Audio-to-Video with LTX-2
LTX-2 is an open-source diffusion model that combines video and audio. Visually it's not at the level of Seedance 2.0, Veo 3.1, or Sora 2, but it’s open-weights, so anyone can play with it. I wanted to see how good it is at generating video from just audio. Off-the-shelf, it's not very good, but I found that if you run the audio through Gemini to generate a prompt, then feed that into LTX-2, in addition to the audio, the output matches the audio much more often. Foley sounds work particularly well, and one fun use case is uploading audio of yourself to see what AI thinks you look like.…
Audio-to-Video with LTX-2 launched on March 2, 2026 with 23 votes, #838 of 23,380 launches that month and more than 90% of that year's launches.
In plain words
LTX-2 is an open-source diffusion model that generates video from audio input. The tool works best when audio is first processed through Gemini to create a text prompt, which is then fed to the model alongside the audio. It performs particularly well with foley sounds and can generate video interpretations of uploaded voice recordings. Limitations include difficulty with famous voices, occasional gender misidentification, and confusion when rendering dialogue with similar-sounding speakers. The model produces lower visual quality than some proprietary alternatives but remains accessible for experimentation.
written from the facts on this page · September 2026
From the sources
Free audio to video AI generator. Convert any audio into a matching video — upload audio, optionally add a starting image and prompt, and generate synced visuals. No sign up needed.
In the maker’s words, at launch
LTX-2 is an open-source diffusion model that combines video and audio. Visually it's not at the level of Seedance 2.0, Veo 3.1, or Sora 2, but it’s open-weights, so anyone can play with it. I wanted to see how good it is at generating video from just audio. Off-the-shelf, it's not very good, but I found that if you…
Does a similar job
all alternatives →
LTX.bio2021 · lightricks.com · ▲164Hey HN, after our 13B release we've been working on a faster version of our open-source video model and we're excited to share it. We started with a 13B base model that already had competitive generation speeds (e.g. 55s for a 5s video on an H100 — faster than any other model out there). But we wanted to push it further to allow everyone to quickly iterate over their video generations. So we built a distilled version focused on speed without sacrificing temporal or spatial coherence. With the Distilled model, you can now generate 5-second 720p videos in about 9.5 seconds on an H100, and…
SFX Engine2024 · sfxengine.com · ▲137I’ve been building SFX Engine, an AI audio playground, and just launched a DJ transitions feature. You drop in two songs, and the app generates a clean, beat-matched transition, just like how a DJ would make! Would love any feedback!
- IBI built a tool to replace capcut audio transcription2025 · meetcosmos.com · ▲26
I originally added this to my site to speed up my video editing process. Last year I started a youtube channel and for some of my longer videos it's annoying to rely on youtube or capcut to transcribe when Whisper is open source. Capcut also recently updated their T&Cs to say they own your content if you use their app, so I cancelled my subscription. Another use-case I have is recording my claude prompts as audio, transcribing them, and then pasting them into my terminal. I mostly work on the CLI (claude, ffmpeg, whisper), but I wanted to make a browser version. Not reinventing the wheel…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
