call
Started Jun 09, 2025, 10:52 PM UTC· resolved Jun 09, 2025, 11:14 PM UTC
- identified Jun 09, 2025, 10:52 PM UTC
3:15pm PDT: There starts to have a resource initialization problem with single prompt agents, causing the concurrency counter to pile up and not get cleared, and caused subsequent calls to get rejected 3:30pm PDT: a fix is starting to get rolled out, and we are resetting concurrency counters for everyone to unblock the calls in the meantime.
- resolved Jun 09, 2025, 11:14 PM UTC
4:12pm: The fix has been deployed, and we've cleared the concurrency counter again to remove all the effects from the issue.
Major May 22, 2025 Inbound and Web call not connecting 16m Web Call, Phone Call
Started May 22, 2025, 04:34 AM UTC· resolved May 22, 2025, 04:51 AM UTC
- identified May 22, 2025, 04:34 AM UTC
The issue is identified and is being mitigated. A fix is rolling out.
- resolved May 22, 2025, 04:51 AM UTC
This incident has been resolved.
Minor May 20, 2025 Call Transfer Failures 1h 13m Phone Call
Started May 20, 2025, 12:33 AM UTC· resolved May 20, 2025, 01:47 AM UTC
- monitoring May 20, 2025, 12:33 AM UTC
Due to a technical issue, some calls experienced failures when performing cold transfers with agent numbers or warm transfers. This led to unexpected call drop-offs during transfer attempts. A fix is currently being deployed to resolve the issue. Impact window: May 19, 1:44 PM PDT – ongoing
- resolved May 20, 2025, 01:47 AM UTC
This incident has been resolved. We are working internally to add more test cases to prevent this from happening.
Notice May 18, 2025 Call Recordings Lost –
Started May 18, 2025, 09:00 PM UTC· resolved May 18, 2025, 09:00 PM UTC
- resolved May 18, 2025, 11:06 PM UTC
Due to a technical issue, the recordings for calls initiated between 2:04 PM and 3:00 PM were lost. All other functionalities — including the calls themselves, transcripts, and logs — were fully unaffected.
Major May 15, 2025 Telnyx Inbound Calling Down 1h 16m Phone Call
Started May 15, 2025, 11:53 PM UTC· resolved May 16, 2025, 01:10 AM UTC
- investigating May 15, 2025, 11:53 PM UTC
Telnyx Inbound Calling is down We are currently investigating an issue with Telnyx where inbound UDP packets appear to be dropped intermittently, resulting in call failures. Our team is actively working with Telnyx to escalate and resolve the issue. Update: Inbound traffic has returned to normal.
- resolved May 16, 2025, 01:10 AM UTC
This incident has been resolved.
Minor May 8, 2025 Calls with background speech denoising not connecting 4h 30m Web Call, Phone Call
Started May 08, 2025, 11:22 PM UTC· resolved May 09, 2025, 03:53 AM UTC
- identified May 08, 2025, 11:22 PM UTC
2am: some calls have not been connected when background speech denoising is enabled 10am: rolled out some fixes which resolved the issue. 3:30pm: received some new reports that calls are not connected. Currently investigating, seems to be related to the network settings of new clusters provisioned for that feature. We are currently rolling out a fix that temporarily disables the feature and direct the traffic to backup clusters in the meantime of fixing that new cluster.
- monitoring May 09, 2025, 12:14 AM UTC
We've identified the issue with the subnet configuration, and a fix has been applied, and traffic should be back to normal now. We are keeping a close eye now on the issue. The feature is turned back on now.
- resolved May 09, 2025, 03:53 AM UTC
This incident has been resolved.
Minor April 24, 2025 Multilingual is currently downgraded 7h 45m Web Call, Phone Call
Started Apr 24, 2025, 09:50 AM UTC· resolved Apr 24, 2025, 05:36 PM UTC
- investigating Apr 24, 2025, 09:50 AM UTC
Please switch to English or a specific language for now—we’re investigating the issue.
- investigating Apr 24, 2025, 09:51 AM UTC
We are continuing to investigate this issue.
- monitoring Apr 24, 2025, 04:21 PM UTC
A fix is being patched.
- resolved Apr 24, 2025, 05:36 PM UTC
This incident has been resolved.
Major April 23, 2025 Retell LLM API incident –
Started Apr 23, 2025, 06:30 PM UTC· resolved Apr 23, 2025, 06:30 PM UTC
- resolved Apr 23, 2025, 09:09 PM UTC
LLM API returned 200 errors on certain valid inputs. This incident has been resolved.
Minor March 31, 2025 Retell Telnyx Outage 1h 30m
Started Mar 31, 2025, 03:00 PM UTC· resolved Mar 31, 2025, 04:30 PM UTC
- resolved Apr 01, 2025, 05:13 PM UTC
Telnyx temporarily banned our account at 8:15 AM PDT 03/31/2025 due to a scammer being reported on the platform, which triggered a traceback event. We’ve implemented KYC measures along with several detection protocols, and have reported all remediation steps to Telnyx. The ban has since been lifted on 9.30 AM. We’ll continue to monitor the situation closely.