### Answer Based on the provided sources, I don't see which specific settings you're referring to in your question. However, I can share the settings that help with misheard names and details during calls. Boosted Keywords is the primary setting to improve transcription accuracy for specific words like names and domain-specific terms [(1) ]() . You can add custom keywords to enhance the model's vocabulary, with support for up to 100 custom keywords . This is configured using the

boosted_keywords

parameter, which accepts a string array of keywords to bias the transcriber model [(2) ]() [(3) ]() . Transcription Mode settings can also help. You can adjust the

stt_mode

parameter to optimize for accuracy instead of speed . The available options are

fast

,

accurate

, or

custom

. Denoising Mode can impact transcription quality if background noise is affecting speech recognition [(1) ]() . The

denoising_mode

parameter offers options including

no-denoise

,

noise-cancellation

, and

noise-and-background-speech-cancellation

[(2) ]() [(3) ]() . If you're experiencing issues with short responses being missed, setting the denoising mode to "No Denoising" can preserve more of the raw audio signal and improve ASR accuracy for brief utterances when the environment is relatively quiet [(1) ]() .

​ To learn more, see the sources I considered: [[1] Increase transcription accuracy](https://docs.retellai.com/reliability/wrong-transcript) [[2] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) [[3] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) ​

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