Song Creator Pro is the Riffusion alternative that stays on your own PC
Made with Song Creator Pro
Every track below was generated locally on a desktop GPU.
Why switch
3 reasons to choose Song Creator Pro over Riffusion
The Riffusion you remember no longer exists
Riffusion launched on 15 December 2022 as a hobby project by Seth Forsgren and Hayk Martiros, raised a $4 million seed round led by Greycroft in October 2023, and launched Producer.ai with its FUZZ-2.0 model in July 2025. Google acquired ProducerAI into Google Labs on 24 February 2026 and renamed it Google Flow Music that April. As of September 2026, riffusion.com permanently redirects to producer.ai, which permanently redirects to flowmusic.app. If you are searching for Riffusion, the product you will land on is a Google service running Google's Lyria models, with Google's terms. Song Creator Pro is a one-time purchase that runs locally, so the copy on your disk cannot be renamed, acquired or migrated out from under you.
The open-source model was a brilliant demo, not a songwriter
The original Riffusion model fine-tuned Stable Diffusion v1.5 to draw spectrogram images from a text prompt, then converted those images into audio. It was a genuinely clever idea, but the clips were only a few seconds long, there were no lyrics or structured vocals, and the GitHub repository now states that the project is no longer actively maintained. It was tested against Python 3.9 and 3.10 and old diffusers releases, and real-time generation wanted a GPU in the class of an RTX 3090 or A10G. Song Creator Pro ships ACE-Step 1.5 and YuE2, which generate complete multi-minute songs with vocals from lyrics you write.
Nothing you make is watermarked or uploaded
Under Google, every output is embedded with SynthID, Google's inaudible watermark for identifying AI-generated content, and every prompt and upload is processed on Google's servers under a Google account. Song Creator Pro loads the model into your own GPU, needs no account and no internet connection once installed, and writes plain MP3, FLAC or WAV files straight to your drive with nothing embedded in them.
Head to head
How Song Creator Pro compares with Riffusion
Comparing against Riffusion in 2026 means comparing against two different things. One is the original open-source model on Hugging Face and GitHub, which you can still download but which is unmaintained. The other is what the Riffusion app became: Google Flow Music, a capable cloud studio running Lyria 3.5 with conversational editing, stem downloads and music videos. The matrix below uses the current hosted product for the Riffusion column unless a row says otherwise, with prices from the Flow Music pricing page and App Store listing as of September 2026.
| Feature | Song Creator Pro | Riffusion |
|---|---|---|
| Generation | ||
| Text-to-song | ||
| Custom lyrics sung back | ||
| Instrumental-only mode | ||
| Remix or cover your own audio | ||
| Replace and extend sections | ||
| Conversational editing agent | Producer agent, via Gemini | |
| Music video generation | Via Veo | |
| Stem separation | 4 engines | Stem downloads |
| Vocal languages | 50+ | Not documented |
| Original open model clip length | Multi-minute songs | A few seconds |
| Producer controls | ||
| Seed control for repeatable output | ||
| Guidance scale | ||
| Inference step count | ||
| Choice of separation model | ||
| Generation history with metadata | ||
| Output and platform | ||
| MP3 export | ||
| WAV export | ||
| FLAC export | ||
| Watermark embedded in output | SynthID | |
| Windows desktop app | ||
| Browser access | ||
| iPhone app | iOS 18 or later | |
| Local and open-source use | ||
| Runs fully offline | Original open model only | |
| Actively maintained local release | ||
| Packaged installer, no Python | ||
| Automatic hardware detection | ||
| Account required | Google account | |
| Limits | ||
| Generations | Unlimited | Credit-metered |
| Free allowance | Full-feature trial | Daily top-up credits |
| Songs per month at entry paid tier | Unlimited | ~600 |
| Concurrent generations | Limited only by your GPU | 2 free, up to 16 paid |
| Marginal cost per track | $0 | Per credit |
| Cost and licensing | ||
| Pricing model | One-time purchase | Monthly or yearly subscription |
| Entry price | $44.99 once | $8/mo ($6 annual) |
| Three-year cost at entry tier | $44.99 | $216 to $288 |
| Top tier | $49.99 once | $64/mo ($48 annual) |
| Commercial rights included | Check current terms | |
| Open model licence | Ships open models | CreativeML OpenRAIL-M |
| Future updates included | While subscribed |
The full list
Top 10 Riffusion alternatives of 2026
Every tool below was checked against its current pricing and terms in August 2026. Prices and limits in this category change often, so verify before you commit.
