AI tool comparison
Coherence Studio vs Stet
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
Productivity
Coherence Studio
Open-source AI screen recorder that edits itself
75%
Panel ship
—
Community
Paid
Entry
Coherence Studio is a fully open-source desktop screen recording app with an AI editing pipeline baked directly in. Record a demo or walkthrough, and it automatically removes dead time and loading screens (AI-based activity detection), generates captions via Whisper, writes an AI narration script, and lets you export a polished video without touching a timeline editor. Available on macOS, Windows, and Linux under MIT license. The project launched April 1, 2026 and surfaced on Hacker News with strong early traction. It positions itself as a developer-friendly alternative to Loom: no subscription, no upload to someone else's server, full control over the output. The narration generation means you can turn a silent screencast into a fully voiced explainer in minutes. For indie developers, open-source maintainers, and technical content creators who need to ship demos and tutorials quickly, Coherence Studio collapses what used to be a multi-tool workflow (record → Descript → export → host) into a single local app. The MIT license means teams can self-host and integrate it into internal tooling.
Productivity
Stet
Open-source macOS dictation that sounds like you, not a corporate AI
75%
Panel ship
—
Community
Free
Entry
Stet is a minimalist, open-source macOS voice input app that transcribes speech and cleans it up without stripping away your natural voice. Named for the editorial term "let it stand," it's built on the principle that AI transcription should preserve your phrasing — not homogenize it into corporate-speak. The app listens locally, then optionally passes transcripts through an AI cleanup layer (OpenAI or Groq) to fix filler words and false starts. You can bring your own API key for completely free usage, or pay $6.99/month for the hosted cloud version. A Supabase backend enforces zero data retention, so nothing is stored after processing. Stet is the work of a single indie developer who noticed that every dictation tool on the market either sounds robotic or aggressively rewrites your words. At 66 Product Hunt upvotes on launch day (April 22, 2026), it's a quiet success that fills a real gap for writers, developers, and anyone who types a lot and is tired of Dragon-era dictation software.
Reviewer scorecard
“MIT license, local-first, cross-platform, and does the boring editing work automatically — this is exactly what I want for shipping release demos. The Whisper integration for captions removes the last tedious step. I'd replace my current Loom + Descript workflow with this immediately if the video quality holds up.”
“Open-source, BYOK, and local-first listening? This is how voice input should work. The Groq integration makes transcription near-instant. I've been using it for commit messages and code comments — genuinely faster than typing for longer explanations.”
“The 'AI intelligent trim' pitch always sounds better in demos than in practice — activity detection is hard to tune across different workflows (coding vs. clicking vs. waiting for a build). Whisper is great but adds real processing time. This project is three weeks old; I'd let it bake for a quarter before replacing a paid tool with it.”
“Apple's built-in dictation has gotten surprisingly good, and it's free with no BYOK setup. The 'preserves your voice' pitch is compelling but subjective — I'd want a side-by-side blind test. Solo indie developer + $7/mo hosted tier raises long-term sustainability questions.”
“Open-source AI video tooling is massively underserved. Coherence Studio could become the ffmpeg of AI screen recording — a foundational layer that other tools build on. The narration generation path is particularly interesting as a template for AI-assisted technical documentation.”
“We're entering an era where voice is the primary interface for AI-assisted work. Tools that get the human-voice preservation problem right now will have a head start when voice input becomes default. Stet's philosophy is the right one.”
“As someone who records a lot of tutorials, the auto-trim alone is worth it — manually cutting out loading screens and typos eats hours. The AI narration generation is a genuine creative assist, not just a gimmick. I'm switching from Loom the moment this hits stable.”
“As a writer, dictation tools that rewrite me drive me insane. Stet is the first one that feels like a scribe rather than an editor. The zero-retention policy means I can dictate client-sensitive notes without anxiety. This is the one.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.