The finetuning Lifetime Deal is now live on AppSumo — grab yours here →
finetuning finetuning
Updated every Friday

Release Notes

What's new, improved, and fixed in finetuning. We ship updates every week and share the details here.

August 21, 2026

Latest

What's New

Studio Makes Videos — Export an MP4 (Beta)

You can't upload an MP3 to Reels, TikTok, Shorts or YouTube — so Studio now finishes the job. On any paid plan, put your own pictures behind a track and export a video you can post. Add a picture to the new Image lane and Export offers Video · MP4 beside Audio · MP3; the video runs from your first picture to your last and takes the sound from that stretch of your timeline — songs, voiceover, sound effects, fades and all. Pick the shape on the preview monitor: Vertical 720×1280 for Reels, TikTok and Shorts, Square 1080×1080 for Instagram, X and LinkedIn, or Wide 1280×720 for YouTube. Pictures behave like everything else on the timeline — drag them, trim them to change how long they hold the screen, and choose how each one arrives: a cut, a crossfade, a dip to black, or a slide. Each can sit still or take a slow zoom or pan, crop to fill the frame or sit whole over a blurred backdrop, and you drag the picture in the preview to pick which part stays in shot.

Elements — A Moving Waveform, Text, and Your Own Logo

Everything you want laid over the picture lives on the new Elements lane: a waveform whose bars move with the music, a progress bar that fills as the clip plays, text — a title, a lyric, a handle — in your choice of font, colour and alignment, and anything you upload: a logo, a sticker, a signature. Animated GIFs play. Elements are timed on the lane and placed in the preview — drag one where you want it, resize it, and it keeps that spot when you switch the video from vertical to square or wide.

Fixes & Improvements

One Studio layout on every screen — the picture stays put at the top, zoom, transport and shape sit in a single row beneath it, and the timeline takes the rest of the screen. It's pinned to the viewport, so reaching for a lane no longer scrolls the preview away.
Export progress stays in the export sheet for both MP3 and MP4, and now runs all the way through writing the final file rather than stopping at the last frame.

August 14, 2026

What's New

Choose the Voice — Male or Female Vocals

You can now tell the model which voice should sing your lyrics. In Advanced mode, turn on Include lyrics and you'll find a new Voice control sitting right under Language: Auto, Female, or Male. Auto stays the default, so nothing changes until you ask it to. Voice is a strong steer rather than a lock — in our own blind listening tests the model never sang the opposite gender, but a take can occasionally come out too indistinct to call, and generating again usually clears it up. Developers get the same control as an optional vocalGender field on the API, and there's a Voice field on the Create Music Track action in Zapier.

Fixes & Improvements

Sound-effect certificates now have a home in the app — completed clips in the Library's Sound Effects tab have their own certificate button, next to Download.

August 7, 2026

What's New

Generation Certificates — Proof Your Track Is Yours

Every completed track on a paid plan now comes with a downloadable PDF generation certificate — a formal, single-page document you can hand to YouTube, a client, or a sponsor to show exactly where your music came from. Issued by Riku AI LLC, the operator of Finetuning, it confirms the track was generated by you on Finetuning — with your prompt, your settings, and the AI model — and states plainly that Finetuning claims no ownership of what you create: all rights in your work stay with you. Each certificate carries a permanent certificate number and a public verification page with a QR code — anyone can confirm it at finetuning.ai/verify, no account needed. Find it under ⋯ → Generation certificate in your Library or on any track page. Developers and agents can fetch the same PDF straight from the API.

Fixes & Improvements

Sound effects get certificates too — one certificate covers the request and its takes.
Certificates stay current: renaming a track refreshes its certificate on the next download — the certificate number never changes.
Certificates are perpetual: they stay valid and verifiable even if you later change plans.

July 31, 2026

What's New

Build a Full Mix with Multiple Songs in Studio

Studio can now bring multiple songs from your Library into one timeline. Hit Add song to build a longer arrangement, then drag each song wherever you want it in the mix. Every song stays independently editable: trim the beginning or end without changing the source track, split at the playhead and work with each section separately, and give any song, voice clip, or sound effect its own fade in and fade out — overlap two songs and combine their fades to create a smooth crossfade. Playback follows the complete Studio timeline, so you can listen straight through song changes, gaps, voiceovers, and sound effects before exporting everything as one MP3. Projects can now run up to 60 minutes of final timeline, regardless of how many source songs you trim or overlap — longer projects stay in your browser, which prepares nearby songs as you work and exports the mix in smaller pieces instead of loading an hour of uncompressed audio into memory at once. Everything is assembled client-side; your Studio sources never take a detour through a new upload or rendering service.

