Hacker News: thangalin

New comment by thangalin in "Ask HN: Are there AI models for generating sounds based on a text and reference?"

thangalin — Wed, 07 Oct 2026 01:09:20 +0000

KeenLore is my locally hosted full-cast emotive audiobook generator I'm developing for my novel:

https://www.youtube.com/watch?v=WAeHgE94rVo

Another HN user suggested embedding sound effects. The lead author of MOSS-TTS emailed me that the next version will have a SOTA voice designer. Poke around the voice design space, you'll find text-to-effects here and there. I certainly have my eyes on this space.

New comment by thangalin in "Norway Eyes Partial Ban of Smart Glasses"

thangalin — Tue, 06 Oct 2026 00:06:29 +0000

> Pun intended?

Guilty.

> I profoundly disagree

People will take to wearing corrective contact lenses that will have recording capabilities in a few years. This is going to open up a huge can of worms for privacy, cinemas, and more. I did not write that we mustn't do anything about it right now, only that it is short-sighted. Creating laws about wearable recording devices would benefit from addressing near-future technology, which will include easily concealed digitally augmented corrective lenses.

* https://www.regjeringen.no/no/aktuelt/vil-innfore-midlertidi...

* https://www.regjeringen.no/en/dep/dfd/org/minister-of-digita...

* Contact: postmottak@dfd.dep.no

New comment by thangalin in "Norway Eyes Partial Ban of Smart Glasses"

thangalin — Mon, 05 Oct 2026 20:27:35 +0000

This is short-sighted; smart contacts are viable.

https://www.bbc.com/news/av/technology-51137379

New comment by thangalin in "Loss of cell identity drives human aging: Two new papers"

thangalin — Sat, 03 Oct 2026 15:52:58 +0000

https://sci-net.xyz/10.1038/s41586-026-10955-0

https://sci-net.xyz/10.1016/j.cell.2025.07.031

New comment by thangalin in "GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price"

thangalin — Tue, 29 Sep 2026 20:34:18 +0000

I started KeenLore (an emotive audiobook creator) that way. I gave it software specifications, languages, JSON schema definitions, container requirements, hardware configuration (8GB NVIDIA T1000 GPU, 96GB RAM), and zero user interface mockups. For the second round, I asked it to build a completely independent, re-entrant, and data isolated demo system on top of the web application. The demo application included voice generation using one of its voice designs. Here's the output:

https://www.youtube.com/watch?v=WAeHgE94rVo

The system performs quotation attribution on my local hardware for my near-future, hard sci-fi novel (having nearly 500 quotations) with over 97% accuracy.

The initial prototype was developed quite quickly, but numerous successive iterations were required to fix numerous gaffs by Opus 5 (because it doesn't actually _understand_ what it takes to make general-purpose audiobook narration software).

New comment by thangalin in "Opus 5.5 is good at explainer videos"

thangalin — Fri, 25 Sep 2026 00:28:39 +0000

I'm looking to put together a tutorial discussing fundamentals of Blues and Swing partner dancing. I have the raw source material. I'd like to change the background, change the attire of instructors (myself and a friend), and fix up other issues (dead space, umms, and other gaffs). The footage is about 22 minutes, and can be split into 5 different segments of about 3 - 4 minutes each.

I'm running Arch Linux and would rather not install DaVinci Resolve, but Blender would be fine for the non-linear video editor.

My plan is to use ChatCut to trim and split into the different sections. After I have the five segments, what would you suggest for swapping the background (environment) and attire? There are two simultaneous camera shots (front and side) that I'd like to stitch together as well.

Any suggestions? (Paying someone a couple of hundred $CAD to take this task off my plate would also work.)

New comment by thangalin in "Gemini 3.8 text-to-speech"

thangalin — Wed, 23 Sep 2026 21:58:56 +0000

> Fish Audio or Higgs

I wasn't able to find a version of these that can create voice samples based on voice designs. Do you mean to use Qwen3 TTS Voice Design to create samples followed by Higgs or Fish Audio to clone the sample voices and narrate the novel?

MOSS-TTS 2.0 will apparently have voice design, as well, on par with ElevenLabs quality.

New comment by thangalin in "Gemini 3.8 text-to-speech"

thangalin — Wed, 23 Sep 2026 19:06:40 +0000

> annotate your text with extra 'stage directions'

Good idea, not something I've considered yet. Wouldn't take much to add it since there's already a feature for selecting a quotation and assigning it an intonation. Same infrastructure could be reused to select arbitrary text and assign stage directions.

New comment by thangalin in "Gemini 3.8 text-to-speech"

thangalin — Wed, 23 Sep 2026 16:18:47 +0000

Here's a video of my Emotive Audiobook Creator, KeenLore, a locally hosted web app:

https://www.youtube.com/watch?v=WAeHgE94rVo

No cloud, no tokens to pay. Reads a book using a full cast of characters. Quotation attribution detection (for my novel) is at 97.2% accuracy (485/499 quotes identified and assigned correctly). The autofill of character voice descriptions uses the prose to determine how the character sounds.

