### Answer Transcription quality depends on the AI models used, which are selected to balance accuracy and processing speed [(1) ]() . Here are the main solutions to optimize transcription: ## Use Boosted Keywords Add custom keywords to enhance the model's vocabulary for specific words or domain-specific terms . You can support up to 100 custom keywords . This is particularly useful for names, brands, street names, and specialized terminology [(2) ]() . ## Adjust Denoising Mode If you're experiencing transcription errors due to background noise or speech, try adjusting the denoising mode setting [(1) ]() . ## Enable Transcription Mode for Accuracy If sentences are being cut off prematurely, turn on transcription mode to optimize for accuracy . This helps when transcription quality is impacted by the system finalizing sentences too early . ## Language Selection Ensure you've selected the correct language and dialect for your use case [(2) ]() . For example, selecting

en-GB

optimizes speech recognition for British English . Select

multi

for multilingual support . ASR quality directly impacts every part of the AI voice agent experience [(3) ]() . If transcription is inaccurate, even advanced AI systems will misunderstand user intent and deliver poor results .

​ 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] Automatic Speech Recognition (ASR)](https://www.retellai.com/glossary/automatic-speech-recognition-asr) ​

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