Song Creator Pro
Unlimited local AI music generation and downloads, one time payment
Song Creator Pro is a Windows desktop app that generates, remixes and separates music entirely on your own GPU. There is no account, no upload step and no credit meter. It ships two open models, ACE-Step 1.5 and YuE2, and is among the first apps anywhere to run YuE2 on 8 GB GPUs rather than the 24 GB its official release demands. You describe a song in plain language and it renders locally, in any of 50+ languages, with inference steps, guidance scale and seed exposed so results are repeatable. It is a one-time purchase rather than a subscription.
Coming from Riffusion? What the original Riffusion promised, a music model on your own hardware, finished into an installable app. It writes full songs with vocals rather than a few seconds of spectrogram audio, and nothing leaves your PC.
Pros
- Runs 100% offline on your own machine, so prompts and audio never leave your PC
- Includes YuE2, the model that outscored Suno on WildSongBench, running on 8 GB GPUs
- One-time purchase with lifetime updates instead of a monthly subscription
- Genuinely unlimited generations with no credits, no daily caps and no download limits
- Built-in stem separation
- Producer-grade controls: seed, guidance scale, inference steps and batch generation
- Exports MP3, FLAC and WAV with full commercial rights included
Cons
- Windows only today, with macOS still on the roadmap
- A GPU (NVIDIA or AMD) is strongly recommended, and speed depends on your hardware
- No browser or mobile access, so you cannot generate from a phone
- No community feed or social sharing features
| Plan | Price |
|---|---|
| itch.io | $44.99 once |
| Microsoft Store | $49.99 once |
| Bundle | $72.50 once |
Google Flow Music
Google's AI music studio, formerly Riffusion and Producer.ai
Google Flow Music started life as Riffusion in 2022, a diffusion model that generated audio as spectrogram images, became Producer.ai in 2025, and was acquired into Google Labs in February 2026 before relaunching under its current name that April. It now runs on Lyria 3 Pro, with Gemini handling conversational editing, Veo generating matching music videos and Nano Banana producing cover art. Every track it renders carries Google's SynthID watermark.
Coming from Riffusion? This is where Riffusion actually went. If you liked the Riffusion app and are happy in the cloud, Flow Music is its direct successor, now on Lyria 3.5 with a conversational Producer agent, stem downloads and a SynthID watermark on every track.
Pros
- Free tier with daily top-up credits and the full core features
- Conversational editing through Gemini rather than prompt and reroll
- Google does not claim ownership of what you generate
- Music videos and cover art produced alongside the track
Cons
- Every output is embedded with Google's SynthID watermark
- Generation is metered by credits, and commercial rights are not stated on the pricing page
- Third name in four years, so the product keeps moving under you
- Cloud-only and tied to a Google account
| Plan | Price |
|---|---|
| Free | $0 |
| Starter | $8/mo ($6 annual) |
| Plus | $24/mo ($18 annual) |
| Member | $64/mo ($48 annual) |
Suno
The most popular AI song generator
Suno is the best known AI music platform and the benchmark most others are measured against. In September 2026 it retired every model before v6 under its Warner settlement and replaced them with the licensed v6 family, which has drawn mixed reviews: cleaner production for some, muffled and more generic output for others. It runs in the browser, has a large community, and offers a duration slider and Advanced Split stem separation that regenerates stems rather than extracting them.
Coming from Riffusion? The most familiar cloud alternative for Riffusion app users who want to leave Google out of it. Polished vocals, though downloads are capped at 20 songs a month on Pro and every pre-v6 model was deleted in September 2026.