Fixes & Improvements

Adding a song feels immediate: it appears on the timeline right away while its waveform finishes loading in the background.
Smarter timeline view: a two-song project automatically gets a little more working room, and Fit always returns to the full composition.
Edit while you listen: scroll and edit later parts of the timeline during playback without the playhead pulling the view back.
Phone gestures match familiar editors: swipe to move across the timeline, tap to select, hold to move a clip, and drag the handles to trim — and the mobile editing panel now sits directly above the player controls.
Export at a glance: large projects show their final duration, an approximate export time, and device guidance before encoding begins.

July 24, 2026

What's New

Studio 2.0 — One Timeline, Your Voice, and Sound Effects

Studio has grown from a pair of tools into a real editor. Everything now lives on one timeline — no more switching between Trim and Loop tabs. Trim right on the waveform by dragging the handles on either side of the track; the parts you're cutting dim out so you can always see what you're keeping. Add your voice by recording straight into the browser or uploading a file — your take lands on its own lane and we level it automatically, and with ducking on, the music steps aside whenever you're talking. Layer in sound effects from your library on a third lane, kept out of the voice balance so effects never dip your music. Edit like a video editor: tap a clip to Split it at the playhead, adjust its Volume, or delete it — drag to move, grab the bracket handles to trim, and nothing is ever destructive. Zoom from fit-to-screen up to 16× when you need to line something up exactly. Then one Export button renders the whole composition — music, voice, and effects — with an optional Repeat of 2×, 4×, or 8× that seamlessly loops the finished piece, always ending on a complete pass. Keyboard shortcuts throughout: Space to play, S to split, I/O to set trim points, arrows to nudge, +/−/0 to zoom. New to Studio? A short three-step walkthrough shows you around.

Fixes & Improvements

Better recording quality: we now ask your microphone for a clean, unprocessed signal at a higher bitrate, instead of the call-optimized processing browsers apply by default. Recordings sound noticeably fuller and less pumpy. Headphones are strongly recommended while recording — without them, your speakers can bleed into the take.
Playback previews the real mix: what you hear on the timeline — ducking, balance, clip trims, effects — is exactly what lands in the exported file.

July 17, 2026

What's New

Download a Playlist as One Continuous Track

Your playlist can now leave the app the way you hear it — as one seamless audio file. Hit Download All on any playlist (or select specific tracks and download just those) and pick your format: separate files — the classic ZIP, unchanged — or one continuous track, every track stitched together in playlist order into a single MP3 named after your playlist. Choose how tracks flow into each other — no gap, a 1s or 2s pause, or a smooth ~2s crossfade — and we'll remember your choice for next time. The whole file is built right in your browser with live progress and a time estimate; just keep the tab open until the download starts. Continuous mode handles up to 100 tracks or 60 minutes per file (bigger playlists are steered to the ZIP), and tracks still generating are skipped and reported. Perfect for DJ-style mixes, focus sessions, podcast beds, or dropping an hour of music into a video editor as a single clip.

July 10, 2026

Fixes & Improvements

Fixed template generation errors with longer additional details: some templates could error with “Music description must be under 700 characters” when you added your own details. We've fixed this across all templates — the additional-details field now always accepts its full 300 characters. Thanks to the user who reported this!

July 3, 2026

What's New

Zapier — Create Instrumentals & Sound Effects from Your Zaps

Our Zapier integration now generates more than songs. Two new actions join Create Music Track: Create Instrumental Track for vocal-free music, and Create Sound Effect for short SFX (1–8s). Instrumentals ride the existing New Completed Track trigger and Find Track by ID search; sound effects get a new Find Sound Effect by ID search (pair it with a Delay step to grab the finished audio). Same connection, same API key. Available on Pro and AppSumo Lifetime.

“What's New” in the App

A lightweight popup now surfaces each release right inside Finetuning, so you don't miss new modes and integrations. It shows once per release and links straight to the create page.

June 26, 2026

What's New

Instrumental Tracks — Vocal-Free Music in One Step

A new Instrumental mode joins Simple, Advanced, and Sound FX on the create page. Pick a use-case style — vlog, podcast, study, cinematic, and more — describe the vibe, and generate. No lyrics, BPM, or key to set: the model picks the instrumentation, tempo, and feel for you. Free and paid plans both create instrumentals; paid tiers unlock the full length.

