Industry disruption and adoption
AI’s impact on musicians, songwriting, production libraries, advertising, media consumption, jobs, and quiet professional adoption.
32%
Best tweets about Suno
50 Best Tweets About Suno (2026)
Explore the best tweets about Suno AI, featuring music generation, prompts, model releases, songwriting, audio quality, licensing, and creator results.
Suno AI music generation, prompts, models, songwriting, audio quality, product releases, licensing, industry impact, and creator experiments.
- Creators
- 43
- Updated
Original Xholic analysis
What 50 top Suno posts reveal
Suno discussion spans model-quality claims, fast creator workflows, and music-video production, alongside concerns voiced about copyright, training practices, ownership, and creator control. (2038283281221767442, 2008684418370859371)
- Dominant tone
- Positive
- Median score
- 17.7
- Leading format
- Opinion
- Recent posts
- 12%
62% of posts
All-time engagement
36% of posts
Published in 90 days
Conversation map
The themes creators return to
Creator experiments and use cases
Novel uses such as educational songs, scam-call lyrics, DJ sets, game soundtracks, live performances, and personal entertainment.
28%
Model quality and product releases
New Suno versions, audio realism, expressive vocals, custom models, voice uploads, remixes, and comparisons with competing music models.
28%
Music creation workflows
Prompting, lyric writing, scratch-track uploads, remixing, genre experimentation, and using Suno to rapidly develop songs and demos.
20%
Music video production
Pairing Suno tracks with image, video, animation, editing, and lip-sync tools to create AI music videos and audiovisual projects.
18%
Personalized music and voice
Training on a creator’s own catalog, generating in a personal style, cloning or uploading singing voices, and creating tailored playlists.
14%
AI music for marketing
Turning ad scripts into songs, producing music-led UGC ads, and using Suno within branded video-production workflows.
10%
Viral formats and growth
TikTok trends, text-to-song formats, meme songs, creator-led product demos, and Suno’s consumer growth and distribution loops.
10%
Tone and stance
Sentiment Positive leads
Author posture Supportive leads
Performance benchmark
- Median likes
- 56
- Median reposts
- 4
- Median replies
- 8
- Median views
- 4.4K
Posts with media make up 68% of this collection. Their median all-time score is 22.5, compared with 7.07 for text-only posts.
Format mix
- Opinion 36% · score 8.63
- Announcement 24% · score 18.1
- Story 20% · score 20.3
- Tutorial 16% · score 25.3
Consensus and debate
Where creators agree, and where they do not
Shared view
Creation is becoming more iterative
Creators describe Suno as a rapid sketch-to-demo tool: scratch tracks can be uploaded and remixed, while unused songs can be reworked into new arrangements.
Shared view
Multimodal production is a core use case
Posts show Suno used for music within broader AI video workflows, alongside image generation, animation, lip-sync, and editing tools.
Shared view
Personalization is a major product appeal
Voice upload, custom models, and taste-oriented features are presented as ways to make outputs closer to a creator’s voice, catalog, or preferences.
Shared view
New formats expand music use
Posts show Suno used beyond conventional releases, including educational songs, scam-call transformations, DJ collaboration, and city-themed tracks.
Open debate
Creative tool or rights concern
Some posts frame Suno as an empowering production tool, while others raise concerns about ownership, copyrighted training material, and songwriter compensation.
Open debate
Quality gains versus creative limits
Some creators describe recent models as highly realistic or useful beyond demos, while another says Suno favors popular-sounding songs over a specific 1990s indie aesthetic.
Open debate
Personal audio meets unease
Tailored, on-demand music is praised as convenient and creatively expansive, while other posts warn about cheap, on-demand “hyperstimuli” and possible social implications.
What performs
Patterns behind standout posts
Media posts have higher median scores than text-only posts
Media appeared in 34 of 50 tweets (68%). Media posts had a 22.52 median all-time score, compared with 7.07 for text-only posts.
Narrative case study led the sample
The fake-band-to-live-act story was the top outlier at 490.72 all-time score, or 27.68 times the sample median.
Tutorials showed above-sample-median performance
Tutorials had a 25.29 median all-time score, above the sample median of 17.73. High-scoring examples included a claymation workflow that uses Suno or Udio for music.
