### Answer Yes, there are several ways to improve transcription accuracy during calls: 1. Boosted Keywords Use this for specific words or domain-specific terms (like medical terminology) that are missing from transcripts. [(1) ]() You can add up to 100 custom keywords to enhance the model's vocabulary. 2. Transcription Mode Settings You can choose between two modes: [(2) ]() - **Optimize for speed**: Uses the latest interim results with low endpointing for lowest latency. - **Optimize for accuracy**: Uses results with higher endpointing, waiting longer with more context for more accurate transcripts (adds ~200ms latency) . If your use case relies heavily on capturing entities like numbers and dates, use the "optimize for accuracy" mode. 3. Denoising Mode If transcription errors occur due to background noise or speech, adjust the [denoising mode setting]() to see if it helps. [(1) ]() 4. Accuracy Mode for Cut-off Sentences If sentences are being cut off (finalized before they should be) , turn on transcription mode optimized for accuracy.

​ To learn more, see the sources I considered: [[1] Increase transcription accuracy](https://docs.retellai.com/reliability/wrong-transcript) [[2] Balance between transcription accuracy and latency](https://docs.retellai.com/build/transcription-mode) ​

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