Best Practices for Conversation Relay Provider Failover

Twilio published best-practice guidance for building application-level provider failover into Voice AI agents running on Twilio Conversation Relay, which uses a third-party transcription (ASR/STT) provider and a text-to-speech (TTS) provider on every call. The guide instructs developers to always set an action URL on <Connect> and to check ErrorCode rather than only SessionStatus, because some mid-call ASR failures report SessionStatus=ended while still including an ErrorCode. It also notes that mid-call TTS failures keep the call connected and surface only as WebSocket error messages, so the developer's server must detect them and send an end message with handoffData before switching providers in the following TwiML.

Best Practices for Conversation Relay Provider Failover Time to read: Written by Reviewed by When you're scaling Voice AI agents in production using Twilio Conversation Relay https://www.twilio.com/docs/voice/conversationrelay , keeping your architecture uninterrupted is critical. That’s especially true during high-volume events like Black Friday or Cyber Monday, or sudden traffic spikes. High load or unexpected provider degradation can introduce latencies, connection drops, or request failures. To harden your Conversation Relay infrastructure against these risks, you need an application-level failover strategy. Conversation Relay https://www.twilio.com/docs/voice/twiml/connect/conversationrelay uses two speech providers on every call: a transcription ASR/STT provider that turns the caller's speech into text, and a text-to-speech TTS provider that speaks your agent's replies. Each one is a third-party service, such as Deepgram, Google, ElevenLabs, or Amazon. Sometimes, a service might be slow, unavailable, or reject a request. This guide covers: - How a provider failure reaches your application, at startup and mid-call. - Which error codes to look for. - How to return new <ConversationRelay TwiML from your action URL that fails over to a different provider, so the caller stays on the line. - How to deal with failures in the middle of a call by sending an end message with handoffData , then switching providers in the TwiML that follows. How failures reach you toc-heading-09102531-97d0-4d50-aa04-e1ef82aababd How failures reach you Where a failure shows up depends on which provider failed and when it failed: | When | Provider | What Conversation Relay does | Where you see it | |---|---|---|---| | Startup | Transcription ASR | Ends the session. | action URL : SessionStatus=failed and an ErrorCode | | Startup welcome greeting | Text-to-speech TTS | Usually ends the session. If the failure arrives just after the call connects, it's reported like a mid-call TTS failure instead next row . | action URL : SessionStatus=failed and an ErrorCode , or a WebSocket error message | | Mid-call | Transcription ASR | Ends the session. | action URL : an ErrorCode SessionStatus may be failed or ended | | Mid-call | Text-to-speech TTS | Keeps the call up. The failed reply is not spoken, and later replies are tried again. | WebSocket error message only. Your server decides whether to end the session. | Two rules follow from this table: - In your action URL handler, check ErrorCode , not only SessionStatus . Some mid-call failures report SessionStatus=ended and still include an ErrorCode . - Handle TTS failures in your WebSocket server. When the agent's voice stops working mid-call, the call stays connected and the caller hears silence. Conversation Relay won't end the call for you. Your server has to notice the error messages and send end see the Mid-call failures section , below . Prerequisites for failover toc-heading-642ff913-77f1-455d-87ff-b65efac9a814 Prerequisites for failover Before implementing custom failover logic, your Conversation Relay application should implement a few basic best practices. These fundamentals will help you build a robust production service. Always set an action URL on <Connect toc-heading-656dd77f-746f-43c1-ba75-8ffa7ab76045 Always set an action URL on <Connect Failover only works when an action URL is set on <Connect . When the Conversation Relay session ends, for any reason, Twilio sends a request to that URL, and the call carries on with the TwiML you return. Without an action URL, the call moves on to whatever verb follows <Connect in the original document, and you can't vary that by error. Name your providers explicitly toc-heading-38e90b07-9c54-44cc-bc3c-82ece9d5098f Name your providers explicitly Always set ttsProvider and transcriptionProvider , even when you're using the defaults. That way every TwiML document says exactly which provider it uses, and your failover TwiML can switch to