Pros
- Polished, clean vocal production across mainstream genres
- Very broad genre coverage and a large, active creator community
- Advanced Split regenerates stems from nearly 100 instrument choices
- Duration control from 10 seconds to 6 minutes in 5-second steps
- Works in any browser on any device, including phones
Cons
- From 3 September 2026 the free tier has no monthly download allowance at all, just a one-off pool of up to 7 trial downloads for personal use
- Paid plans cap downloads: Pro allows only 20 songs a month, Premier 60
- Subscription credits expire and never roll over between days or months
- All audio is processed on Suno's servers, so nothing stays private
- Every pre-v6 model was deleted in September 2026, so old songs cannot be extended or regenerated, and Sony and Universal litigation is ongoing
| Plan | Price |
|---|---|
| Free | $0 |
| Pro | $10/mo ($8 annual) |
| Premier | $30/mo ($24 annual) |
ACE-Step
The open-source model behind much of local AI music
ACE-Step is an open-source music foundation model from ACE Studio and StepFun, and version 1.5 added an FSQ tokenizer along with remix, edit and cover tooling. It is free to download and run locally, and it is the engine underneath a number of consumer local apps, including parts of Song Creator Pro.
Coming from Riffusion? The spiritual heir to the open-source Riffusion model: free weights you run yourself, but a current, maintained model that produces full songs instead of short clips. You still handle Python, CUDA and the setup.
Pros
- Free and open source, with no licence fee at all
- Runs entirely on your own hardware
- Strong remix, edit and cover capabilities
Cons
- You have to set up Python 3.11 or 3.12, uv, GPU drivers and model weights yourself
- The bundled Gradio web UI is a developer tool rather than a polished app
- No support, and troubleshooting means reading GitHub issues
- Keeping up with model updates is manual work
| Plan | Price |
|---|---|
| Open source | Free |
YuE2
Open full-song generation, if you have the VRAM
YuE2, released in September 2026, is an open-weight model that generates complete structured songs with synchronised vocals directly from lyrics, produces an editable score, and can cover existing songs in new styles. On the WildSongBench benchmark it outscored every Suno model, including the since-retired v5. It remains a research release rather than a product; Song Creator Pro packages it for Windows and is among the first apps to run it on 8 GB GPUs.
Coming from Riffusion? If the appeal of Riffusion was running an open model locally, YuE2 is the one that sings full songs from your lyrics. The official release wants Linux and around 24 GB of VRAM, which is the gap Song Creator Pro closes.
Pros
- Generates full songs with vocals from lyrics, entirely locally
- Outscored Suno v5 and v6 on the WildSongBench benchmark
- Editable scores and score-based covers, which no cloud tool offers
- Free, open weights with an active research community
Cons
- The official release targets Linux and wants roughly 24 GB of VRAM
- Vocals in English, Mandarin and Japanese only
- Command-line research code with no polished interface
- No commercial support of any kind
| Plan | Price |
|---|---|
| Open source | Free |
Stable Audio
Stability AI's audio model, strong on instrumentals
Stable Audio from Stability AI focuses on high-quality instrumental generation, sound design and loops rather than full vocal songs. It is a common pick for producers who want royalty-free beds and textures, and Stable Audio Open gives the research community a downloadable variant.
Coming from Riffusion? Closest in lineage, since Riffusion was built on Stable Diffusion. Stability AI's own audio model is excellent for loops and instrumentals and publishes open weights, but it does not sing.
Pros
- Excellent instrumental, loop and sound-design output
- Backed by an established research lab, with an open model variant
- Clean royalty-free licensing for paid users
Cons
- Vocals are a weak point compared with Suno or Mureka
- Cloud subscription for the hosted product, with no free plan and a $12 a month entry tier
- Less suited to writing complete songs with lyrics
| Plan | Price |
|---|---|
| Solo | $12/mo |
| Session | $30/mo |
| Producer | $90/mo |
| Studio | $199/mo |
ElevenLabs Music
The cleanest licensing story in AI music
Eleven Music is ElevenLabs' entry into music generation, launched in August 2025 and substantially upgraded with v2 in 2026. Its distinguishing feature is legal rather than sonic: it was trained on licensed stems and built in partnership with rights holders before launch, rather than settling lawsuits afterwards. It supports vocals in 59 languages and generates section by section with inpainting.
Coming from Riffusion? The pick if the Google acquisition left you uneasy about provenance. Trained on licensed material from the start, with vocals in 59 languages and commercial rights from its $6 Starter plan.
