Launched this week

Caresse

Launched this week

AI-powered intimate audio experiences

6 followers

AI-powered intimate audio experiences

6 followers

•

•

Most intimacy apps offer static scripts or repetitive experiences. Caresse is different. Using a multi-model AI pipeline, every guided audio session is uniquely generated based on your preferences, mood, relationship dynamic, and selected boundaries. Whether you’re exploring solo or with a partner, Caresse creates immersive, private experiences that prioritize consent, personalization, and imagination—making every session feel fresh, meaningful, and uniquely yours.

Free Options

Launch tags:Artificial Intelligence•Audio•Intimacy

Launch Team / Built With

Tabstack Browser AutomationAutomate the web in your app or agent, no browser to host

Promoted

Maker

📌

Hi Product Hunt! 👋 I'm Rémi, a solo (bootstrapped) developer from France, and I'm excited to share Caresse today. Why I built this Regulations around explicit content platforms are getting a lot more restrictive — age verification laws in France, similar moves spreading across the UK and elsewhere, sites getting blocked, throttled, or forced to shut down entirely. At the same time, most intimacy apps still fall into one of two camps: static scripts that get repetitive after a few uses, or platforms built around visual content that don't leave much room for imagination — or for consent and personalization. I wanted a third option: something legal, private, and consent-first, where the experience is generated for you rather than reused from a library everyone else sees. What Caresse actually does Caresse creates guided audio sessions using AI. Before each session, you set your preferences, mood, relationship dynamic, intensity, and any boundaries — Caresse then generates a unique session around that, every time. No two sessions are the same. It works solo or with a partner, and everything is audio-only: no video, no visuals, just voice and imagination. How it's built This has genuinely been the most technically interesting project I've worked on: iOS and Android apps share a single UI, built with Kotlin Multiplatform Backend is a .NET 10 API running on Azure Container Apps, with Postgres as the database Each session runs through a 6-step LLM pipeline, including an AI-as-judge step that checks coherence and consistency before anything reaches the user, keeping generation fast without sacrificing quality I've been documenting the architecture in a "Building Caresse" series on Medium if you want the deep dive — starting with how the multi-phase LLM pipeline is orchestrated. Everything — backend, mobile apps, AI orchestration — has been built solo over the past few months. What I'd love your feedback on Does the concept make sense to you, and would you use something like this? What would make you trust an AI-generated intimate experience — or what would stop you? What feature would you want next (more languages, partner sync, video eventually, something else)? I'll be here all day answering every question — critical feedback especially welcome. Thanks for checking out Caresse! ❤️

Report

7d ago

Forum Threads

p/caresse

•

1d ago

🧵 The tech stack behind Caresse — and why we made these calls

Frontend: Kotlin Multiplatform + Compose Multiplatform, shared UI across iOS/Android.
Kotlin was hard to love at first the module/folder hierarchy fights you early on. But once it clicks, KMP is a banger on almost every level: the IDE, the language itself, and the ability to drop down to native when you actually need to.
We went full Compose Multiplatform for the UI... except one screen: the audio player.
Native audio APIs on iOS/Android are just too different (and too finicky) to abstract cleanly, so that one component is native on each platform. Everything else one codebase.
Backend: .NET 10, hosted on Azure Container Apps.
Why .NET over Java or Go? Best perf/productivity tradeoff out there right now. C# is more expressive than Go, and the ecosystem is lighter than Java's (minimal APIs, EF Core, native DI = way less boilerplate). vs Go specifically: we keep strong typing and better abstractions as the codebase grows, without giving up performance .NET 10 is now neck and neck with Go in benchmarks.
Why Azure specifically: it's the only cloud that gives you a free Postgres DB with basically no limits to get started. For a bootstrapped build, that's a big deal real Postgres, zero cost, day one.
Dev setup: Rider on Apple Silicon. Excellent tooling, natively optimized for ARM, no Rosetta tax.
TL;DR: shared UI via KMP + Compose (native only where it truly matters), a .NET 10 backend that punches above its weight, and Azure Container Apps + free Postgres to keep costs at zero while we validate.

Building in public questions/roasts welcome

p/caresse

•

1d ago

Which feature would you add next to Caresse?

Long-distance mode
More voices
Apple Watch support
?

p/caresse

•

1d ago

What’s more important during Caresse audio session?

What s more important during Caresse audio session?

Personalization
Voice quality
Story
Sound design
?

View all

Forum Threads

p/caresse

•

1d ago

🧵 The tech stack behind Caresse — and why we made these calls

Frontend: Kotlin Multiplatform + Compose Multiplatform, shared UI across iOS/Android.
Kotlin was hard to love at first the module/folder hierarchy fights you early on. But once it clicks, KMP is a banger on almost every level: the IDE, the language itself, and the ability to drop down to native when you actually need to.
We went full Compose Multiplatform for the UI... except one screen: the audio player.
Native audio APIs on iOS/Android are just too different (and too finicky) to abstract cleanly, so that one component is native on each platform. Everything else one codebase.
Backend: .NET 10, hosted on Azure Container Apps.
Why .NET over Java or Go? Best perf/productivity tradeoff out there right now. C# is more expressive than Go, and the ecosystem is lighter than Java's (minimal APIs, EF Core, native DI = way less boilerplate). vs Go specifically: we keep strong typing and better abstractions as the codebase grows, without giving up performance .NET 10 is now neck and neck with Go in benchmarks.
Why Azure specifically: it's the only cloud that gives you a free Postgres DB with basically no limits to get started. For a bootstrapped build, that's a big deal real Postgres, zero cost, day one.
Dev setup: Rider on Apple Silicon. Excellent tooling, natively optimized for ARM, no Rosetta tax.
TL;DR: shared UI via KMP + Compose (native only where it truly matters), a .NET 10 backend that punches above its weight, and Azure Container Apps + free Postgres to keep costs at zero while we validate.

Building in public questions/roasts welcome

p/caresse

•

1d ago

Which feature would you add next to Caresse?

Long-distance mode
More voices
Apple Watch support
?

p/caresse

•

1d ago

What’s more important during Caresse audio session?

What s more important during Caresse audio session?

Personalization
Voice quality
Story
Sound design
?

View all