a different one. If you leave out the TTS or transcription settings for a language, Conversation Relay fills them from a default ElevenLabs with a default voice for TTS; Google or Deepgram for transcription . That default is not something you can fail over from or to on purpose. Set ttsProvider next to voice as well, rather than letting the provider be inferred from the voice name. Track the attempt number toc-heading-112857bd-7b9d-4034-ba14-2f534088d0b6 Track the attempt number Put the attempt number, and which providers you've already tried, in the action URL query string for example ?attempt=2&tts=google . Your handler then knows where it is in the failover chain and can't end up in a loop see the Avoiding failover loops section for more . Watch your action URL parameters toc-heading-76f0cf8b-bf22-4a9d-95c2-47a6a0f3be5a Watch your action URL parameters When the session ends, Twilio sends the standard Voice call parameters https://www.twilio.com/docs/voice/api/call-resource statuscallback CallSid , AccountSid , From , To , CallStatus , and so on plus these Conversation Relay parameters: | Parameter | Present | Description | |---|---|---| | SessionId | Always | ID of the Conversation Relay session that ended. | | SessionStatus | Always | completed : the caller hung up. ended : the session was ended, normally by your end message. failed : the session ended because of an error. | | SessionDuration | Always | How long the session lasted, in seconds. | | ErrorCode | On error | Twilio error code. Branch on this. | | ErrorMessage | On error | Human-readable description. It can include the provider's own error text. Log it, but don't branch on it, because the wording can change. | | HandoffData | When you sent it | The handoffData string from your end message, passed through unchanged. | Error codes to watch toc-heading-ec4a3317-bbf1-486b-b4ea-da1b5d325c1a Error codes to watch Some error codes you’ll get back from the webhook suggest it’s time for you to fail over to another provider. This section has an overview of the types of codes you may see, plus the individual error codes. Provider failures: candidates for failover toc-heading-c53ba6c6-542d-470b-aa2d-5b8d42cbb3d0 Provider failures: candidates for failover | Code | Meaning | Typical cause | Recommended action | |---|---|---|---| | 64114 | Unable to connect to ASR provider | The transcription provider is unreachable, timed out during setup, or failed during the call. | Fail over transcription to a different transcriptionProvider . | | 64111 | TTS provider service error | The TTS provider returned a server error 5xx , timed out, or dropped the connection. This usually means a provider outage or slowdown. | Fail over TTS to a different ttsProvider . | | 64112 | TTS provider conversion error | The TTS provider rejected the request, for example because the voice ID doesn't exist, the credentials or quota are invalid, or the text or settings aren't supported. ErrorMessage or the WebSocket description includes the provider's reason. | Fail over TTS to keep the caller on the line, and check your voice and provider configuration. This error usually happens again with the same settings. Exception: if the message contains input timeout exceeded , see the 64112 section below. | | 64103 | Internal server error | Something failed inside Twilio, not at your speech provider. Provider failures are reported with 64111, 64112, and 64114 instead. | Retry once with the same providers. If the error keeps happening, contact Twilio Support with the CallSid . | | Code | Meaning | Suggested handling | |---|---|---| | 64102 | Unable to connect to WebSocket URL | Fail over to a backup WebSocket URL url= , not to a different speech provider. | | 64105 | WebSocket session ended | Your server closed the WebSocket without sending end . Send end instead see the Mid-call failures section . | | 64107 | Invalid message received | Your server sent a malformed message. Fix the server. | | 64104 | Max call duration reached | Expected behavior. No failover. | Startup failures toc-heading-34ec8bfe-a964-47bf-9659-87e2b042d820 Startup failures A startup failure means the session ended before the conversation got going. Usually the caller has heard nothing yet, or only part of the welcome greeting. Conversation Relay calls your action URL with SessionStatus=failed and an ErrorCode , and the caller stays on the line while you return new TwiML. Original TwiML primary providers toc-heading-534a1c95-0c4f-4360-9a1f-c04e83358c8d Original TwiML primary providers Transcription ASR failed at startup: ErrorCode=64114 toc-heading-a64078f5-122e-4381-857b-5f8264060b2c Transcription ASR failed at startup: ErrorCode=64114 Keep the TTS provider and switch the transcription provider: When you switch transcription providers, also change speechModel to a model the new provider supports. A Deepgram model name sent to Google, or the other way round, fails with 64106 . TTS failed at startup: ErrorCode=64111 or 64112 toc-heading-99cd4a3a-d66e-4604-9920-80c30d15b4eb TTS failed at startup: ErrorCode=64111 or 64112 Keep the transcription provider and switch the TTS provider and voice: Voices belong to a provider. When you change ttsProvider , choose a voice from the new provider's catalog. Pick your backup voice in advance, so the agent sounds as close as possible to the primary. The backup provider must also support your language . Providers don't all serve the same languages, and a backup that doesn't for example Amazon with zh-TW or he-IL is rejected with 64101 , which means your failover TwiML fails too. Test every backup voice for each language you support. The <Parameter elements are passed to your WebSocket server in the setup message under customParameters . That way your agent knows it's running on a failover session, and can, for example, keep the response style shorter or log the event. Example action URL handler toc-heading-179b1f52-3c35-4f2a-817e-0b3ff0efd2a4 Example action URL handler Here's a minimal Node.js Express handler. It picks the next provider, limits the number of attempts, and falls back to a human agent when nothing else works: Mid-call failures toc-heading-800bb1eb-adae-4608-8873-e280e4323010 Mid-call failures Sometimes, you’ll need to react to a failure in the middle of a call. The following sections detail failure modes you could run into during a live call and detail whether you should take action. Mid-call transcription failure: no additional action needed in your WebSocket server toc-heading-06b99ceb-dfc6-4b96-9088-abdb85152809 If the transcription provider fails during the call, Conversation Relay ends the session and calls your action URL with ErrorCode=64114 or 64103 if the failure was inside Twilio . Depending on where in the call the failure happened, SessionStatus may be failed or ended . Your WebSocket connection is closed. The action URL handler from the Example action URL handler section above already deals with this: it sees the ASR error code and returns TwiML with the other transcriptionProvider . To carry on the conversation instead of starting over, store your conversation state server-side keyed by CallSid and look it up again when the new session's setup message arrives. setup always includes callSid . Mid-call TTS failure: your WebSocket server must act toc-heading-71b4ec57-b0ee-42bc-bfc0-44887b5ee834 A mid-call TTS failure does not end the session . Conversation Relay sends an error message to your WebSocket server, doesn't speak that reply, and keeps the call connected. If the provider is down, every later reply fails the same way, and the caller hears silence until they hang up. The error message comes in one of two forms, depending on the provider: The first form is used by most providers, including ElevenLabs and Deepgram. The second is used by Google and Amazon voices, and it doesn't include the unspoken text. Both include the error code code: ... . When the first form also includes the text that couldn't be spoken tokens: ... , you can pass it to the new session so the caller hears the reply they missed. Recommended handling: - Read the code from description . Treat 64111 and 64112 as TTS failures, whichever form the message takes. Skip 64112 with input timeout exceeded see the Error codes to watch section . Other codes, such as 64106 for a media URL that couldn't be played, aren't provider failures. - Decide when to fail over. A single 64111 can be a one-off. Two failures in a row, or any failure during the first turn the welcome greeting , means the provider can't be relied on, so fail over. - Send an end message with handoffData that describes why you're ending and what the next session needs. handoffData must be a string , so call JSON.stringify on your object. - Conversation Relay ends the session and calls your action URL with SessionStatus=ended and HandoffData set to your string. Your handler returns TwiML that uses a different ttsProvider . The end message: Handling the handoff in your action URL toc-heading-95ba5020-cd2e-44e1-8935-a0f25a285383 Handling the handoff in your action URL The handler above already reads HandoffData . When reasonCode is tts-failure , it moves on to the next TTS provider. It also passes conversationId through a <Parameter , so the new session's setup message resumes the same conversation. Here's the TwiML for a mid-call TTS handoff that also replays the unspoken text: Putting unspokenText in welcomeGreeting means the caller hears the reply that failed. If you'd rather