# Agent says transitions calls aloud and speaks Chinese instead of transitioning **URL:** \ **Category:** Support Help\ **Tags:** bug\ **Created:** [June 1, 2026, 3:43pm UTC](https://community.retellai.com/t/agent-says-transitions-calls-aloud-and-speaks-chinese-instead-of-transitioning/2956 "2026-06-01T15:43:46Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![rodrigo.christiansen](https://yyz2.discourse-cdn.com/flex008/user_avatar/community.retellai.com/rodrigo.christiansen/32/1731_2.png) [@rodrigo.christiansen](https://community.retellai.com/u/rodrigo.christiansen)\ **Post date:** [June 1, 2026, 3:43pm UTC](https://community.retellai.com/t/agent-says-transitions-calls-aloud-and-speaks-chinese-instead-of-transitioning/2956/1 "2026-06-01T15:43:46Z")
Instead of transitioning to the appropriate node, the agent will say aloud things like these: - {“tool\_uses”:[{“recipient\_name”:“functions.transition\_to\_gather\_info”,“parameters”:{}}]} - functions.transition\_to\_gather\_info 大发彩票快三commentary to=functions.transition\_to\_gather\_info 天天送彩票json{} 大发彩票网 We have experienced the error with GPT 5.4. ---
**Author:** ![discourse\_ai\_spam](https://avatars.discourse-cdn.com/v4/letter/d/c68b51/32.png) [@discourse\_ai\_spam](https://community.retellai.com/u/discourse_ai_spam)\ **Post date:** [June 1, 2026, 3:43pm UTC](https://community.retellai.com/t/agent-says-transitions-calls-aloud-and-speaks-chinese-instead-of-transitioning/2956/2 "2026-06-01T15:43:48Z")
---
**Author:** ![system](https://canada1.discourse-cdn.com/flex008/uploads/retell1/original/2X/a/a06e2942efdc48016940732a05d1274957507ee3.png) [@system](https://community.retellai.com/u/system)\ **Post date:** [June 1, 2026, 3:50pm UTC](https://community.retellai.com/t/agent-says-transitions-calls-aloud-and-speaks-chinese-instead-of-transitioning/2956/3 "2026-06-01T15:50:07Z")
---
**Author:** ![Shah-Fazal](https://yyz2.discourse-cdn.com/flex008/user_avatar/community.retellai.com/shah-fazal/32/2522_2.png) [@Shah-Fazal](https://community.retellai.com/u/Shah-Fazal)\ **Post date:** [June 1, 2026, 3:50pm UTC](https://community.retellai.com/t/agent-says-transitions-calls-aloud-and-speaks-chinese-instead-of-transitioning/2956/4 "2026-06-01T15:50:43Z")
Hey @rodrigo.christiansen can you share your Agent ID and the Call ID ? where you faced this issue. Thank You ---
**Author:** ![rodrigo.christiansen](https://yyz2.discourse-cdn.com/flex008/user_avatar/community.retellai.com/rodrigo.christiansen/32/1731_2.png) [@rodrigo.christiansen](https://community.retellai.com/u/rodrigo.christiansen)\ **Post date:** [June 1, 2026, 5:13pm UTC](https://community.retellai.com/t/agent-says-transitions-calls-aloud-and-speaks-chinese-instead-of-transitioning/2956/5 "2026-06-01T17:13:57Z")
@Shah-Fazal Here’s a sample of calls with the first issue: - call\_abdd66c3af9f8d4c96447c98671 - call\_dc1320fb8c707894e2510935793 - call\_4195d1a578137befa837cfa637a - call\_f1411d76a6b90d88d99c5c0bc00 - call\_e3df6df3400fda624ac336a3ff7 - call\_d918c211ef71ee0ad8949ee531c - call\_1bf08b709f151ec2d8d2657b092 And another set with the second issue: - call\_99bc4283d49e935097c0b675dbb - call\_c1abe58a72261c1d2e6829e8056 - call\_6d9673467182aa5c15c411ba302 - call\_a9bd7d2e8b09db4f43ba73bc346 - call\_acafeee81ebbbb1ccf2b73a78fd - call\_29c88136b067677bc100c11f31d - call\_3bfa30166c19c68de6b32dcd49e ---
**Author:** ![Shah-Fazal](https://yyz2.discourse-cdn.com/flex008/user_avatar/community.retellai.com/shah-fazal/32/2522_2.png) [@Shah-Fazal](https://community.retellai.com/u/Shah-Fazal)\ **Post date:** [June 1, 2026, 5:36pm UTC](https://community.retellai.com/t/agent-says-transitions-calls-aloud-and-speaks-chinese-instead-of-transitioning/2956/6 "2026-06-01T17:36:52Z")
Hey @rodrigo.christiansen I have escalated your issue to the team. ---
**Author:** ![Shah-Fazal](https://yyz2.discourse-cdn.com/flex008/user_avatar/community.retellai.com/shah-fazal/32/2522_2.png) [@Shah-Fazal](https://community.retellai.com/u/Shah-Fazal)\ **Post date:** [June 1, 2026, 8:33pm UTC](https://community.retellai.com/t/agent-says-transitions-calls-aloud-and-speaks-chinese-instead-of-transitioning/2956/7 "2026-06-01T20:33:45Z")
Hey @rodrigo.christiansen both symptoms (the JSON`commentary to=functions.*` tokens and the CJK bursts) look like the same underlying failure mode. What we found on the sampled calls (e.g. call\_abdd66c3af9f8d4c96447c98671, call\_99bc4283d49e935097c0b675dbb): - They ran on **gpt-5.4** via OpenAI’s Responses API. The strings being spoken aloud `{"tool_uses":[{"recipient_name":"functions.transition_to_gather_info"...}]}`, `commentary to=functions.transition_to_gather_info`) are OpenAI’s internal tool-call channel markers — they should land in the structured tool-call output, but the model is occasionally emitting them as plain assistant text, so TTS reads them out. - The `transition_to_` names match how our stateful-LLM engine auto-names transitions between your states, so that part is expected — the bug is that the model is verbalizing the protocol token instead of invoking the tool. - The Chinese-character bursts (大发彩票 / 天天送彩票) co-occur in the same off-distribution turns and appear to come from the model as well — none of those strings exist anywhere in our code, and your agent is configured en-US with 11labs-Kate, so there’s no path inside Retell that could introduce them. We’re attributing them to the provider by elimination; we have not yet extracted the raw model payload for one of those turns to quote verbatim. Recommended next steps (workarounds while we don’t have a fix for the model behavior itself): 1. Move the agent off gpt-5.4. You mentioned gpt-4.1 reproduces it too, so I’d suggest trying a different family — e.g. gpt-4o or claude-sonnet-4 — rather than another gpt-5.x variant. We have not specifically reproduced or cleared those alternatives against this exact failure mode, so please share a few new call IDs after the swap and we’ll confirm. 2. Optionally add a guard near the top of the general prompt: “Respond only in English. Never output the strings `functions.`, `to=functions.`, `{"tool_uses"`, or any non-Latin characters.” This doesn’t fix the underlying model behavior, but is worth trying as a mitigation. 3. The agent we inspected is currently running off its draft version (isPublished=false). Make sure any model change is published so production traffic picks it up. We’ll also look internally at whether we can detect and strip these Harmony channel markers server-side before TTS for gpt-5.x sessions. Thank You