Changelog

1.7.1

Improved

• ●Chat box. The message box on both tabs is wider and grows as you type, up to ten lines, then scrolls, and shrinks back after you send. The ^ button pins it at full height.
• ●More time in your DAW. A generation in a DAW now gets up to 10 minutes, as it does in the standalone app, so slow reasoning models finish instead of timing out.
• ●Local models on another computer. Point Ollama or LM Studio at a computer on your network, like http://192.168.1.20:11434 or http://studio-mac.local:11434. Settings tells you when an address cannot be used.
• ●Drum chats cost less on follow-ups. Later requests in a drum chat no longer re-send the beat grids and reference beats of earlier turns, so long sessions use fewer tokens. The request you are sending is unchanged.

Fixed

• ●Updates take effect at once. After an update, Aether replaces its helper app if one from the older version is still running, so you no longer need to quit it or restart your computer.
• ●Windows: no crash on quit, no freeze when the helper stops. Closing the standalone app while a model list was still loading could crash it, and if the network helper stopped, your DAW froze for a second or more every couple of seconds until Aether restarted it.
• ●Long recordings keep every note. A long take with a lot of pitch bend, aftertouch or pedal could freeze your DAW and lose notes. It now records smoothly, and Aether tells you if the recording buffer ever fills.
• ●Local models. Ollama now gets your whole request (it asks for a 32K context window, which uses more memory, details), LM Studio tells you how to fix a window that is too small, and a single installed Ollama model now works without choosing it first.
• ●Providers. Retired Grok models, a trailing slash on a local server URL, cut-off Claude Haiku replies and older GPT-4 models no longer fail requests, and a reasoning model's stray "</think>" tag no longer freezes the plugin. Model lists without an API key no longer send an empty login, and Gemini keeps each model's output limit after a restart.
• ●Generation. Chords you type keep their key, batch variations vary more, keep their order and keep the tempo, key, time signature and length you set, and Redo, sections and multi-track references reach the AI as you wrote them. New Chat on Drums no longer makes your next Generate request leave out your clip. A chat answer that includes MIDI now loads as a clip instead of text, and an edit that returns only some parts keeps the others.
• ●Drums. Beats follow the style, swing, drum map and pieces you pick, in batches and when opened from the Library too, and Quantize no longer doubles a hit or moves Footwork's straight hats. A project whose drum map was deleted now tells you when you open it, and switching to a drum map without some of a beat's pieces keeps every other piece on its own lane, with mute and solo on the piece you chose. Each version of a beat in the Library opens on its own style, Multi-track exports name each track as its lane does, and the drum map message now says when a piece plays as another one or cannot be placed.
• ●Library. Batches, tags and deleted versions save and show correctly, clips on an unplugged drive are kept, and confirming an action after closing the window no longer crashes the DAW. A clip that cannot be saved now says so, instead of coming back as a single part.
• ●Playback. With Loop on, the piano roll and the audio wrap at the same point; with Loop off, a clip rings out to its end; closing the window stops the preview. On Drums, muting a lane or switching Raw and Processed while stopped no longer makes the first beat play twice as loud. Switching Raw, Clean or Enhance while a clip plays keeps held notes sounding, and a layer or drum lane that is both soloed and muted is now silent, as in a DAW.
• ●Several Aethers at once. Settings, system prompts and drum maps set in one window or in the Standalone are no longer undone by another. Style preferences you edit reach the other open windows, closing a window no longer removes a clip another one just dragged, and a request's error notice appears in the window that sent it.
• ●Closing the window with a menu open no longer crashes your DAW. On Mac with the Audio Unit (Logic, GarageBand, or Live set to AU), closing Aether's window while the Drums gear settings, the Enhance settings or a dropdown list was open could crash the DAW.
• ●Also fixed: Undo after New Chat, license activation messages, license checks after you close the plugin window, a pause while the network helper starts (and the request that used to fail right after it), the Start Helper and Check Connection buttons cut off in Settings, the plugin format your account page lists for each activation, a request sent after Clear MIDI with no clip, a recording kept across a window close, the Bars total with Sections, the playback tempo dropdown (it now shows your DAW's tempo under Lock to Host), and the messages for a local model server: one that is not running is no longer reported as an internet problem, and one still working at the 10-minute limit now says the request timed out. Long notifications now wrap instead of being cut off, the Library says Show in Explorer on Windows, disabled controls such as Swing on a triplet style look disabled, the Layers channel box shows channels 10 to 16, drum plans no longer show a garbled section, and the message for a generation with no reply mentions a diagnostic report only when one is sent.