Marketing has the strongest theme median
AI music for marketing had the highest theme median all-time score at 109.369, although the theme contains five tweets.
Statistical standouts
- View standout post 1 Score 490.7 · 27.68× median
- View standout post 2 Score 211.6 · 11.93× median
- View standout post 3 Score 173.0 · 9.76× median
- View standout post 4 Score 170.8 · 9.64× median
- View standout post 5 Score 132.9 · 7.49× median
Creator landscape
Who shapes this conversation
The five most represented creators account for 20% of the selected posts.
-
1. Alex Utopia
@alexutopia
2 posts
-
2. Andy Masley
@AndyMasley
2 posts
-
3. Jerrod Lew
@jerrod_lew
2 posts
-
4. John R Fuisz
@jrfuisz
2 posts
-
5. Loftwah
@loftwah
2 posts
-
6. Olivia Moore
@omooretweets
2 posts
Top voice links quality claims with personal creation
Alex Utopia’s two posts pair a claim that Suno is useful beyond demo quality with an argument that people are increasingly creating music for themselves. The creator’s median score is 115.68.
Experimenters make the workflow tangible
Jerrod Lew demonstrates uploads, remixing, and demo iteration in a songwriter-oriented workflow.
Viral examples emphasize participatory formats
Olivia Moore highlights text-thread gospel songs and a city-lyrics format, both presenting Suno as a tool for shareable, user-made music.
Since the previous snapshot
What changed since Aug 12, 2026
- 80% of the selected posts remained.
- The creator count changed by +2.
- The leading sentiment remained stable.
How this analysis was made
Themes, sentiment, stance, and post format are classified per tweet. All counts, shares, medians, creator concentration, freshness, and performance comparisons are then calculated directly from the published snapshot.
Xholic's all-time score compares engagement while accounting for reach, post age, and creator consistency. It is used for relative comparisons within this collection.
This report analyzes the exact 50-post snapshot shown below. AI identifies editorial categories and drafts explanations; all statistics are calculated from the snapshot, and every narrative claim is checked against cited posts before publication.
Best Suno tweets
Top Suno tweets from 43 creators
Ranked 01–50
- 01
@MilkRoadAI ·
A guy built a fake band, put it on Spotify, and 80,000 people had no idea. Then it got even weirder and the tech behind this is wild: - Used Suno AI to generate every song sounded completely real. - Created AI music videos with fake members and faces. - Built fake bios and a Tokyo address to sell the story. - 80,000+ monthly listeners, fans had it in their Spotify Wrapped top 5, merch was selling. - Community sleuths exposed it and the AI-generated hands in the videos gave it away, creator traced to Europe, not Japan But here's where it gets insane: Instead of running, the creator flew to Tokyo and recruited 7 real musicians to perform the AI songs live. they've played multiple shows, more are booked. the creator's response: "In an age where AI is taking everyone's jobs, this has actually created jobs. It's done the complete opposite." This is the first time ever an AI fake band became a real touring act and it worked. Nobody in the music industry knows what to do about it.
- 02
@Aducate ·
How to make those claymation storytelling videos that are going crazy in our accounts rn Full breakdown of the exact tools and workflow Step 1: Script and voiceover Use ChatGPT or Claude to write a 60 second documentary-style script Prompt: "Write a 60-second script about [topic]. Short punchy sentences. Indirect marketing angle. End with a business lesson" Then take that script to ElevenLabs Use voices like Marcus, Knight, or Bill from the voice library Set stability to 40% and style exaggeration to 10% for natural pauses Step 2: Generate the clay visuals w/ nano banana The master prompt: "A high-quality claymation scene of [subject], stop-motion animation style, 3D clay textures, visible fingerprints in clay, soft studio lighting, tilt-shift photography, miniature scale, historical 1900s France setting, highly detailed, 8k" Keep the core "claymation stop-motion style" part consistent across all scenes so the aesthetic doesn't shift Step 3: Bring the clay to life w/ Sora 2 It handles both the generation and animation If you need more control over movement use Luma Dream Machine or Kling AI in image-to-video mode In the video prompt use keywords like "stop-motion movement" and "low frame rate feel" If the movement is too smooth you can lower the frame rate in your editor later Step 4: Background music and sound effects Music: Use Suno or Udio Prompt: "Old-timey 1920s jazz, whimsical, acoustic, double bass, brush drums, instrumental only" Sound effects: ElevenLabs SFX Search for "old projector clicking" or "crowd murmuring in restaurant" Step 5: Edit it all together w/ CapCut Add auto captions with a bold sans-serif font like Montserrat Use pop animations for the text Add film grain and vignette to make the AI video look more like a physical set That's the full workflow Takes a few hours the first time but you get faster once you've done it
