Show HN: SpeakStruct – Turn voice into consistent structured data

[prashanttrivedy]

https://speakstruct.co/

Hey folks,

Built SpeakStruct to allow users to setup templates to turn voice input into consistent, structured output. Use cases from feedback I've had are customer support, coaching/check-ins, note taking, etc.

Although there is a pricing section, signing up is free (no CC required). If you don't want to sign up, a demo is available here (sale-sy demo, but shows the product). https://app.arcade.software/share/nWm35szNPwD3PpH4eUSp

Open to all feedback.

[mdaniel]

> Open to all feedback

Ok, then I'll bite: who is the target audience that cannot watch a video without some horrible music turned up way louder than the voiceover? At least over on YT, if there's some b-roll music playing over something, then I'm almost guaranteed it's a scam of some kind and just close the window

[prashanttrivedy → mdaniel]

Fair point. I thought the background music volume lowered sufficiently during the voice-over, but I guess not. Will look to adjust that.

[thornewolf]

Looks great! Right in line with what I think a lot of people will realize they need in the next few months-years.

[prashanttrivedy → thornewolf]

Out of interest, what use cases/people did you have in mind?

[FezzikTheGiant]

are you using whisper at the backend