1.7.0

Improved

• ●Layers replaces Texture. Pick any mix of Bass, Chords, Melody, Pad, Arp and Counter-melody in Quick Params, or add your own with + Other. Auto lets the AI choose.
• ●Drag to DAW drags what you hear. Muted layers stay out, soloed layers go alone, and the button says what goes ("Drag 3 of 5"). Its arrow picks Single clip or Multi-track.
• ●No more offline lock. Once your purchase is 16 days old and Aether has checked in once, it never locks for being offline.
• ●Ableton racks keep their pad names, and far more drum names are recognised, from kik and hh to TR909MT.
• ●A tidier top bar. Loop is a symbol, Drag to DAW is wider, and on Drums the Single clip or Multi-track choice sits beside it.
• ●Claude costs less on quick follow-ups, like a batch or a retry within about five minutes.

Fixed

• ●Clearer license messages. A payment dispute or a deactivated computer now says so, with 48 hours' notice.
• ●Drags land where you expect, keeping your preview tempo and the channel the Layers panel shows.
• ●The screen keeps up after New, undo, redo and Import MIDI.
• ●Cancel and re-send stop the old request at once, fixing a possible crash.
• ●Prompt fix: "make the synth pop" no longer switches your chat to Pop.
• ●Update checks keep working after you close the plugin window.
• ●Plus smaller fixes to Quick Params, the layer buttons and ChatGPT drum replies.

1.6.2

Fixed

• ●On Mac, other plugins' errors are left to your DAW. When another plugin or the DAW itself hits a fault, Aether now hands it to the DAW's own handling as if Aether weren't installed, so an error another plugin would have recovered from no longer closes your DAW. Aether also stops sending crash reports for these.
• ●Closing Aether right after opening it no longer risks a crash. Closing the plugin window within a few seconds of opening it, while Aether was still starting its network helper, could crash your DAW.

1.6.1

Fixed

• ●No more re-entering your key after a month away. When Aether hasn't checked your license in over 30 days, it now checks again when you open it and unlocks on its own. Offline, it stays locked until it can reach the license server, then unlocks shortly after you reconnect. Aether still works for 30 days without a connection, as before.

1.6.0

Improved

• ●More variety. The same request in a new chat now gives you a genuinely different take instead of the same idea again.
• ●A key you type wins. When your message names a key, such as "in F# minor", Aether now uses it instead of the Key and Scale controls. With Key on Any key, new chats also no longer keep landing in the same key.
• ●Cheaper follow-ups. Follow-up requests in a chat now use noticeably fewer tokens, so a long session costs less.
• ●Reasoning Effort for Claude. Claude Opus 4.5 and later, Sonnet 4.6 and later and Fable now have the Reasoning Effort control. It starts on Model default, which leaves each model on its own level, and Low makes generations much faster: an 8-bar Sonnet 5.5 piece took about 40 seconds instead of one and a half to two minutes.
• ●Smoother on Windows. Resizing the window takes about 40% less work, and opening or closing a side panel with a long chat about 70% less, so it slides without stalling. A panel's contents now appear already laid out as it opens, instead of re-wrapping as it widens. Aether no longer redraws the piano roll or re-measures its side panels while you aren't using it, dragging a column divider or an Enhance slider keeps up with your mouse, and scrolling the chat past your own messages and Pro Mode plans does far less work.
• ●The update notice stays until you update. When a new version is out, Aether now tells you every time you open it, including in Logic, and a check that fails tries again an hour later. Dismissing the banner hides it for that version; a small dot on Settings, a matching dot on the About tab and a line on About stay until you install the update, with links to download it, see what's new, or get release emails.