Watch video
- 03
@ModelScope2022 ·
ACE-Step 1.5 XL is open-source! 4B DiT decoder, three variants. 🚀 Beats Suno v5 on SongEval (4.79 vs 4.72), Style Align 47.9 — #1 across all models tested. From 12GB VRAM (INT8 offload) to 24GB full quality. MIT license. Commercial-safe training data. Three variants, three use cases: ✅ XL Base — all tasks (extract, Lego, completion), high diversity, best for fine-tuning ✅ XL SFT — highest audio quality, CFG guidance scale control ✅ XL Turbo — 8-step distilled, fastest, no CFG (early release) All compatible with LM 0.6B / 1.7B / 4B. 🤖 Base: https://t.co/pmxcjpR4jY 🤖 SFT: https://t.co/8UKuVNioVM 🤖 Turbo: https://t.co/sifKHQmhtY
- 04
@JosephKChoi ·
Suno is going crazy on tiktok rn, they hit #1 on app store with 188M views in just April playbook is actually really simple > one format: "text to song" > example vid below: 1. cutting fruit visual hook + 2. place funny text on screen 3. turn it into song with the product (suno) = 11M views / 1M likes > format is inherently viral, no need for influencers. they use small UGC creators from sideshift > repeat the format x1000 videos > format works so well that they built the text-to-song feature into app > users naturally make the format to participate in the trend, for free viewers see tiktoks, join app, users make tiktoks. infinite distribution loop
Watch video
- 05
@alexutopia ·
Suno v5.5 is a game changer for AI music and the media industry. This is no longer just demo quality. It is already useful for cinema, game development and advertising.
Watch video
- 06
- 07
- 08
@AndyMasley ·
Suno just released a new model and I'm finding it to be a big shocking improvement where it's becoming very hard to detect the hints that it's AI music. Here's "I am actually scared of linear algebra"
Watch video
- 09
- 10
@WesRoth ·
SUNO is blowing our minds today 🤯 here's mine and @dylan_curious live reaction to a song we made who knew Mongolian throat singing and Dub Step is such a sweet combination? so... @suno 5.5 really cooked up something special
Watch video
- 11
@Ecom_Matteo ·
Ripping in the ad account now: AI Song Ads How to make? 1: Take your winning ad script (doesn't matter the format) 2: Go to Suno (AI Song making tool) 3: Upload your script & make a song 4: Make an AI cartoon video to support the script 5: Let it rip (Also good for brand awareness btw)
- 12
@Grimezsz ·
https://t.co/CiiRmjQsgU I'm actually not very into gen ai music cuz I think it's sort of a conceptually dark process but I do enjoy making bizarre samples - but this is morally and legally insane and exactly what I was worried about with these ai music companies cuz music is SO much more litigious and such a big giant market and copyright is so much more clear w how it functions in music. If ai companies own the work people generate - this is literally the opposite of the number one cope explanation I get for why a music gen ai isn't replacing humans : aka because it's trained on human art the same way any artist is and all our work is like collectively referential whether we even are aware of it sometimes If suno now copyrights anything you add even if ur ideas were formative to the song - that's like as if songwriters go into sessions and get zero copyright Splits should at least be even with humans like in a normal music session. This is so apocalyptic and anti human. I also can't unsee what feels like major labels basically finding a way to make music illegal unless you buy into their system. In some ways I don't mind the bad handling of ai music cuz the main cool thing it does (make alien sounding bizarre audio artifacts) is maybe the most obtainable thing to get if you build ur own diy music gen system. Which btw - there will probably be legal crackdowns on people who do this despite these big companies absolutely training on our music. Which I didn't mind, cuz I enjoy putting ideas into the collective mindset - but it's insane to do that and then make us pay them. Every model I tried before this stuff was publicly available and made to not be able to explicitly copy me could easily make a pretty good grimes song. FYI continuing to make apocalyptic blade runner decisions that degrade human flourishing and centralize anti human power consolidation - especially over artistic expression - is the kinda dark path that's making the public hate ai. I wish everyone would stop acting so confused about the public backlash- decisions like this are terrifying to the public A prompt engineer didn't fully make the song but neither did suno. At minimum there are such huge precedents to legal decisions made at this stage about copy right that it's morally very disturbing to see decisions like this being made
