Hey there, so I'm working on a system within VAPI and I find that the transcription is transcribing the correct word (when boosting that word). Then however, there is a second transcription of the same audio and the second time, the one that is being passed into the message and into the LLM, is incorrect. Now I wonder if that's because on the second transcription there is no boosting. https://cdn.discordapp.com/attachments/1336366437773738150/1336366704711831552/CleanShot_2025-02-04_at_16.03.182x.png?ex=67a38bfa&is=67a23a7a&hm=87c51f7c80f8f2aef0fd85870bc0d0af702b3f4bf6705883b3000b9b8bd19d02&

@Hugo Hello! It sounds like you're experiencing an inconsistency with the transcription service, where the word boosting works correctly on the initial transcription but not on subsequent ones. This could be due to a variety of reasons, such as different settings being applied to the second transcription process or a lack of word boosting in that phase. To address this issue, you may want to ensure that the word boosting is consistently applied across all transcription processes. If the settings are supposed to be the same for both transcriptions and you're still encountering this problem, it might be a good idea to review the configuration of your voice pipeline to confirm that the word boosting is enabled where necessary. If you need further assistance with checking or adjusting your settings, please let me know, and I can help guide you through the process or provide more detailed support.

Nice try, VAPI bot. 😁 I always appreciate your efforts.