Pros
- Trained on licensed material from the start, giving it the clearest commercial position of any major platform
- Vocals in 59 languages, with native-quality delivery in 11
- Section-by-section building and inpainting to regenerate parts of a track
- Can generate stems, lyrics and full compositions, and shift style mid-track
- A mature, well-documented API for developers
Cons
- Credits are shared with ElevenLabs' speech products, so music competes with your voice usage
- Film, TV and large studio game rights require an Enterprise plan
- Output is capped at 44.1 kHz, and formats are MP3, PCM, Opus and telephony codecs
- Cloud-only with no offline option
- The music product is newer and less battle-tested than its voice tooling
| Plan | Price |
|---|---|
| Free | $0 |
| Starter | $6/mo ($5 annual) |
| Creator | $22/mo |
| Pro | $99/mo |
Mureka
Voice cloning and high song throughput
Mureka is a full-stack AI music platform whose current flagship is the V9.5 model. Its standout capability is voice cloning: upload a short sample of a voice you have rights to and Mureka will perform new songs in it. Plans run on a credit it calls Gold, but each tier states roughly how many songs its Gold buys, which keeps the maths easy, and it bundles stem separation and a lyrics generator.
Coming from Riffusion? A cloud option with voice cloning and plans that state how many songs they buy. Useful if Flow Music's credit maths or Google account requirement is what pushed you away.
Pros
- Voice cloning for songs, included with commercial rights on the Premier plan
- Each paid plan states an approximate song count alongside its Gold allowance
- High volume allowance on paid plans, with about 500 songs a month at the entry paid tier
- Stem separation, region and melody editing, and reference audio uploads
- Exports MP3 and MP4, with WAV, MIDI and stems on Premier
Cons
- Around 10 vocal languages, far fewer than Suno or ElevenLabs
- The free plan is 50 Gold a day on the older V7.5 model, with no downloads and personal use only
- Voice cloning of a real person carries obvious rights risk if you get consent wrong
- Cloud processing, so reference audio you upload leaves your machine
- Smaller community and less third-party tooling than Suno
| Plan | Price |
|---|---|
| Free | $0 |
| Pro | $10/mo ($8 annual) |
| Premier | $30/mo ($24 annual) |
Mubert
Royalty-free background music built from human-made samples
Mubert generates royalty-free functional music, the kind that sits behind videos, podcasts, apps and streams, by assembling tracks from a large library of samples contributed by human musicians who get paid when their loops are used. That gives it a cleaner provenance story than models trained by scraping, and it is why Mubert has avoided the lawsuits that reshaped Suno and Udio. You generate by prompt, mood, genre or activity, with tracks up to 25 minutes long, and a developer API serves the same engine to apps and games. As of September 2026 plans run from a free Ambassador tier to a $199 a month Business tier. The catch is scope: it makes background beds, not songs with vocals, and no plan allows publishing to Spotify or other streaming services.
Coming from Riffusion? For anyone who loved the original Riffusion's endlessly interpolating loops more than finished songs. Mubert generates long royalty-free instrumental beds up to 25 minutes, built from licensed human-made samples, but no vocals.
Pros
- Built from licensed human-made samples, so its rights story is unusually clean
- Tracks up to 25 minutes long, well suited to podcasts, streams and ambient beds
- Unlimited lossless and MP3 downloads on every paid plan
- A mature API for generating music inside apps, games and products
- Stem editing on all tiers, with a full track editor for structure, BPM and key on Pro and Business
Cons
- No vocal generation, so it cannot write an actual song with lyrics
- No plan permits releasing tracks to Spotify, Apple Music or any streaming platform, or registering them with Content ID
- Commercial use for monetized content starts at Pro, $39 a month, which adds up fast against a one-time purchase
- The free and Creator tiers are non-commercial only, with the free tier requiring attribution
- Cloud-only, and payments are non-refundable on every tier
| Plan | Price |
|---|---|
| Ambassador | $0 |
| Creator | $14/mo ($11.69 annual) |
| Pro | $39/mo ($32.49 annual) |
| Business | $199/mo ($149.29 annual) |
Musci.io
One credit pool across seven other engines
Musci.io is best understood as an aggregator rather than a model of its own. A single credit balance buys generations across seven third-party engines including Suno, Udio, ElevenLabs Music, Mureka, MiniMax Music, ACE-Step and Google Lyria 3. It wraps them in one interface and adds side tools such as a vocal remover, song extender and lyrics generator.
Coming from Riffusion? Lets you try Google Lyria alongside Suno, ElevenLabs, ACE-Step and others on one credit pool, which is a cheap way to hear what Riffusion's successor model sounds like before subscribing to anything.