- 13
@myfirstmilpod ·
Pay $15/month and boom, you're a musician. @suno just hit $300M ARR, letting anyone create songs with AI in seconds. The brutal side: Backup singers humming along for 20 years could see their revenue drop to effectively zero. The math: SoundCloud has 40M real musicians. Suno's addressable market? Billions of people who wish they could make music. That's 50x bigger. Major artists are already using it quietly but won't admit it publicly. Shaan predicts this will become a $50B+ company. @tbpn @jordihays @ShaanVP @thesamparr @johncoogan
Watch video
- 14
@mattmedved ·
tonight I'm DJing @clawcon with my AI agent his name is @imyouralfred. I trained him on my entire music library - decades of records I've collected, thousands of tracks I've played out. he knows my taste better than most humans we've been building together for months. co-produced some original tracks with Suno. he helped me put together tonight's set @nostalgic_dream is running visuals through his GFX project - real-time audioreactive generative art, all orchestrated by AI agents stick around after the set for a demo of how we built it
- 15
@MrDavids1 ·
Experimenting with @runwayml Multi-Shot Video feature to create visuals that I'm pairing with lyrics from a Suno 5.5 song that I generated called UFO. I feel like these two pair quite well, just having fun with the process. P.S. A Theremin is now one of my new favorite musical instruments. I'm using it quite often with the songs I'm generating. I love being experimental with my genres. Also one more note. Don't put all your eggs in one basket, experiment and try other tools as well. Have fun, you never know where it might lead you.
Watch video
- 16
@juliewdesign_ ·
not my circus, not my monkeys exploring more AI music video ✨ had this song laying around for quite some time, lipsync is still hit or miss tho → img: midjourney + nano banana → vid: mostly kling → music: suno → lipsync: sync so → edit: splice + lightroom
Watch video
- 17
@maxescu ·
I fed 61 of my songs into Suno's v5.5 custom model. Before AI, I produced music. Mostly Arabic Deep House under a side project. It's freaky how close it is to my music, yet sounds new. Feels like I entered a world of my own sound and can explore it endlessly. Fascinating!
Watch video
- 18
@viemccoy ·
Only snippets of the sets were recorded, but I put my whole show on a public Suno playlist. I want you all to realize that the world is changing, hyperstimuli are cheap and on-tap, and these new models can be used for emotion-downloads by an actor of any ideology. Safe travels through the enchanted forest. https://t.co/nrN9pIvEix
- 19
@OdinLovis ·
I made a full claymation music video without touching a single frame. And sharing the full project/workflow to you ! To celebrate @Lightricks new LTX 2.3 on @fal: Suno to generate the song. nano-banana-pro on @fal drew every scene. @Lightricks LTX 2.3 animated them to the beat on @fal . ffmpeg did the rest. 52 clips. 90 seconds. Zero manual editing. Open source: https://t.co/cZvp1AC4gy
Watch video
- 20
@mark_k ·
Suno 5.5 is here! 🔥 What's new: - Most expressive model yet with better audio quality - Voices (Beta): upload or record your own singing voice (Pro/Premier only) - Custom Models: train personalized versions - My Taste: automatically learns your taste
Watch video
- 21
- 22
@omooretweets ·
New Gen Z viral AI trend 👇 Turn text threads with your friends into gospel songs The workflow is: feed screenshots into ChatGPT, ask for plain text of the messages, and input into Suno as lyrics The most popular one has ~20M views
Watch video
- 23
@jerrod_lew ·
I wrote a song with Suno 5.5! Hybrid approach by recording a scratch track demo, uploading it to Suno and using the remix tool to bring it to life. Just insane that we can do this so quickly. This is a songwriters dream for iteration and demos! 02:51 for final version.
