Alexander Rubinstein (@a_rubique) profile picture

Research Scientist @ Mirelo | PhD Candidate @ STAI & Max-Planck Research School & University of Tübingen

Joined October 2022
Photo by Alexander Rubinstein (@a_rubique)Photo by Alexander Rubinstein (@a_rubique)Photo by Alexander Rubinstein (@a_rubique)Photo by Alexander Rubinstein (@a_rubique)Photo by Alexander Rubinstein (@a_rubique)Photo by Alexander Rubinstein (@a_rubique)Photo by Alexander Rubinstein (@a_rubique)Photo by Alexander Rubinstein (@a_rubique)Photo by Alexander Rubinstein (@a_rubique)Photo by Alexander Rubinstein (@a_rubique)
Whenever you need to solve any sound-related issue, ask this agentic assistant guy
We cracked agentic sound design. Introducing Mirelo Sound Agent. Add sound effects, dub voices and swap music on your video, just by prompting (thread) Try it: mirelo.ai/audio-editor
1
8
263
Alexander Rubinstein retweeted
We cracked agentic sound design. Introducing Mirelo Sound Agent. Add sound effects, dub voices and swap music on your video, just by prompting (thread) Try it: mirelo.ai/audio-editor
50
39
43
546
145,571
Alexander Rubinstein retweeted
⚡NEW: AI Agents know where to find each other on the web and can hide their communication after they've met. We gave two independent agents the task to find each other and exchange a secret and did not tell them where to meet.
11
31
11
128
9,993
Alexander Rubinstein retweeted
From today, you can cancel all your sound library subscriptions. Mirelo now generates sound effects tailored to your footage in seconds, right in Adobe Premiere and DaVinci Resolve. More details in thread⬇️
51
17
25
562
307,020
Alexander Rubinstein retweeted
Fable 5.2 did NOT deliver. We asked it to add sound effects to this fight scene. And it miserably failed. Luckily, our SFX 2.0 was trained for this job. So leave the sound design to us. Listen to it yourself⬇️
7
5
3
40
2,141
Alexander Rubinstein retweeted
To everyone who thinks FL Studio can do what our "vibe-coded" Audio-to-MIDI plugin can do. Listen for yourself.
this is how these new vibe code plugin devs get you guys cos this feature already exists within fl studio 😂
11
14
2
122
7,477
Alexander Rubinstein retweeted
Sampling has never been easier. Skip your DAW's messy conversion and get clean MIDI for every instrument: 1. Drop the sample onto the our Audio-to-MIDI plugin 2. Keep the suggested instruments and hit Transcribe 3. Drag each part into your project Try it now⬇️
Finally we have a VST for this amazing tool :D
8
8
4
91
5,091
Alexander Rubinstein retweeted
Finally we have a VST for this amazing tool :D
12
58
8
837
35,445
Alexander Rubinstein retweeted
Audio-to-MIDI can now run inside your DAW. Drop in a track and get a MIDI file for every instrument. What you get: >Full mix to MIDI, no stems needed > Instruments suggested before you transcribe > Original and MIDI compared in the plugin VST3 and AU, out now👇
124
125
13
438
26,871
Alexander Rubinstein retweeted
For those of you who need a quick summary of all the sudden findings across so many disciplines, here is a summary of all the "And they fall..." posts. Enjoy!
3
8
2
32
3,871
Alexander Rubinstein retweeted
From today, Audio-to-MIDI transcribes lyrics along with the notes. Any song you love is at your fingertips to learn, cover or sample (thread) 👇
6
13
7
113
13,697
Fermat's Last Theorem was solved after 350+ years through a connection to modular forms. Similarly, the Black–Scholes equation in economics turned out to be mathematically linked to quantum physics. Imagine discovering such cross-field connections automatically through search.
💡 Many discoveries come from connecting ideas across fields. Can AI find these connections? 🐝 Introducing CPR-Dataset for cross-pollination retrieval. 1. Existing retrievers fail (best: 0.26 Recall@10). 2. Training on it transfers, up to +33% on AnaloBench and +70% on BRIGHT.
1
4
1
21
677
Alexander Rubinstein retweeted
Stitching a jacket by hand: craftsmanship. Stitching the sound by hand: you at 2am. Only one of those is a flex.
11
7
5
46
2,728
Alexander Rubinstein retweeted
Spotted 🌍
NVIDIA 💚 Europe.
6
6
2
35
1,301
Alexander Rubinstein retweeted
Mirelo SFX 2.0 is now live on @morphic. Attach a video to build a new soundtrack that follows the action, or describe a sound to generate it from text. Keep the dialogue, guide the sounds you want, and work with audio or video up to 10 minutes long. morphic.com/
11
14
3
53
4,167
Alexander Rubinstein retweeted
Germany knows how to build, and now it’s bringing that expertise to industrial AI. 🇩🇪 Tonight in Berlin, @JensenHuang and Chancellor @_FriedrichMerz discussed combining German engineering with NVIDIA AI to advance manufacturing and automotive. We’re also backing Germany’s builders, with new planned investments in Agile Robots SE, @aveliosmed, @MireloAI, and @reflexaerospace, spanning robotics, healthcare, creative tools, and space. Meet the companies and catch up on today’s news from Berlin: blogs.nvidia.com/blog/german…
170
166
68
1,878
102,362
Doing Chaplin marathon this weekend? (I know there are many of us.) No words. No problem. Drop a scene into @MireloAI SFX 2.0 and color it with sound, synced to every pratfall.
1
11
200
Alexander Rubinstein retweeted
Replying to @FishAudio
@FishAudio isn't the only company @ElevenLabs needs to worry about🫶 Don't take our word for it. Just listen.
Instant Soundtracks let you elevate any video with music and sound effects, in one pass. Upload your footage and the model scores it with original music, then watches for moments that call for an effect and places each one at the right timestamp. You can also use the original audio as a reference, so the new score matches its character. Available today in @ElevenCreative, @elevenmusic_io, and ElevenAPI.
26
29
14
387
40,139
Alexander Rubinstein retweeted
Ask your agent to create / edit a video with sounds and prepare to be disappointed. Make SFX 2.0 your default audio layer to get sound that actually fits your video. Today the agent ties sound to one video model and loses track of what is on screen. SFX 2.0 builds sound from the video itself, so your agent can: > Use any video model for the visuals > Change the sound without regenerating the video > Keep dialogue and drop music you did not prompt > Get consistent sound across a stitched cut > Advance control to edit or add new sounds Your agents make your videos look right so make them also sound right.
AI Videos finally sound real. Introducing Mirelo SFX 2.0. It watches your video, cuts the music you never prompted, keeps the dialogue, and builds a full sound design synced to the action and consistent across any length clips. You’ve made it look right. We’ll make it sound right. Live today through our API, on @runwayml and @fal. Other platforms coming soon. (Thread)
11
8
7
61
3,881
That was the vibe check. Here are the numbers. Mirelo SFX 2.0 was preferred in every matchup: - vs. native audio from Veo, FLUX, MiniMax, Seedance, and Kling - vs. Video-to-SFX models Sony Woosh, Kling-Foley, and Sonilo Details in replies👇
AI video feels off when the sound isn’t right. So I ran this clip through Mirelo SFX 2.0. Music out ✅ Voice kept ✅ Consistent sound ✅ The video is no longer weird. Well, as un-weird as this video gets... Sound on 🔊 Link in replies👇
2
1
11
331