### Answer If you're experiencing transcription misinterpretations even with accuracy mode enabled, here are several solutions to improve ASR accuracy: [(1) ]() Boosted Keywords - Add custom keywords (up to 100) to enhance the model's vocabulary for specific words that are being misinterpreted. You can configure this using the

boosted_keywords

parameter: [(2) ]()

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

Denoising Mode - If background noise or speech is causing issues, adjust the

denoising_mode

setting. [(1) ]() Available options include: [(2) ]()

json
"denoising_mode": "noise-cancellation"

Options are:

no-denoise

,

noise-cancellation

, or

noise-and-background-speech-cancellation

. Short Response Issues - If short responses like "sure" or "yes" are being missed and background noise isn't high, try setting denoising mode to "no-denoise" to preserve more of the raw audio signal. [(1) ]() Language-Specific Settings - For English agents, you can use

vocab_specialization

set to either "general" or "medical" depending on your domain. [(2) ]() [(3) ]() STT Mode Configuration - Ensure

stt_mode

is set to "accurate" rather than "fast": [(2) ]()

json
"stt_mode": "accurate"

These settings can be configured when updating your agent through the API or dashboard. [(4) ]()

​ To learn more, see the sources I considered: [[1] Increase transcription accuracy](https://docs.retellai.com/reliability/wrong-transcript) [[2] Get Voice Agent](https://docs.retellai.com/api-references/get-agent) [[3] Get Agent Versions](https://docs.retellai.com/api-references/get-agent-versions) [[4] Update Voice Agent](https://docs.retellai.com/api-references/update-agent) ​

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