Pros
- Try seven engines without taking out seven separate subscriptions
- Per-generation costs are low, from around $0.04 for a Lyria clip
- Useful extras including vocal remover, song extension and cover generation
- Royalty-free commercial rights from the Standard plan up
Cons
- It does not own a model, so quality, features and availability depend entirely on upstream providers
- Any upstream change, such as Udio disabling downloads, flows straight through to you
- Your audio passes through both Musci.io and the underlying engine
- No deep arrangement control and no enterprise licensing documentation
- No free tier is listed, and commercial licensing and WAV export start at the $29.99 Standard plan
| Plan | Price |
|---|---|
| Starter | $9.99/mo |
| Standard | $29.99/mo |
| Premium | $99.99/mo |
Round by round
Song Creator Pro vs Riffusion
Six categories, each with a winner.
Conversational editing
Winner: RiffusionCredit where it is due. The Producer agent that started life at Producer.ai and now runs on Gemini lets you talk to a track: replace a chorus, extend an intro into a different genre, ask for variations on a guitar solo. It now runs on Lyria 3.5, which Google describes as improving musicality, lyrics, vocals and control. Song Creator Pro's repaint and remix tools are more repeatable, with seed and guidance control, but you operate them rather than converse with them. For a beginner who does not yet know the vocabulary, the Riffusion successor is easier.
Getting started for free
Winner: RiffusionFlow Music's free plan tops up credits every day with two concurrent generations and needs only a Google account. Song Creator Pro offers a free trial on the Microsoft Store but is ultimately a paid download. If you want to make a few songs a week in a browser and never pay anything, the cloud product is the practical choice and there is no point pretending otherwise.
Running it yourself
Winner: Song Creator ProThis is the part of Riffusion that disappeared. The original model is still on Hugging Face under the CreativeML OpenRAIL-M licence, but the GitHub repository is marked as no longer maintained, targets Python 3.9 and 3.10, and produces a few seconds of audio per clip. The product that replaced it is cloud-only. Song Creator Pro is a Windows installer that detects your hardware, picks a backend, and runs YuE2 on 8 GB GPUs when its official release asks for roughly 24 GB, with CPU-only processing, int8 quantization and CPU offloading for weaker machines.
Full songs with vocals
Winner: Song Creator ProAgainst the original open model this is not a contest: Riffusion generated short instrumental clips from spectrograms and never sang your lyrics. Song Creator Pro ships YuE2, which builds complete structured songs with synchronised vocals from the lyrics you type, plus ACE-Step 1.5 for vocals in more than 50 languages. The hosted successor can sing, but only in the cloud and only with a watermark attached.
What lands in the file
Winner: Song Creator ProGoogle embeds SynthID in everything Flow Music generates. It is inaudible and intended for provenance rather than restriction, but it is permanent and detectable, so any track you release can be identified as machine-generated. Song Creator Pro writes ordinary MP3, FLAC and WAV files with nothing embedded, which matters for client work and anywhere an AI-disclosure policy applies.
Cost over time
Winner: Song Creator ProFlow Music's paid plans are $8, $24 and $64 a month, or $6, $18 and $48 a month billed yearly, according to its pricing page and App Store listing in September 2026. Three years at the entry tier comes to between $216 and $288, and the top tier to between $1,728 and $2,304. Song Creator Pro is $49.99 once on the Microsoft Store or $44.99 on itch.io, with unlimited generation and lifetime updates. The monthly Starter plan passes that in about six months.
The verdict
Conclusion
Riffusion deserves its place in AI music history. In December 2022 it showed that an image model could be taught to make music, it released the code and weights openly, and it grew into an app with over a million monthly users by mid-2025. The team's later work, Producer.ai and the FUZZ-2.0 model, was good enough that Google bought the company in February 2026.
But the Riffusion name now leads somewhere else. The app became Producer.ai and then Google Flow Music, a cloud service with a Google account, credit-metered plans from $8 a month and a SynthID watermark on every output. The open-source model is still downloadable, but it is unmaintained, produces clips a few seconds long and cannot sing. If you liked the hosted app, Flow Music is its natural continuation and a strong product in its own right.
If what drew you to Riffusion was the idea of a music model running on your own machine, Song Creator Pro is the finished version of that idea. It installs ACE-Step 1.5 and YuE2 on Windows, generates full songs with vocals in more than 50 languages, runs offline with no account, separates stems with a choice of four engines, and exposes seed, guidance scale and inference steps. It costs $49.99 once, and the version you install keeps working however the cloud market changes.
