What commenters asked our summary
In our own words. Each line links to the comment it is based on.
- Can these models run on an iPhone, for example to read articles aloud like a podcast?From this comment
- Can users create custom voices themselves, or must they go through the team, and could a license be bought?From this comment
- Does the model support expressive control through pitch, speed, volume settings or tags like coughs and laughs?From this comment
- How hard is it to run via a C++ runtime instead of Python, and is the iOS version written in Swift?From this comment
- Would an Android app be able to take over from the built-in text-to-speech engine?From this comment
What they doubted or pushed back on our summary
- Without details on data, training or novel architecture, one commenter assumes this is finetuning of another model repackaged.From this comment
- Small models usually struggle with prosody, making speech hard to follow, so they wondered how this one performs.From this comment
- Such models often fail on short strings like button labels that screen readers repeat constantly.From this comment
- The docs claim GPU speed but the repo shows no way to run on a GPU, and install size may exceed a gigabyte.From this comment
What the maker answered our summary
48 replies from the maker in the thread; the points below are the ones we could tie to a comment.
- A mobile software kit and inference engine are coming soon; community methods for iOS already exist and can be found by searching.From this comment
- Expressive tags are not supported yet, and they asked which tags users would find most useful.From this comment
- They will add professional voices and a do-it-yourself custom voice path, with a model for it due in two to three weeks.From this comment
- They will add a side-by-side example comparing the released models on the same text.From this comment
What a builder can take from it: Answer questions about platforms, voice customization and missing features with concrete timelines and offers to help, since that turned skepticism into goodwill here. our reading
The title, taken apart our calculation
This post got 561 points; the median for all 1442 posts is 112. In Open source projects (328 posts) the median is 103 points and 38 comments.
When it was posted our calculation
Thursday at 15:00 UTC. Of 4,000 Show HN posts submitted in that UTC hour over the window (2025-11-20 to 2026-11-20), 133 (3.3%) reached 50 points; on Thursdays it was 2.7% of 8,077. The average over all hours is 2.9%. One post's time does not explain its result; the full table of hours is on the Show HN hub.
Check your title our calculation
Type the title you plan to post. It is compared with 1,442 Show HN posts that reached 50 or more points: its length, its shape, and how posts of that length and shape did. Nothing is sent anywhere.
Type a title above to see where it sits.
Draft my Show HN post
Paste your site address and get title options and a first comment for your own Show HN post, written from what your site says and checked against the numbers above. Nothing is posted for you.
Free to try and no account needed. FoxPlug is for people who ship several projects and keep stalling on telling anyone: it turns what you ship into posts you approve before anything goes out. See what each plan includes.
More Open source projects teardowns
Points, comments, titles and times are Hacker News's own numbers, read from the post itself, last updated Nov 2026. Summaries of what people said are ours, written in our own words, and each one links to the comment it came from. Percentages and medians marked "our calculation" are computed from the posts counted on the page: they describe what happened, not what will happen to your post. FoxPlug posts nothing for you. Plans and limits are on the pricing page. Questions: support.
After the launch post: a changelog your users read
A launch brings visitors once. FoxPlug turns what you ship afterwards into a public changelog and ready posts, so the next visitor finds something new.
Start your changelog See a SaaS changelog example
Free to start. Pro is a month.
FoxPlug Pro
- A public changelog page and feed for each project
- Visual cards and walkthrough videos made from what you shipped
- Posts for X, LinkedIn and dev.to written from your changes
- Connect GitHub and the tools you build with