lee/hpr-knowledge-base
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit: HPR Knowledge Base MCP Server

Browse Source 
- MCP server with stdio transport for local use
- Search episodes, transcripts, hosts, and series
- 4,511 episodes with metadata and transcripts
- Data loader with in-memory JSON storage

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Lee Hanken
2025-10-26 10:54:13 +00:00
commit 7c8efd2228
4494 changed files with 1705541 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

77
hpr_transcripts/hpr0543.txt Normal file
View File

@@ -0,0 +1,77 @@
Episode: 543
Title: HPR0543: Xoke's Podcasting Script
Source: https://hub.hackerpublicradio.org/ccdn.php?filename=/eps/hpr0543/hpr0543.mp3
Transcribed: 2025-10-07 22:48:50
---
It's okay, I'm thinking about you.
Welcome back to Public Radio. My name is Soak. Let's try this one again then. It does
help if you're actually picking it up from the right impulse device. Anyway so very briefly
I am going to go through a little script. I wrote bash script because bash is excellent. What
it does is it lets you make podcasts faster and I'm still working on it. It changes pretty regularly.
Go to the Soak.org when I finish testing up the new versions up there. Currently we're on
0.2.4 but I'm still kind of working on that so it's more like 0.2.4 alpha. Anyway it's licensed
under the GPL version 3. It has pretty much everything I do is it what what it does is as a bunch
of constant stuff I'll go through that and the basic idea behind it is you plug a microphone
into your computer you run this script it starts recording from that microphone you say whatever
you need to do it then records it encodes it and uploads it and the idea is it sorts everything
out that needs to if you want in turn out your music it will stick that on. So let's go through
some of exactly how it works. It's fairly simplistic. There are a bunch of variables and options
and some of the constants are things like the output file names which is just read from the
you read simply from the command line parameter you call it you call the script and then whatever
the file name so it doesn't have issues with their writing. Complete file which is the file with
the intro and outro which are currently stored as way files could probably change that flag but
you know this is fairly simplistic get something up and working again these simple intro and outro
file names we can just change that so it's not a huge big deal. If you want to listen to it before
uploads or anything you've got the playback file it will put some tags in for you currently only
on the MP3s don't actually know if speaks does have tags but you know working on that.
FTP details use name passwords so name not sure if I should have password actually in there or not
but again working progress. Then a recording quality whether you want a bunch of options here so
recording quality, intro, outro is one, a flag is zero excited the heck probably radio don't need
a flag but if I want this will not put a flag file, an ob file, MP3 file and the speaks file and
I can change the compression rates on all of those. Then we get to the main script which basically
just doesn't A record to grab the information which is pretty simplistic. Then if you want to
into an outro on the front it uses socks to blow them in otherwise we don't but we need to rename
the file to make sure it's still we're looking at the same file name. Convert it into a flag
or an MP3 format if you need and speaks. If you want to playback do a playback and if you want
an upload do an upload I'm working on that upload a bit at the moment so you know that will be coming
along slowly but say keep an eye on circle all and the idea behind this is that my Python stuff
for example was taking me for ever to do I mean literally I would spend about a month from those
most of a month not you know not spending 150 hours just making a half an hour show but
I would write a script now as I was writing the script I would sort the code out and make sure
the code worked copy it back in and then copy it back out to make sure what I copied in worked
and then rewrite scripts and bits as I didn't like read through it several times I mean that would
take hours alone then I would end up recording it and listening to it again and again and again
and taking out the arms and the ears but it's and anything like that I didn't like
oh yeah when I breathed in for example like there and all this kind of stuff and it was
taking a long time and I wanted a much easier fast way of doing so this is going to be a much
more raw gritty thing I'm probably going to be speaking too fast occasionally I do without
trying to insult all the American listeners the English do seem to speak faster than the Americans
generally so I do try and slow my speech down because with the accent as well as speaking too
fast it does make it harder for a lot of the Americans to understand so I try and slow my speech
down and Mrs. Zoko always tells me when my parents come to visit I kick into talking fast again
and then she has issues understanding me and you know I live with her so you'll understand that
I'm trying to make sure that it is a lot easier to understand I mean I'm not going quite into her
I'm not going into a full radio voice or yeah I know bad impersonation but I'm not trying to
do anything like that now this is just my normal voice trying to make it a little clearer slowing
it down trying to it enunciate a little better but by and large this is me this is how I speak
so you're going to have to put up with some of that but the idea is it's going to be a lot easier
for me to do stuff like that and it does mean that you know if you did have something that could
actually just run a back script I have no idea if the Android could or the Android phones could
or not but potentially there's you do a simple thing like that and you can run this
so there's you know a bunch of changes I need to do to the program to make sure it is working
perfectly as everyone wants but at the moment I'm trying to tailor it mainly for the
hanker public radio people but given our options in there that if anyone else wants to they can
because someone was a deep geek someone's talking about doing a speaks file so I added speaks
encoding in there I have never used speaks up until recently just when I started this I was playing
around with it but I figured it why not it's a couple extra lines and it just gives that extra
flexibility so feel free to email me if you have any suggestions comments questions all the standard
stuff and we shall see what's going on now of course you're going to hear me hit control C and
then you're going to get my standard outro and hopefully this time it actually worked and record
it because I was picking it from the right microphone not sort of an internal speaker on the laptop
thank you for listening if you want to give me any feedback you can go to zoke.org that's x-ray
osca kilo echo dot osca Romeo golf you can send me feedback through there or you can email me at
search so at gmail.com that's x-ray osca kilo echo Sierra osca Romeo uniform at gmail.com
thank you for listening to hanker public radio hpr is sponsored by caro.net so head on over to
c-a-r-o dot e c all of us in