Are they going to verify that everyone said their sequence correctly? It would be a silly and pointless prank to derail the effort by omitting a number on purpose, but this is the internet... Or maybe it's just the 'coming together' aspect that we're going for anyway, in which case, it doesn't matter :)
Maybe they could run it through Whisper on Groq? It should be able to process individual clips in about a second.
>We're aware it's likely that if you're reading out a long string of digits like this, you're likely to slip up or say a wrong digit. Mistakes are a very human feature, but as long as you correct it and carry on, they're fine - we just need evidence of humans having said the whole prime, not necessarily in one go. You can watch your video back through before submitting to check it's ok. If you want to edit together multiple clips to make your video, that's also fine!
So they need the some degree of semantic understanding to recognize corrections, in the various forms they can take. Speech to text alone is insufficient.