Instrumental Tracks on the API

Generate instrumentals programmatically with the new POST /v1/instrumental endpoint — same key, auth, and webhook flow as music, drawing from your shared monthly generations. Your generations list now returns a type field and accepts a ?type=instrumental filter. Available on Pro and AppSumo Lifetime. Docs: docs.finetuning.ai.

ft CLI v0.3.0 — Instrumentals & Sound Effects in Your Terminal

The ft command-line tool catches up to the API: create instrumentals with ft instrumental, generate sound effects with ft sfx, and filter your library by --type. Run ft update to pull the new version. Docs: docs.finetuning.ai.

June 19, 2026

What's New

Sound Effect Mode

Sound effects get their own mode in the create flow. Describe the sound, set the length (1–8 seconds), and generate — no mixer, no musical settings. Finished clips land in the Sound Effects tab in your Library.

Sound Effect API

Generate sound effects programmatically — same key, auth, and webhook flow as music. New endpoints create a SFX (1–8s), list them, and fetch one by ID, with a shared 100/day allowance across the API and web app. Available on Pro and AppSumo Lifetime. Docs: docs.finetuning.ai.

Fixes & Improvements

Weekly and Monthly Top Charts are live: see the most-loved tracks of the week and month, get inspired, and watch your own climb the ranks.

June 12, 2026

What's New

Bulk Actions — Select Many Tracks, Act Once

Your Library and playlists now have a Select button. Tick multiple tracks (or Select all) and act on them all at once — download as ZIP (up to 500 tracks), add to a playlist, or delete. Inside a playlist you can also move tracks to another playlist or remove them without touching your library.

Public API v1.2 — Bulk Endpoints & Playlists

Five new endpoints let you bulk-delete tracks and manage playlists programmatically — up to 100 track IDs per request, and each bulk call counts as just one request against your rate limit. Available on Pro and AppSumo Lifetime plans. Docs: docs.finetuning.ai.

Bulk Actions in the ft CLI

Bulk actions are in the ft CLI too — manage your library and playlists in batches straight from your terminal, working the same way as the API.

June 5, 2026

What's Coming

Bigger Things in Testing

This week we kicked off some of the deeper, more technical work to take finetuning to the next level. It's taking a little longer than a week to get live, but it's already in internal testing. We expect to ship early next week, Tuesday or Wednesday, with a further release on Friday.

May 29, 2026

What's New

19 New Quick-Create Templates

The Quick Create menu just got 19 brand-new templates — one-tap starting points across beats & hip-hop, electronic, band & vocal, cinematic & world, and global & pop. Each comes tuned with its own tempo, key, and feel. Pick a card on the home page or in Simple mode and generate.

Finetuning on Zapier — Automate Your Music (Beta)

Finetuning now connects to Zapier, wiring your music generation into 8,000+ apps with no code. Three building blocks: a New Completed Track trigger that fires the moment a track finishes (MP3 link, title, duration, settings attached), a Create Music Track action to kick off a track from any Zap, and a Find Track by ID search. Available on Pro and AppSumo Lifetime plans, in private beta. Docs: docs.finetuning.ai/docs/integrations/zapier.

May 21, 2026

What's New

ft — Generate Music From Your Terminal

Finetuning now has a CLI. ft lets you generate, list, inspect, and download tracks straight from your shell. Available on Pro and AppSumo Lifetime plans. Docs: docs.finetuning.ai/docs/cli/commands.

Claude Code Skill — Drive ft From Any AI Agent

A new skill teaches Claude (and other AI agents via AGENTS.md) how to drive ft for you — ask in plain English and it runs the right commands. Docs: docs.finetuning.ai/docs/cli/skill.

Embed Your Tracks & Playlists on Any Site

Drop a Finetuning player into any website. Open the share popup on a public track or playlist, switch to the new Embed tab, and pick an inline iframe or a floating widget. Choose one of 12 visual presets (or tweak theme, accent, corners, border, size) and copy the snippet. Available on Plus, Pro, and AppSumo Lifetime plans.

Improvements

Library Remembers Your View

Pick grid or list on the Library page and we'll remember it next time. No more flipping back to grid every visit.

Clearer Welcome Email

The post-signup welcome email used to say "you have 10 free credits!" which sounded like you could spend them all on day one. Reality: free tier is 10 credits a month, up to 2 tracks a day. The email now says exactly that, so new users aren't surprised when they hit the daily cap.