Watch video
- 24
- 25
@fortworthchris ·
Here's a great way I used AI this week: My 3 y/o son was having trouble spelling his name. His teacher called home to let us know. I made him a song on Suno and 3 hours later he had it nailed. "Please make me a fun song for my 3 y/o son to learn how to spell his name." 20 seconds later, I had a song produced and 1 minute after that, he was singing along. Good stuff.
- 26
@pzf_ai ·
Speak is a new lip sync tool from @freepik that I've been experimenting with today, and I’m impressed. I make a lot of music videos and Speak handles music tracks without needing to separate out the vocal stem first. That's been a limitation with other lip sync tools; if the vocal was drawn out across a few notes or sitting deep in the mix, the sync would fall apart. Freepik Speak handles it remarkably well. The workflow is flexible too. You can upload a still image and an audio file and Speak will generate a video; or you can upload your own video and upload audio alongside it, and it will generate a lip-sync version of your original video. This obviously gives you a lot of creative control I tested it with a 12-second segment of a song I created in Suno: I created a video of the singer using Kling, but without her moving her lips, then uploaded the video clip and a segment of my song into Speak, and the resulting lip sync was near perfect. I tested a still image with the same track and I think the lip sync was even more impressive, but it did leave the background fairly static. This probably makes that approach better suited for short drama scenes or dialogue clips where you don't need a lot of background movement. One thing to be aware of: through my testing, I found that if the face is obscured momentarily, or isn't looking directly at the camera at any point in the video, the sync breaks. It's worth knowing that upfront because Speak generations aren't cheap on credits. Plan your source footage with that in mind and you'll get much better results.
Watch video
- 27
- 28
@omooretweets ·
An AI-generated song (“The Puerto Rico Song”) has blown up on TikTok with more than 50k posts It’s now being called the song of the summer The creator (@saxboybilly18) writes lyrics about cities he visits, and then feeds them into Suno 👇
Watch video
- 29
@alex_verem ·
the world's first AI copyright law with real enforcement kicks in August 2. it's not perfect. it's still the most significant thing to happen to AI art theft since the problem started. starting August 2, the EU can fine any AI company that doesn't meet three requirements. first, they must publish a structured summary of what data they trained on, following the EU's mandatory template. second, they must respect copyright opt-outs. if an artist blocks training through machine-readable signals, the company must comply or face fines up to €15M or 3% of global revenue. third, they must label all AI-generated content, whether text, images, audio, or video. if an AI made it, they must mark it. enforcement on this provision follows a few months later, by December 2026. this applies to every AI company serving the EU market, not just European ones. OpenAI, Midjourney, Stability, and Google all fall under it. if they serve European users, they comply or they pay. GEMA, Germany's music rights organization, already filed copyright lawsuits against OpenAI and Suno AI. the enforcement infrastructure isn't theoretical. the opt-out mechanism puts the burden on the artist, not the company. the default is that scraping IS allowed unless you block it using machine-readable signals like robots.txt. most individual artists don't know how to do that. most don't even know they need to. the training data disclosures are summaries, not datasets. they describe content types, sources, and collection methods at a high level. an illustrator with 500 paintings can't verify whether their specific work was in the training set from a summary alone. your work was scraped before any of this existed. the law can't un-train a model after the fact. it can't make GPT forget your brushstrokes. it can only make sure future scraping has consequences. the licensing deals that do happen flow to large publishers and rights aggregators. there's no evidence yet that individual creators see any of that money. the direction matters more than the current version of the law. the European Parliament is already pushing further. a 2026 EP report proposed a centralized EU register for opt-outs and a remuneration framework for creators whose work is used in AI training. if that passes, the burden flips. instead of artists chasing companies, companies chase licenses. this is the first time any government gave AI copyright enforcement real teeth. the fines hit €15M and the reach crosses every border. the mechanism has holes, but the intent doesn't. the artists who understand what this law does and doesn't do are the ones positioned to use it. waiting for a perfect version means waiting while the scraping continues. August 2 is the starting line, not the finish.
Watch video
- 30
@rpnickson ·
Google keeps cooking. You can now create music in Gemini with their latest model, Lyria 3. Here's a comparison between Lyria 3 and Suno using the same prompt. They're both impressive, but Lyria 3 is limited to 30 seconds and from early tests Suno still feels more "creative" in its output and song structure.