Frequently Asked Questions
Riffusion launched on 15 December 2022 as an open-source project by Seth Forsgren and Hayk Martiros that generated music as spectrogram images. The team raised a $4 million seed round in October 2023, launched Producer.ai with the FUZZ-2.0 model in July 2025, and was acquired by Google into Google Labs on 24 February 2026. In April 2026 Google renamed the product Google Flow Music. As of September 2026, riffusion.com redirects to producer.ai, which redirects to flowmusic.app.
Yes, they are successive names for the same team's product. Riffusion became Producer.ai in 2025 and Google Flow Music in April 2026. The underlying model has changed along the way, from the original Stable Diffusion spectrogram model to FUZZ-2.0 and now Google's Lyria 3.5.
It depends which Riffusion you used. If you want the hosted app experience, Google Flow Music is its direct successor. For a local, offline tool with a one-time price, Song Creator Pro. For free open models you set up yourself, ACE-Step 1.5 or YuE2. For polished cloud vocals outside Google, Suno or ElevenLabs Music. For long instrumental beds, Mubert.
Yes, but with caveats. The riffusion-model-v1 weights are on Hugging Face under the CreativeML OpenRAIL-M licence and the code is MIT licensed on GitHub. The repository is marked as no longer actively maintained, was tested with Python 3.9 and 3.10, and needs a GPU able to run Stable Diffusion at about 50 steps in under five seconds, such as an RTX 3090 or A10G, for real-time generation. CPU works but is slow. It produces clips a few seconds long with no lyrics.
As of September 2026 there is a free plan with daily top-up credits and two concurrent generations. Paid plans are Starter at $8 a month ($6 billed yearly) for 3,000 credits, about 600 songs, Plus at $24 ($18 yearly) for 10,000 credits, about 2,000 songs, and Member at $64 ($48 yearly) for 30,000 credits, about 6,000 songs. Google AI Plus subscribers get Starter plan benefits included.
Yes. Google says all outputs are embedded with its SynthID watermark for identifying AI-generated content. Song Creator Pro generates ordinary audio files with no watermark, because the model runs on your own hardware.
Song Creator Pro runs entirely on your own Windows PC and needs no internet connection after installation, with no account and no upload step. ACE-Step and YuE2 also run locally if you are comfortable setting up Python, CUDA and model weights yourself, and the original Riffusion model can still run offline, though it is unmaintained.
Song Creator Pro is a one-time purchase of $49.99 on the Microsoft Store or $44.99 on itch.io, with lifetime updates and unlimited generation. ACE-Step and YuE2 are free and open source if you are prepared to set them up yourself.
Windows 10 or later. A GPU (NVIDIA or AMD) is recommended for speed, and Song Creator Pro is among the first applications to run YuE2 on 8 GB cards when the official release targets roughly 24 GB. It detects your hardware and suggests the best backend, and supports CPU-only processing, int8 quantization and CPU offloading for weaker machines, which work but take longer. macOS support is on the roadmap but has not shipped.
Yes. The Extract feature offers four engines: ACE-Step for the widest range of instrument types, Demucs 4-stem for vocals, drums, bass and other, a fine-tuned Demucs 4-stem for cleaner versions of those, and Demucs 6-stem which adds guitar and piano. It works locally on any MP3, WAV, FLAC or M4A file.
Keep comparing
See how Song Creator Pro compares with other tools
vs Suno
Learn morevs Udio
Learn morevs ElevenLabs Music
Learn morevs Mureka
Learn morevs MiniMax Music
Learn morevs Musci.io
Learn morevs Google Flow Music
Learn morevs Soundraw
Learn morevs Mubert
Learn morevs AIVA
Learn morevs Boomy
Learn morevs Stable Audio
Learn morevs Tad AI
Learn morevs ACE Studio
Learn morevs Soundful
Learn morevs Beatoven.ai
Learn moreSong Creator Pro is more than just a Riffusion alternative
Unlimited local generation, remixing and stem separation on your own GPU. One payment, lifetime updates, and nothing ever leaves your machine.
Get Song Creator ProFree trial on the Microsoft Store · One-time payment · No recurring fees