Fixed

• ●The right genre and the right parts. "Make it pop" no longer switches your chat to Pop, "a funk tune with a slap bass line" now writes the whole tune instead of only the bass, and "remove the horns" removes them for good.
• ●Sections come out the length you asked for. Bar counts now land on the sections you wrote them against, as in "verse (8 bars), chorus (16 bars)", and a length for the whole song is shared between its sections. A tempo or time signature is no longer mistaken for a bar count, and edits such as "make the chorus bigger" no longer turn your whole clip into one Chorus.
• ●Redo gives a new take. Redo now asks again from your original request and starting point, on both tabs, instead of reworking the take it replaces.
• ●Better batches. Variations now differ more from each other, and every one uses your dropped file, recording or loaded clip. A batch no longer repeats on your next send, stops partway, or drifts into a genre you didn't ask for.
• ●Recordings reach your next message. Notes you record are now sent with your next message in a new chat. With a clip loaded, Aether tells you to start a New Chat to use them.
• ●FL Studio keeps your session. Minimizing Aether in FL Studio no longer clears your chat, typed message, attached MIDI or controls, and no longer leads to a crash. Your chat and controls are now also saved with your project.
• ●Library fixes. Clips no longer go missing when Aether is open in two places at once, such as two plugin windows or your DAW and the Standalone, and Refresh offers to restore any that did. Changing the save folder or deleting an idea now covers every version, and Add to Chat keeps a clip's tempo, time signature and parts. Filtering by a tag whose name contains brackets, such as "Lo-fi (dusty)", now shows its clips, and the tag filter keeps its choice when your tags change.
• ●Gemini works with new API keys. Gemini now starts on Gemini 3.8 Flash, and a saved Gemini 2.0 Flash choice, which Google has shut down, moves to it. If Gemini 2.5 fails on your key, switch to Gemini 3.8 Flash in the model list. Override default temperature does not apply to Gemini 3 models.
• ●Claude works again, newest models included. Claude now starts on Sonnet 5.5, since Anthropic has shut down Sonnet 4, the old default, and a saved choice of another shut-down model, such as Opus 4.1, moves to Sonnet 5.5 as well. Opus 5.5, Sonnet 5.5 and Fable 5.1 now generate instead of failing with an error. When Claude declines a request, the chat now says so and shows the reason Anthropic gives.
• ●Tempo and meter fixes. A waltz, or a meter you type such as 6/8, now comes back in that meter instead of 4/4, unless Lock to Host or a Time Sig other than 4/4 is set. Drums now follow your DAW's time signature with Lock to Host on, tempos above 300 BPM work on the Melodic tab, and changing drum controls no longer resets your tempo.
• ●Other fixes.
  • ○Drag to DAW no longer drops MIDI back into Aether.
  • ○Two layers on the same note both show in the piano roll.
  • ○Switching providers mid-chat no longer loses what you asked for earlier.
  • ○The AI provider, model, or Ollama or LM Studio server address you choose no longer reverts to your previous choice the next time Aether opens.
  • ○A generation is no longer canceled by a send on the other tab or by opening Settings.
  • ○Picking a kit in the Drums tab's Sound menu no longer freezes the window, and the previous kit keeps playing until the new one is ready.
  • ○Collapsing a column right after dragging its divider no longer makes it jump wider first.
  • ○Settings no longer shows a MIDI preview channel control, which had no effect.
  • ○Override default temperature now shows as unavailable for every ChatGPT model that ignores it.
  • ○Aether no longer sends a temperature to Claude Opus 4.7 and later, Sonnet 5 and later or Fable, which reject it, and Override default temperature shows as unavailable for them.
  • ○The note count on your message now includes layers named for an instrument, such as a violin. Only the count was wrong; those notes were always sent.
  • ○A note that starts where the same note ends, or just before, now plays, and keeps its length when you drag the clip out or it is saved to your Library. Before, it could play silent and land in your DAW as a zero-length note. Importing or dropping a multi-track .mid, or loading one from your Library, also keeps both notes where one track ends a note just as another track starts it.

1.5.0

New

• ●Drop in a Drum Rack. Drag an Ableton .adg onto the Drums tab and Aether reads every pad, its note and its name, and builds the drum map from it. The map opens filled in so you can check it before you save, and dropping the same rack again updates that map instead of making a second one.
• ●Your own pads, named your way. Drum maps can now hold pads beyond the sixteen standard names, such as "Cajón", named in any language, and Aether writes parts for them. Each pad also has an optional note for saying what an unusual pad is.
• ●Eight more drum styles. Alt-Pop, Afrobeats, Country, Hardstyle, Jersey Club, Phonk, R&B / Neo-Soul and Reggae now each have their own kit, groove and fills.