Bug Fixes

Floating widget icon was invisible on some accent colors: When you picked a bright accent (e.g. coral, yellow), the icon inside the launcher button could end up the same color as the background and disappear. The icon now auto-contrasts against the accent, so it stays visible no matter what color you pick.
Embed border could trigger scrollbars: Turning on the bold border on an embedded player added internal scrollbars in some iframes. Border is now painted inside the box instead of around it — no more layout shift.

May 15, 2026

What's New

Public Track Pages Are Now Listenable Without Signup

Public share links — finetuning.ai/t/... for tracks and finetuning.ai/p/... for playlists — no longer require an account just to listen. Hit play and the music starts.

Optional Password Protection on Public Shares

You can now set a password on any public share link, available on every tier including free. Toggle the password on inside the share popup on any of your tracks or playlists, type a password, and only people with the password can play it. Useful for soft-launches, sending a track to a specific group, or keeping a public link technically alive while you decide who's allowed in. Change or remove the password at any time from the same share popup.

Secure Links — Private Delivery for Clients

A new type of share link, built for creators sending tracks to paying clients, agencies, or collaborators. Open any track's share popup and switch to the Secure tab to create one. No account required for the recipient — they get a clean, private listening page with your branding applied (logo, colors, custom background) for a true white-label feel. Links are expiring (default 7 days, configurable), support optional passwords, show view counts so you can spot leaks, and can be revoked any time without rotating URLs on every link you've sent. Secure Links are available on Pro plans and AppSumo Lifetime Tier 2+.

Public API v1.1 — Webhook Callbacks

If you're building on top of the Finetuning public API, you can now skip polling. Add a webhook URL to your POST /v1/generations request and we'll POST the finished track straight to your endpoint the moment it's ready. The callback fires once, identifies itself with User-Agent: finetuning-webhook/1.0, and includes the full generation payload (id, status, audioUrl, prompt, parameters). Add your own secret as a query string on the webhook URL and we'll preserve it on the way out, so you can verify the callback came from your own request. Full guide and examples are on docs.finetuning.ai.

Longer Tracks on Paid Plans

Max track length on paid plans is now 3 minutes 30 seconds (was 3 minutes), both on the web app and via the API. Free tier stays at 2 minutes.

Improvements

Cleaner Share UX

We tightened up the share popup to make it easier to understand at a glance — clearer toggles, less digging around, and a better path to managing your existing links.

Custom Prompts in Simple Mode

You can now add your own prompt on top of a Simple mode Template. Pick a Template for the overall sound, then layer in a short prompt to nudge the vibe, instrumentation, or mood — the best of both worlds between one-click generation and the full prompt experience.

Friendlier Advanced Settings

We reworked the parameters in Advanced settings to be more user-friendly — clearer labels, better defaults, and less guesswork about what each knob actually does.

Stricter Rate Limit on Public API Generation

To keep the music generation queue healthy for everyone, the public API now allows 10 generations per minute per user on POST /v1/generations. Reads (status polling, listing, account info) stay on the broader 60/minute limit so you can keep checking on jobs without burning your generation budget.

Bug Fixes

Playlist theme customizer save failing: Saving a custom color theme on a playlist quietly errored on the server side for some users — fixed. Theme saves now work for everyone.
Playlist share popup error on first share: Opening the share popup on a brand-new public playlist could 500 on the server — fixed.

May 8, 2026

What's New

Studio (Beta) — Trim and Loop Your Tracks

Studio is here. Take any track you've generated and reshape it without leaving finetuning. Trim lets you pick the exact section you want and download just that piece — bit-perfect quality (no re-encoding) and exports in seconds. Loop turns a short section into a longer track, anywhere from a few seconds up to 60 minutes, with a seamless seam at every repeat. Perfect for background music, study sessions, livestream beds, and content scoring. Open Studio from the home page or jump straight in from any track — the waveform editor lets you scrub, drag the selection, and preview your edit before downloading. Long exports show live progress and an estimated time remaining. Works on desktop and mobile (including iPhone), with desktop recommended for the longest loops. Studio is a premium feature, currently in beta — no watermarks, full commercial rights on everything you export.

Bug Fixes

Downloads occasionally failing on previously-played tracks: A small number of users couldn't download tracks they'd already played in the same browser. Downloads now request a fresh copy on every click, so the next attempt succeeds and stays working from then on. Affects both single-track and playlist ZIP downloads.

