### Answer To improve how the agent transcribes and spells names correctly, you can use these approaches: 1. Use Boosted Keywords Add names you expect to hear frequently to the

boosted_keywords

field. This biases the transcriber to recognize those specific words more accurately. [(1) ]() [(2) ]()

javascript
"boosted_keywords": [
  "retell",
  "kroger"
]

[(1) ]() You would add common names or specific names relevant to your use case to this array. 2. Change STT Mode to Accurate Set

stt_mode

to

"accurate"

instead of

"fast"

for better transcription quality. [(1) ]() [(2) ]()

javascript
"stt_mode": "fast"

[(1) ]() Change this to

"accurate"

for improved recognition. 3. Adjust Denoising Mode Try different denoising settings to reduce background interference that may affect transcription. The available options are

"noise-cancellation"

and

"noise-and-background-speech-cancellation"

. [(3) ]() 4. Prompt Engineering In your prompt, instruct the agent to ask for spelling confirmation when capturing names, or to repeat back what it heard so the caller can correct it if needed.

​ To learn more, see the sources I considered: [[1] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) [[2] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) [[3] List Voice Agents](https://docs.retellai.com/api-references/list-agents) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer --- The

{{current_time}}

variable defaults to the

America/Los_Angeles

timezone. [(1) ]() To get the correct date and time for your specific timezone, use the timezone-specific variable format:

{{current_time_[timezone]}}

For example: -

{{current_time_Australia/Sydney}}

-

{{current_time_America/New_York}}

-

{{current_time_Europe/Rome}}

, [(2) ]() , [(3) ]() Troubleshooting steps: 1. Specify your timezone explicitly rather than using the default

{{current_time}}

. [(1) ]() , [(3) ]() 2. Publish your agent after making changes—some users have reported date issues that resolved after publishing. [(4) ]() 3. Use

{{current_calendar_[timezone]}}

if you need a 14-day calendar view in your specified timezone. [(1) ]() , [(3) ]() Example usage in your prompt:

Context: current time is {{current_time_America/New_York}}

[(1) ]() This issue with incorrect dates has been reported by other users in the community, and specifying the timezone explicitly along with publishing the agent has helped resolve it in several cases. [(5) ]() , [(4) ]() , [(6) ]()

​ To learn more, see the sources I considered: [[1] Dynamic Variables](https://docs.retellai.com/build/dynamic-variables) [[2] Simulation Testing Now Live for All Agents](https://www.retellai.com/changelog/simulation-testing-now-live-for-all-agents-c27zh) [[3] Discord message from @27th_supreme on 2025-11-24](https://discord.com/channels/1186424376300679209/1294891368505937952/1442599523443671273) [[4] Issue with current date](https://discord.com/channels/1186424376300679209/1432663702485864448) [[5] Current_Time variable not working](https://discord.com/channels/1186424376300679209/1301829402446790717) [[6] im using the {{current_time}} variable, but the agent says is march 14th instead of march 5th](https://discord.com/channels/1186424376300679209/1346957336966725683) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

@AI Evy in each and every node?

### Answer No, you don't need to add the timezone variable to each and every node individually. The

{{current_time_[timezone]}}

variable should be placed in your Global Prompt (global settings) , which sets the context for conversations across all nodes. [(1) ]() Global settings apply to the entire conversation and help maintain consistency across all nodes. By adding the current time context in your global prompt like this:

Context: current time is {{current_time_America/New_York}}

...the agent will have access to the correct date/time information throughout the entire conversation flow, regardless of which node it's currently in. You only need to set it once at the agent level in the global settings, not per-node.

​ To learn more, see the sources I considered: [[1] Retell AI’s Advanced Conversation Flow | Retell AI](https://www.retellai.com/blog/unlocking-complex-interactions-with-retell-ais-conversation-flow) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer Retell AI webhooks are designed to retry up to 3 times if they don't receive a successful response (2xx status code) within 10 seconds. [(1) ]() [(2) ]() Common reasons your webhook is being hit multiple times: 1. Timeout – Your endpoint takes longer than 10 seconds to respond, so Retell retries. [(1) ]() 2. Non-2xx response – Your endpoint returns an error status code, triggering a retry. [(1) ]() [(3) ]() 3. Multiple webhook events – Retell sends 3 separate webhook events per call:

call_started

,

call_ended

, and

call_analyzed

. If you're seeing duplicates, you may be receiving all three events. [(1) ]() [(4) ]() How to fix this: - Ensure your webhook endpoint responds with a 2xx status code within 10 seconds. [(1) ]() [(2) ]() - Return the response immediately, then process the data asynchronously if needed. - Check your logs to identify if the issue is timeouts or error responses. [(3) ]() - If you only need post-call analysis data, filter for the

call_analyzed

event type in the payload. [(1) ]() [(4) ]() The webhook payload includes an

event

field that tells you which event triggered it:

json
{
  "event": "call_ended",
  "call": { ... }
}

[(1) ]() Filter by this field to handle each event type appropriately and avoid duplicate processing.

​ To learn more, see the sources I considered: [[1] Webhook Overview](https://docs.retellai.com/features/webhook-overview) [[2] Inbound webhook](https://docs.retellai.com/features/inbound-call-webhook) [[3] Webhook called multiple times inconsistently for one call](https://discord.com/channels/1186424376300679209/1357052408819355729) [[4] Discord message from @majestic_seahorse_21472 on 2025-03-13](https://discord.com/channels/1186424376300679209/1294891368505937952/1349768291303821312) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.