The conversation before Thanksgiving happened to coincide with the opening of OpenAI's drama. However, the editor was tired and I tried a variety of different tools. The quality was better than the past few live broadcasts and interviews (but I am a perfectionist and said it was still good). It’s not good, I have to keep working hard).
There are still too many tools in the English world, so there are more automated tools available for conversations in English. Last time I used Chinese with Jin Feng, the tools were limited and their use was relatively limited.
The biggest difference between this video and the past is that the video is recorded at both ends, and then multi-track merged, so that the video of both sides is clearer, the sound is also processed in this way, and the sound of both sides is also good. Of course, it’s also because Jianshuo and I have almost the same audio equipment (he bought the same model as me through my Amway service😂), so it’s the result of two poor students having more stationery.
But the effect of this combined recording is very encouraging to me. Next time there will be a more professional local simultaneous recording service, which should be easier to manage and post-produce.
In addition, there is great potential to try to use AI to rewrite the content of conversations. If you write various prompts well, you may be able to re-create these recording materials into very rich text content. I'm going to try this next, especially after talking to a group of people.