Employs Gemma 4[1] for the prose analysis (voice fills, quotation detection) and Qwen3 TTS Voice Design[2] for creating voice samples. Runs on an 8GB NVIDIA T1000 GPU card, 96 GB RAM, and a AMD Ryzen 5 7600.

[1]: https://deepmind.google/models/gemma/gemma-4/

[2]: https://huggingface.co/spaces/Qwen/Qwen3-TTS-Voice-Design

New comment by thangalin in "The first new cat species discovered in 100 years"

thangalin — Fri, 18 Sep 2026 21:08:42 +0000

On a related paw, Leopardus guigna (güiña) in Anticura goes by the cute name of kodkod:

https://en.wikipedia.org/wiki/Kodkod#/media/File:Leopardus_g...

New comment by thangalin in "Hackers Got Inside a Flock Camera"

thangalin — Wed, 16 Sep 2026 15:08:25 +0000

https://i.ibb.co/WWWYznHX/flock-future.png ;-)

New comment by thangalin in "JetKVM Mini"

thangalin — Sun, 13 Sep 2026 20:39:17 +0000

You missed the Tangentially part, which is what tells people that it is a different type of KVM, which are also useful to many.

New comment by thangalin in "JetKVM Mini"

thangalin — Sun, 13 Sep 2026 17:23:08 +0000

Tangentially, I tested many KVM models:

https://hardwarerecs.stackexchange.com/questions/18561/kvm-d...

The only one that met my requirements was the UGREEN 8K@60Hz DisplayPort KVM switch:

https://www.amazon.ca/gp/product/B0CFFFHFJT

Several months in without any major issues.

New comment by thangalin in "Make your first edit to OpenStreetMap"

thangalin — Sun, 13 Sep 2026 17:14:15 +0000

Of possible interest, I once used an OSM editor to help draw Voronoi diagrams on spherical surfaces in a scalable vector graphic file format to help depict planet-wide fissures from colossal collisions.

https://dave.autonoma.ca/blog/2020/05/12/impacts-project-vor...

New comment by thangalin in "From Git to Fossil (2025)"

thangalin — Sun, 13 Sep 2026 07:24:35 +0000

If all you want is a simple read-only web presence for a Git repository, there are plenty of solutions. Here's mine:

https://repo.autonoma.ca/repo/treetrek

New comment by thangalin in "Researchers Spot Fake Ancient Pottery Using the Earth's Magnetic Field"

thangalin — Wed, 09 Sep 2026 06:42:24 +0000

https://impacts.to/downloads/lowres/impacts.pdf#page=23

Quoting my book:

"Studying these layered strata is known as magnetostratigraphy and can be used to verify radioactive dating methods. Geologists used magnetostratigraphy to cross-check the dates of the Nakali Formation, where Nakalipithecus nakayamai’s jaw was found."

New comment by thangalin in "27.5KB language-agnostic WebGPU syntax highlighter"

thangalin — Wed, 09 Sep 2026 04:16:11 +0000

27 KB is extraordinarily impressive. Here's a deterministic suite of common language- and format-specific PHP files an LLM wrote for me in 32 KB, for comparison:

https://repo.autonoma.ca/repo/treetrek/tree/HEAD/render/rule...

New comment by thangalin in "On the Navier–Stokes Millennium Prize Problem"

thangalin — Tue, 08 Sep 2026 19:28:56 +0000

The proof of finite-time singularity may impact both fluid dynamics models (CFD) and AI reasoning models. Under specific conditions, Navier–Stokes equations allow velocity to grow infinitely, causing the continuum fluid assumption to break down. Knowing the exact mathematical breakdown mechanisms helps developers improve adaptive mesh refinement and sub-grid scale models around high-vorticity regions (like vortex stretching and turbulent shear layers). While aerodynamic simulations for vehicles operate far from singularity thresholds, their stability at extreme boundaries could improve?

Proving out the combination of scaling inference-time compute and agent collaboration to solve previously intractable mathematical problems is WOW. By pairing creative candidate generation with automated proof checkers (like Lean) we are leaning into a repeatable framework for AI-driven scientific discovery.

New comment by thangalin in "LibreOffice breaks download records after declaring it has no AI features"

thangalin — Tue, 08 Sep 2026 16:53:24 +0000

For my text editor, KeenWrite[1], 42% of users answered that they'd use AI. Since the majority don't want it, no AI has been added.

[1]: https://keenwrite.com/

New comment by thangalin in "Flock used >100 times to track veteran who recorded traffic stop"

thangalin — Sat, 05 Sep 2026 17:39:02 +0000

https://i.ibb.co/WWWYznHX/flock-future.png ;-)