LatentScore – Type a mood, get procedural/ambient music (open source)
Hey HN, I've used Generative.fm for years and love it, but I always wanted to just describe what I was in the mood for instead of scrolling through presets. So I built this. You type a text description of anything - from "mountain sunrise" to "neon city" - and it generates a procedural/ambient stream matching that mood. It runs locally, no account, no tracking, no ads. Under the hood it's a custom synthesizer driven by sentence embeddings, not a generative AI model (although you can choose to use one!) — so there's no GPU, no API calls, and it starts playing almost instantly. The whole…
In plain words
LatentScore generates procedural ambient music based on text descriptions of moods or scenes. Users type descriptions like "mountain sunrise" or "neon city" and receive a matching audio stream that plays instantly. The tool runs locally without requiring accounts, tracking, or ads. It uses a custom synthesizer driven by sentence embeddings rather than a generative AI model, eliminating the need for GPU processing or API calls. The open-source software is available as a web player and Python library, making it suitable for both casual listeners and developers seeking programmatic audio generation.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, I've used Generative.fm for years and love it, but I always wanted to just describe what I was in the mood for instead of scrolling through presets. So I built this. You type a text description of anything - from "mountain sunrise" to "neon city" - and it generates a procedural/ambient stream matching that mood. It runs locally, no account, no tracking, no ads. Under the hood it's a custom synthesizer driven by sentence embeddings, not a generative AI model (although you can choose to use one!) — so there's no GPU, no API calls, and it starts playing almost instantly. The whole thing is open source: https://github.com/prabal-rje/latentscore If you're a developer and want to use it programmatically it's also a Python library - pip install latentscore — one line to render audio. But honestly I just use the web player myself when I'm working. Fair warning: it's still alpha and the synth has limits, so please don't expect full songs or vocals. It's ambient/procedural only. But for focus music or background atmosphere, I think it's pretty good. Would love to know what vibes you try and whether they land! - Prabal
Does the same job
all alternatives →
- AAAn algorithmic audio landscape2024 · ambient.garden · ▲193
This is an web audio experiment I've been wanting to do for a long time. Basically an ambient music composition, but all the sound elements are laid out in space, and that musical space can be explored freely. It's definitely inspired by in-world music that sometimes appears in games. I basically took that concept, keeping the music aspect, and dropping the entire "game" aspect. I also turned it into a more "traditional" non-interactive album, but since I started with code, why not program the whole thing? Had a blast making the entire album from code, the complete source for the album is…
- SASonauto – A more controllable AI music creator2024 · sonauto.ai · ▲454
Hey HN, My cofounder and I trained an AI music generation model and after a month of testing we're launching 1.0 today. Ours is interesting because it's a latent diffusion model instead of a language model, which makes it more controllable: https://sonauto.ai/ Others do music generation by training a Vector Quantized Variational Autoencoder like Descript Audio Codec (https://github.com/descriptinc/descript-audio-codec) to turn music into tokens, then training an LLM on those tokens. Instead, we ripped the tokenization part off and replaced it with a normal…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
