@jay
Both Deepgram and Talkscriber have their own strengths and are efficient in different scenarios. Deepgram is known for its robust models and ability to handle various accents and noisy environments, while Talkscriber is praised for its precision with clear speech.
Since you're experiencing issues with Deepgram's transcription of ID numbers, it might be worth trying out Talkscriber to see if it performs better for your specific use case. It's important to note that the performance can vary based on the audio quality, speaker's accent, and background noise.
I recommend running a few tests with Talkscriber using the same audio samples you've tried with Deepgram. This way, you can directly compare the accuracy of both transcribers, especially for the ID numbers that are causing issues.
Would you like to proceed with setting up a test for Talkscriber? If so, I can guide you through the process or provide you with the necessary information to get started.