Recommended Free Tools
Some links on this page are affiliate links: if you buy through them we may earn a commission, at no extra cost to you.
A 2019 parody video made Donald Trump appear to sing Eurythmics’ “Sweet Dreams (Are Made of This),” but Trump did not record the performance—and Google did not make or release the video. Futurism reported that the YouTube account Coding Elite created it using synthetic voice technology associated with Google research, alongside footage altered to make Trump look as if he were singing.
Futurism’s April 8, 2019, story, “Watch Google’s AI Make Trump Sing Eurythmics’ ‘Sweet Dreams’”, identified the video’s creator as Coding Elite. The article cited the YouTube video ID D6h2-I7q_RU. Its headline’s shorthand can be misleading: the reporting attributes the finished parody to Coding Elite, while connecting its voice-synthesis technique to research by Google engineers.
The clip is a synthetic vocal rendition paired with digitally manipulated footage. It is not evidence that Trump sang the song, authorized a recording, or that Google produced the video. Futurism also pointed to an earlier Coding Elite video that made Trump appear to sing Eminem’s “Lose Yourself.”
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →How can AI make someone appear to sing?
There are two distinct tasks in a clip like this. First, a system must generate audio that resembles a particular speaker while following lyrics and musical phrasing. Second, the video must be altered so the person’s visible performance appears to match that audio.
#1 Best Overall
- Create stunning photos and videos with powerful AI tools, intuitive editing, and eye-catching effects.
- Enhanced Screen Recording - Capture screen & webcam together, export as separate clips, and adjust placement in your final project.
- AI Object Mask - Auto-detect & mask any object, even in complex scenes, to highlight elements and add stunning effects.
- AI Object Removal with Object Detection - Clean up photos fast with AI that detects and removes distractions automatically.
- AI Image Enhancer with Face Retouch - Clearer, sharper photos with AI denoising, deblurring, and face retouching.
The synthetic voice
The Google-linked research cited in the story is “Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis”. It describes Global Style Tokens (GSTs), a method integrated with Tacotron-style speech synthesis. In accessible terms, GSTs let a speech system learn and control qualities of delivery—such as pitch movement, energy, pace, and expressiveness—and use a reference recording to guide how different text is spoken.
That offers a useful explanation of the research connection: a reference signal can contribute characteristics of a voice or speaking style even when its words differ from the text being synthesized. But the paper is about speech synthesis, not a technical report on this particular song. The available reporting does not establish the precise model, audio pipeline, training data, or musical workflow Coding Elite used. It would be inaccurate to say the paper proves that an unmodified GST system generated the video’s vocals.
Rank #2
- ✔️ Create, Edit & Export Videos & Slideshows: Effortlessly create, edit, and export high-quality videos in HD, 4K, and 8K with powerful editing tools, templates, and effects.
- ✔️ Multi-Track Video Editing & AI Media Management: Edit multiple tracks with a timeline, advanced effects, and AI-driven tools to manage and optimize your media.
- ✔️ Over 1000 Templates & Effects: Apply creative filters, transitions, titles, and animations with just a few clicks for professional-quality videos.
- ✔️ Green Screen (Alpha Channel), PiP Effects & Motion Tracker: Use advanced Green Screen and Picture-in-Picture (PiP) features along with Motion Tracking to add stunning visual effects.
- ✔️ Lifetime License for 1 PC | No Subscription Fees: Enjoy a one-time purchase with lifetime access, fully compatible with Windows 11, 10. No hidden costs or subscriptions.
The altered footage
Futurism described the footage as automatically altered to make Trump look as though he were singing. That is the extent of the technical detail in the report: it does not identify a particular lip-sync model, face-swapping method, editing program, or source-footage workflow. Audio generation and visual manipulation should therefore be understood as separate parts of the effect, not as one all-purpose Google system.
Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minutePC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Is it a deepfake?
“Deepfake” is a reasonable broad label for synthetic or manipulated media of this kind, but it does not tell you exactly how the clip was made. More specifically, the reported video combines a Trump-like synthesized vocal performance with altered footage. The evidence does not establish whether the visual effect involved face replacement, mouth animation, compositing, or another technique.
Rank #3
- Enhanced Screen Recording - Capture screen & webcam together, export as separate clips, and adjust placement in your final project.
- Color Adjustment Controls - Automatically improve image color, contrast, and quality of your videos.
- Frame Interpolation - Transform grainy footage into smoother, more detailed scenes by seamlessly adding AI-generated frames. (feature available on Intel AI PCs only)
- AI Object Mask - Auto-detect & mask any object, even in complex scenes, to highlight elements and add stunning effects.
- Brand Kits - Manage assets, colors, and designs to keep your video content consistent and memorable.
The clip fits an early wave of AI-generated celebrity and political media that drew public attention to how familiar voices and images could be repurposed. It is best read as a 2019 synthetic-media parody, not as an example of today’s text-to-video systems—and not as proof that the method was technically primitive in every respect. Its significance is that research associated with controllable speech synthesis could inform a conspicuous public-facing creative use.
What the research does—and does not—show
The GST paper describes a way to model expressive speech characteristics without requiring explicit labels for every style, and to control or transfer stylistic qualities using a reference signal. Its Tacotron-based approach concerns synthesized speech. It does not show that Google trained a model on Trump’s voice, created this parody, endorsed it, or designed the research for political impersonation. Nor does it establish that the resulting voice was perfect or indistinguishable from Trump.
Rank #4
- AI Object Removal with Object Detection - Clean up photos fast with AI that detects and removes distractions automatically.
- AI Image Enhancer with Face Retouch - Clearer, sharper photos with AI denoising, deblurring, and face retouching.
- Wire Removal - AI detects and erases power lines for clear, uncluttered outdoor visuals.
- Quick Actions - AI analyzes your photo and applies personalized edits.
- Face and Body Retouch - Smooth skin, remove wrinkles, and reshape features with AI-powered precision.
That distinction matters whenever a headline says “Google’s AI.” A research contribution by Google-affiliated authors is not the same thing as a Google product, an official demonstration, or a company-produced piece of media. In this case, the reporting names Coding Elite as the creator and links the technique to Google engineers’ research.
Free tools Windows power users keep installed
One-click scans. No signup required.
How to assess a clip like this
- Check the original source and date. The 2019 report identifies Coding Elite and gives the original video URL: youtube.com/watch?v=D6h2-I7q_RU. An old link does not guarantee that the video remains playable; availability may change.
- Look for context from reliable reporting. A viral repost can lose the original label or caption that identified it as parody or synthetic media.
- Separate what is visible from what is claimed. A convincing-looking mouth movement does not establish that a person recorded the audio. Voice and footage can be generated or edited independently.
- Do not infer endorsement or authorization. The reporting does not say Trump approved the performance or that Google supported the creator.
Copyright and impersonation questions
The video raises questions about the song, any recording or arrangement used, the source footage, and the use of a public figure’s voice and likeness. Parody, copyright, publicity rights, false endorsement, and platform policies can depend on the specific material and jurisdiction. The sources cited here do not establish whether permission was granted, a claim was filed, or a court reached any conclusion, so the clip should not be described as definitively legal or illegal.
Although this example is framed as entertainment, the same broad capabilities can be used for satire, misinformation, fraud, or harassment. When synthetic political media circulates without its original context, provenance matters: identify who uploaded it, when, and whether trustworthy reporting explains how it was made before treating it as authentic.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