not, use a short "where were we?" greeting, or leave welcomeGreeting out and have your agent speak first once setup arrives. Ending the call for other mid-call reasons toc-heading-7a1f26e9-d3b8-42f4-ab80-b49119fbb881 Ending the call for other mid-call reasons You can use the same end plus handoffData pattern for any mid-call problem your server detects, for example when your LLM provider is down, a tool call keeps failing, or the caller asks for a person. Set a different reasonCode llm-failure , live-agent , ... and branch on it in your action URL handler. Always prefer end to closing the WebSocket. If you close the WebSocket, the session fails with 64105 and you lose the HandoffData . Avoiding failover loops toc-heading-8c9b0476-3a4c-4ad5-96be-d6bf2fd856da Avoiding failover loops When you add failovers to your Conversation Relay app, you need to be careful that you don’t accidentally create a loop which cycles through fallback providers and never exits. This list contains our best practices for avoiding a failover loop. - Limit the number of attempts. Carry attempt in the action URL and stop after 2 or 3. - Change something on every attempt. Only retry identical TwiML for 64103, and only once. - Don't fail over on configuration errors 64101, 64106 . They fail the same way on every attempt. - Always have a final fallback that doesn't use Conversation Relay , such as <Say with a <Dial to a human agent, <Enqueue , <Record for voicemail, or a polite <Hangup . <Say uses Twilio's own TTS, so it doesn't depend on the provider that just failed. - Return <Response/ when SessionStatus=completed , because the caller has already hung up. Checklist toc-heading-a9a9b9d3-bef2-4afc-ab85-5c60ff7cdaf9 Checklist Looking for a cheatsheet on how to handle failovers in your production Conversation Relay app? This list contains a succinct version of our advice from this post, so you can check that your app is handling possible failure cases. - ☐ Every <Connect has an action URL that carries attempt and the current providers. - ☐ ttsProvider , voice , transcriptionProvider , and speechModel are set explicitly. - ☐ A backup voice and a backup speech model are chosen and tested for each language you support. A backup that doesn't serve the language fails with 64101. - ☐ The action URL handler branches on ErrorCode not only SessionStatus and parses HandoffData . - ☐ 64114 fails over transcription. 64111 and 64112 fail over TTS. 64103 retries once. 64101 and 64106 go to the fallback and get alerted on. - ☐ Your WebSocket server watches for error messages with 64111 or 64112 in both message forms and sends end with handoffData . - ☐ Conversation state is stored server-side and resumed through <Parameter name="conversationId" . - ☐ The final fallback doesn't depend on Conversation Relay. - ☐ ErrorCode , ErrorMessage , and CallSid are logged for every failover, so you can follow up with Twilio Support. Conclusion toc-heading-afc42966-100c-4053-92f8-cf71e3b18996 Conclusion By implementing these failover strategies, your Conversation Relay Voice AI agents will be more resilient against speech provider outages, traffic surges, and transient degradations. Building a multi-provider fallback strategy helps ensure continuous, high-availability conversation flow – whether you’re dealing with high-volume events like Black Friday, or traffic on a random weeknight. With these best practices in place, your voice infrastructure can be hardened for enterprise scale. We can’t wait to see – and hear – what you build Suggested resources toc-heading-acb5c7b4-602b-4b81-ad5a-f16644dce764 Suggested resources - Twilio Conversation Relay Overview & Documentation https://www.twilio.com/docs/voice/conversationrelay - ConversationRelay TwiML Noun Reference https://www.twilio.com/docs/voice/twiml/connect/conversationrelay - Twilio Voice Call Resource & Status Callback Parameters https://www.twilio.com/docs/voice/api/call-resource statuscallback Daniel Jansson is a Tech Lead at Twilio, where they have worked since 2017 and helped create Conversation Relay. They spend a lot of their time making voice AI calls keep working when the speech-to-text or text-to-speech provider on the other end doesn't. They can be reached at djansson at twilio.com https://twilio.com . Related Posts Related Resources Twilio Docs From APIs to SDKs to sample apps API reference documentation, SDKs, helper libraries, quickstarts, and tutorials for your language and platform. Resource Center The latest ebooks, industry reports, and webinars Learn from customer engagement experts to improve your own communication. Ahoy Twilio's developer community hub Best practices, code samples, and inspiration to build communications and digital engagement experiences.