Q: Some questions about voice recognition, content creation...
Thanks in advance for providing a few ground-level details. I'm considering Video to Blog to assist me in repurposing podcast content. My format is interview style, normally with at least two voices in each episode. Currently I download a transcript that does well at distinguishing voices and then submit the transcript to ChatGPT. How well does V2B work at doing the same?
Also, if I want to create multiple articles / posts that focus on subsegments within an episode, can V2B be trained to do that? And does it remember and improve the writing style / tone over time, or is that something that needs to be submitted with each content request?
Andrew_VideoToBlog
May 7, 2025A: For your first question, yes. Be sure to select the "Premium Transcription" option and then select the "App Speaker Labels" option. This will ensure your video is transcribed correctly while distinguishing between multiple speakers.
Yes, you can create multiple posts from one episode by leveraging our Time Range feature which lets you specify a specific time range of the video for the blog post to focus on.
It won't currently remember / improve the writing style by itself, but any settings you configure (like tone, etc) and/or custom instructions you provide can be saved to a template for easy reuse between videos.
Triplevee