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

67
hpr_transcripts/hpr4188.txt Normal file
View File

@@ -0,0 +1,67 @@
Episode: 4188
Title: HPR4188: Re: HPR4172 Comment by Ken Fallon
Source: https://hub.hackerpublicradio.org/ccdn.php?filename=/eps/hpr4188/hpr4188.mp3
Transcribed: 2025-10-25 21:01:25
---
This is Hacker Public Radio Episode 4188 for Wednesday, the 21st of August 2024.
Today's show is entitled, Read Per Comment by Ken Fallon.
It is part of the series' accessibility.
It is hosted by Archer's 72, and is about 5 minutes long.
It carries a clean flag.
The summary is, Archer's 72 responds to Ken's comment on Pro with hopefully enough detail.
Hello, HPR.
This is your host, Archer 72, for another episode of Hacker Public Radio.
My subject today is Piper Voice Enthusus, continued.
In response to Ken's comment on my show, HPR 4172ree, HPR 4172Piper,
HPR Voice Enthusus, I am responding to his comment with a solution.
I'm glad that Ken commented, because I had put the problem on the back burner and forgot about it.
Both of us had the make command for the Piper GitHub repo fail at 22%.
I ignored it for the time being in compiled Piper for the Raspberry Pi instead.
Now here is the comment that got me to figure out how to get Piper working on my own FIDOR 40 laptop.
With the voice I'm using, it garbled the comments, so I will be changing voices temporarily.
Common hash one posted on 2024-07-24, 424-27 by Ken Fallen Fails on FIDOR 40-22% linking
C-shared library lives Bikengi. So it's sector of the errors too long to be spoken here.
Common hash two posted on 2024-07-26, 930-817 by Archer 72ree, Colin Fails on FIDOR 40,
I get the same failure and found that there was a release in 2023 I put the downloaded Piper
directory and slash op along with the Piper voices slash and directory and have a successful
voice output. And of comments and further conversations with Ken, I found that a vital part of Piper
voice synthesis had been forgotten. For example, if you were using Piper to convert a text
file to .wav, the command need to include the following, input.txt Piper executable location.
For example, slash op slash Piper slash Piper model and the model location. For example,
slash op slash Piper was a slash note. The voice use need to include the voice in .onks format
and also the voice configuration in .json format output underscore file output.way the final
script is included in the show notes. That said, now if you had downloaded the voices from
HBR 4172, there should be a successful voice to text output. To put the final touches on my
voice, which is the NUS-cusal-medium voice process just a bit with the SOX program.
The following parts are processed. Add to seconds of silence to the beginning of the file,
reduce clipping by reducing the volume to 99% of input reduced the tempo by 12% the resulting
script will be in the show notes. One last thing, it was brought to my attention that the Piper voice,
Bryce may sound like William Shatner in the original Star Trek TV series. I will put that clip in
here and see what the community thinks. Feel free to leave a comment saying ye or nay on this opinion.
From Wikipedia, the free encyclopedia automatic announcement a synthetic voice announcing an
arriving train in Sweden. Speech synthesis is the artificial production of human speech.
A computer system used for this purpose is called a speech synthesizer and can be implemented
in software or hardware products. A text to speech TTS system converts normal language text
into speech, other systems render symbolic linguistic representations like phonetic transcriptions
into speech. One the reverse process is speech recognition. Synthesized speech can be created by
concatenating pieces of recorded speech that are stored in a database. Systems differ in the size
of the stored speech units, a system that stores phones or diffones provides the largest output
but may lack clarity. For specific usage domains, the storage of entire words or sentences
allows for high quality output. Alternatively, a synthesizer can incorporate a model of the vocal
tract and other human voice characteristics to create a completely synthetic voice output.
To the quality of a speech synthesizer is judged by its similarity to the human voice
and by its ability to be understood clearly. An intelligible text to speech program allows people
with visual impairments or reading disabilities to listen to written words on a home computer.
Many computer operating systems have included speech synthesizers since the early 1990s.
What you just heard was the Bryce voice from Piper. What do you think?
If this tool works for you, feel free to leave comments on the show. Better yet, record a show
of your own. Looking forward to hearing from the next host whether it be by text to speech or
a microphone. Remember to support free software and apps in the F-Frood store if you use Android.
This has been your host, Archer72. Bye!
You have been listening to Hacker Public Radio at HackerPublicRadio.org. Today's show was
contributed by a HBR listener like yourself. If you ever thought of recording podcasts,
you can click on our contribute link to find out how easy it leads. Hosting for HBR has been
kindly provided by an honesthost.com, the internet archive and our syncs.net.
On the Sadois status, today's show is released under Creative Commons' Attribution 4.0 International