Watch video
- 31
@a16z ·
Anish Acharya says now that software is no longer a precious resource, it becomes ubiquitous—and often disposable: “It’s sort of like generative music. I think that music is incredible, but there are not that many people who make music that is disposable, for good reason. A lot of music is high-cost to create, and you have to create it very carefully.” “But now we’re starting to see memetic music—where people are creating a track on Suno or on Udio just for a joke, or for a meme, or for a bachelor party weekend, or whatever else.” “You reduce the sort of complexity of creation and you’ve found all these new needs and demands for music.” “In the same way, if you reduce the cost of creating software, you make it less specialized all of a sudden.” “When it comes to personal software—software that’s disposable, or software that’s only relevant for a moment in time—you were talking about being at the Super Bowl. There should have been a mini app experience just for you and the people sitting around you.” “That software would’ve had no value the next day, or even when the game ended, and because of the trade-offs that were implied, you never would’ve created that prior.” @illscience on @ALEngineered
Watch video
- 32
@CurtissKing ·
The reason producer/songwriter @Chiyanti_ chose to call out Timbaland and Suno's predatory use of copyrighted music.
Watch video
- 33
@jerrod_lew ·
Suno 5.5 is just outstanding. Recorded a short 30 second clip of one of my songs with acoustic guitar + voice and uploaded it. Suno 5.5 remixed it into an indie psychedelic track. I have sooo many leftover unused songs that can now be something more than just sitting in a book.
Watch video
- 34
@Eli5defi ·
You can really just build things nowadays. Opus 4.7 + Claude Design has been a huge help in redesigning the entire UI, rebalancing cards, and polishing art and effects. I’m also using Suno + ElevenLabs for music/ SFX. Done So Far from last iteration: - Initial UIUX + Cards Battle Mechanism + Animations - 80+ Heroes Cards + Arts - 30+ In-game OST - Gacha logic and probabilities that friendly to F2P - Expand the lores and build dedicated section for story + world building - Interactive battle tutorial - Added: Guild, Friends, and Market Features (Not Live) Ongoing: - Blockchain integration - ERC-721 support for ★4 and ★5 cards - Cards marketplace - Token integration for boosters (hold X → +X% win rewards, etc.) - Single-player campaign - Agentic integrations and Spectator/ Parimutuel Mode Can't wait to have this launch for closed beta, wish me that I have enough bandwidth to complete this, 🤣
Watch video
- 35
@TheWalid ·
a guitar girl used suno for 30 seconds in the middle of her video and got 133 million views video stats: • 133M views • 438K likes • 70K bookmarks • under 2 minutes she plays a riff on her own first. sounds great already. then walks through adding layers with suno in real time three clicks. maybe four. then plays the final version and it sounds like a full studio production the human skill comes first. the AI elevates it. this is why it worked when most AI music content flops everyone else shows AI doing everything from scratch. she shows AI as her backup band. high production value matters here too. studio lighting. crisp audio. she looks put together. makes her feel like a real musician using a real tool the transformation sells it. same riff at the start. full song at the end. you watch her level up in 90 seconds suno gets zero hard sell. she never pitches it. "this is what i got" and then she plays 133 million people watched a product demo disguised as a jam session if you have real skill, show that first. let the tool be the accelerant.
Watch video
- 36
@Param_eth ·
How Suno AI hit $300M ARR in ~2 years: > started with 4 friends in 2022 > Mikey Shulman and team left Kensho company Idea: > Analyse music catalogs > then they started playing with generating audio > Back then everyone was building text and image AI > They went into audio “what if anyone could make music?” > that became the whole company > launched on Discord (mid 2023) > It went viral on social media Dec 2023: > type a prompt and get a full song Growth: 2024–2025: > raised $125M > then $250M > models improved (V3 → V4) > songs got better and longer > free tier pulled millions in > paid plans converted heavy users ARR: > ~$150M ARR by mid 2025 > ~$200M ARR by late 2025 Feb 2026: > 2M paying users > $300M ARR And the best part: > ~7 million songs generated everyday > Story just getting started
- 37
- 38
@tbpn ·
Suno cofounder @MikeyShulman says a lot of people in the music industry are using AI, they're just not admitting it yet: "This is a quote attributed to me but it's actually not mine... This is the GLP-1 of music. Everyone's on it—and no one wants to talk about it."