April 30, 2026

Improvements

More Room to Experiment with Prompts

We bumped the prompt character limit from 500 to 700 so you have more space to describe the sound you want. The prompt input now also shows a live character counter as you type, so you'll see exactly how much room you have left instead of running into an error after you hit generate.

Account Upgrades Now Take Effect Faster

We tightened how account plan status is refreshed across the app. If you upgrade, redeem an AppSumo code, or change plan level, the create flow now checks your latest account status before deciding whether you can generate. This is especially helpful for AppSumo users who upgraded tiers while already signed in — previously, an old browser session could still behave like a free account until you logged out and back in. Now the app refreshes your plan in the background so your new access is recognized much more reliably.

Bug Fixes

AppSumo upgraded users blocked from generating: Fixed cases where upgraded AppSumo accounts were still being treated as free users because the browser had stale plan data.
Paid feature access after tier changes: Custom branding and API access now check the latest account tier instead of relying only on older session data.
Create page credit display freshness: The create page now refreshes account data before treating a zero-credit state as final, reducing false "out of credits" messages after an upgrade.

April 24, 2026

What's New

Simple Mode — Generate a Song in One Click

Not every user wants to write a prompt. We added a Simple mode on the create page for exactly that — pick a curated Template, optionally add lyrics, set the length, and hit generate. That's it. No prompt writing, no mixer, no tag picking. 36 curated Templates to start (with more on the way), each pre-tuned with its own sound, BPM, and musical settings. Quick Create on the home page is now the Simple mode entry point — tap a Template card and you're one step away from a finished track. Advanced mode is still right there when you want the full prompt + mixer experience, and you can switch between the two without losing your place.

Write Lyrics in Your Own Language

The AI lyrics enhancer now has an "Other" language option. Pick it and type your draft in any language you speak — Thai, Japanese, Vietnamese, anything — and the enhancer will work in that same language instead of silently translating everything to English.

Improvements

Mobile Track Actions — Easier to Reach

On shared track pages, the action buttons (Play, Like, Queue, Copy link) now sit directly under the cover image on mobile so you can hit Play above the fold — no more scrolling past the title, description, stats, and tags to find the controls.

Bug Fixes

Redemption code activation while signed in: Users who were already logged in couldn't activate a redemption code on their account — fixed.

April 17, 2026

What's New

WAV Download

You can now download your tracks as WAV files for higher quality audio. When you hit download, a format picker lets you choose between MP3 or WAV.

Flexible Track Duration

The duration slider now goes down to 5 seconds with 1-second precision — perfect for short intros, bridges, jingles, or sound effects. You can also type the exact length directly (supports m:ss format like 0:15 or 1:30). Same goes for BPM — click the number to type an exact value.

Clone Mode Picker

Cloning a track now asks you what you want: a new variation (same settings, fresh seed) or an exact clone (identical reproduction, same seed). No more confusion about whether clone gives you a copy or something new.

Featured Track Prompts

Tap the three-dot menu on any featured track to see the full prompt and tags used to create it. Copy the prompt or jump straight to the create page with it pre-filled — great for learning what works.

Volume Control

The audio player now has a volume slider. On desktop it's a popup next to the player controls; on mobile it's a slider in the expanded player view. Click/tap the speaker icon to mute/unmute.

Improvements

Better Free Tier Messaging

Free plan users hitting their generation limit now see a clear upgrade prompt instead of a confusing "too many requests" error.

Improved Prompt Input

The prompt field now shows a descriptive example placeholder: "Describe the vibe you want... e.g. chill lofi with acoustic guitar for a rainy day" — helping new users write better prompts from the start.

Custom Branding — Explained

We added a dedicated section on the features page explaining exactly what Custom Branding includes: themes, logo, background, bio, social links, and white-label options. Plus a new FAQ entry and updated pricing descriptions.

Bug Fixes

BPM accuracy: Fixed a parsing issue in the API that could silently default BPM to 120. Your BPM setting now passes through correctly.
Create button reset: The sidebar and bottom nav "Create" button now properly resets to a fresh creation state when you're already on the create page.
AI Enhance overlay: The AI Enhance button on the lyrics input no longer covers text on mobile — it now has a frosted glass background.
Safari horizontal scroll: Fixed an issue where the create page could scroll horizontally on Safari/mobile.
MP3 download: Downloads now save to your device correctly instead of navigating to the audio URL.
Clone icon: Updated to a cleaner duplicate+arrow design.