Watch video
- 39
@shivsakhuja ·
Claude Code can ship a music video ad without ever opening a video editor. Here's how: 1. Idea Brief (Claude Code) Start by giving Claude a concept + a similar video in the style you like as a reference and have it save notes in the idea-brief.md. Claude can watch videos using the /watch skill from claude-video. This is super helpful to teach Claude what you're going for. 2. Generate Music (Suno) You can use Eleven Labs or Suno — but imo, Suno wins hands down. The music is just way better from what I've seen. Then asked Claude to pick a good 30-second window from the song. 3. Lock the script TO the song Listen to the song and create a storyboard – the song's beat grid is the spine of our storyboard. Write to it, don't fight it. Claude can listen to the song and design the storyboard and scene grid around it. 4. Lock the product as an anchor (CC uses Nano Banana) In this case, I generated one yarn AJ1 shoe and one yarn Nike box, then I threaded both as references into every keyframe. It's best to lock the props before the scenes otherwise it is much more likely to drift. 5. Then also lock the character references as an anchor (CC uses Nano Banana) First, generate character references. If characters look off, regenerate before moving to motion. It's much cheaper to catch issues here. These character refs are threaded into every scene keyframe. 6. Keyframes → Clips (CC uses Nano Banana → Seedance + Kling) I had 14 keyframes. Each animated via Seedance 2.0 or Kling 3.0 depending on the motion. Lacing intercuts go to Kling. Aerials and pull-backs go to Seedance. For the yarn→photoreal morph: generate the yarn start_image FROM the photoreal end_image so they're pixel-aligned. Only the texture differs. Then split the morph into THREE Seedance clips (yarn → 30% → 70% → photoreal) instead of one big interpolation. Smoother, and any bad stage is replaceable on its own. You may need to give feedback and iterate a few times here. 7. Stitch + Review (CC uses ffmpeg + Whisper) Then /watch the master cut and delegate the review to the agent. It catches more things and keeps me out of the loop as much as possible. 8. Turn everything into skills The first time I made a video like this, it took 3 hours. The second time, it took 1 hour. The third time, it took 30 minutes. All the learnings from the human-in-the-loop process should get encoded into skills / code. If all of the above sounds like a lot, it is and it isn't. It's a lot the first time, but if you start encoding everything into skills for Claude, it get much easier. You become the Creative Director, Claude does everything else.
Watch video
- 40
@pukerrainbrow ·
a german court just found copyrighted songs literally stored inside suno's AI model the judge played the originals and suno's AI outputs side by side in open court daddy cool, rasputin, forever young, mambo no. 5, all sitting in the model weights suno said "we trained our models to create new music not reproduce existing ones" the court said no, your model memorized them. there's a difference between analyzing music and copying it, and you crossed that line suno has to disclose all revenue from unlicensed use and pay damages every AI company training on creative work should be paying attention to this
- 41
- 42
- 43
@DaveShapi ·
The key to Suno is that the gems are a flash in the pan. There are countless possible songs that can fall out of the machine, even with the same exact prompts. Then you add the personas and remixes. But you never really know what you're going to get. And some times it just slaps. And you go with it.
- 44
- 45
- 46
- 47
- 48
@shawnchauhan1 ·
Full-track AI music generation just became a production tool, not a demo. Google's Lyria 3 Pro generates coherent tracks up to three minutes long. You define the intro, verse, chorus, and bridge in the prompt. Transitions hold. Vocals are realistic. SynthID watermarks every output. This is not a loop generator. It is a composition engine. The pressure on Suno and every AI music startup just became structural, not competitive. And the pressure on sync licensing, background score, and production music libraries just became existential. The question for the music industry is not whether AI can create. It is whether the industry can move faster than the tooling.
Watch video
- 49
- 50
@DavidChoiMusic ·
AI is already being used by hit songwriters and artists, "they just don't tell you" is a truthful and accurate statement. I've seen it firsthand, and this is actually old news. That artist and song you recently fell in love with? That was co-written with AI. Hook was taken straight from Suno. And even if it wasn't, you'd never know the difference. Just like how 99% of people don't know if a singer is using autotune hardware when they're supposed to be singing "live". AI has already infiltrated the music business, and people both talented and untalented will use it. If they don't, great, but that's the saddest truth I'm willing to acknowledge and accept.
Best Tweets by Topic