Improved

• ●A fuller first-run tutorial. The walkthrough now covers the Drums tab and its controls, refreshing your model list, and the custom system prompts for each tab, in fourteen steps instead of nine. It opens each panel it points at, so you see the real control rather than a collapsed rail.

Fixed

• ●Aether picks the style you meant. Requests such as "amapiano house", "indie pop" or "garage rock" now get the style you named instead of a neighboring one, and Afrobeats (2010s West African pop) is now its own style, separate from Afrobeat (the 1970s band sound).
• ●Better beats. Drum and bass now comes back as the two-step at around 174 BPM, with snares on 2 and 4; ask for "half time" if you want the old feel. Beats now fill every bar you ask for, trap hat bursts and big room fills can use 32nd notes, and a BPM you set now wins over a style's usual tempo.
• ●Drums tab fixes. The export shape selector (Combined, Multi-track, Single piece) is now on screen and remembers your choice, the drum map card now shows in the chat, and the drum ruler counts beats (1.1, 1.2, 1.3) like the Melodic roll. Maps saved by older builds show proper pad names, such as "Kick" instead of "kick".
• ●Loops without a tempo map fully. A dropped loop that carries no tempo, such as one from Ableton's Export MIDI Clip, now gets its kick and snare mapped too, not just the hi-hat, and the import dialog tells you it used your session tempo.
• ●Melodic clips remember what you asked for. Library clips from the Melodic tab now save your prompt instead of "Chat generation", so you can search them by what you wrote. Clips saved earlier keep their old label.

1.4.0

New

• ●A Drums tab. Own chat, controls, clip and provider. Switching tabs keeps both. A finished beat never yanks you over.
• ●Generate is now Melodic. Same tab, new name, now that Drums sits next to it.
• ●Beats land on the right pads. Aether assigns every drum pitch. The model only names pieces. Exports on channel 10.
• ●Kit lanes instead of a piano roll. One lane per piece, kick at the bottom, solo and mute on the lane, velocity as opacity.
• ●About thirty styles. Boom bap, trap, drill, house, techno, jungle, UK garage, afrobeat, amapiano and more. Or just describe it.
• ●Live controls, no generation. Quantize, swing, humanize and ghost depth edit the beat you already have and bake into the drag-out.
• ●Three preview kits. Live Kit, Electronic Kit, Hip Hop Kit. Sound is what you hear in Aether. MIDI Map is what leaves for the DAW.
• ●Batch on Drums. 2 to 5 beats from one prompt, told apart in drum terms so they diverge. Numbered buttons switch between them.
• ●Drum map in the reply. Note, piece and pitch names, plus Copy map. The Note names chip picks Live or scientific conventions.
• ●Three export shapes. Combined (one track), Multi-track (one track per piece), Single piece (one lane, C3, for a one-shot sampler).
• ●Drop a MIDI beat in. It becomes the clip and the next-prompt reference. Tempo and meter fill in. Live controls work on imports.
• ●Any pad layout, not just GM. Import opens a mapper with a guess and hit counts. Save the map. The next loop from that rack comes in filled.
• ●Unmapped pieces still play. Missing entries fall back to GM and say so. Changing a map re-reads the beat on screen. No regenerate.
• ●Sections on Drums. Named parts with bar counts (Intro 8, Build 8, Drop 8). Suggestions follow the style.
• ●Beats go to the Library. Typed as Drums or Melodic, filtered by the tab you are on. A batch is one card. Add to chat uses a beat as the next reference. A saved beat reopens on the map it was written under, even after you rename or delete that map.
• ●Separate system prompt for drums. Settings has Active prompt for Melodic and for Drums. Drum starts empty so an old melodic prompt does not steer beats.
• ●Pro Mode on Drums. Plan, then write. One toggle for both tabs. With Batch each variation is planned on its own, so five variations is ten calls.

Improved

• ●Quick Params, Chat and Library are resizable. Drag the seam. Widths persist. Chat is shared by both tabs.

Fixed

• ●ChatGPT and Gemini now show the same Thought-panel plan as Claude, Grok and DeepSeek.
• ●Library cards keep ratings and action buttons at any panel width.
• ●Library clips, imports and older takes loop at the last bar, not through trailing silence.
• ●The first batch variation appears as soon as it lands.
• ●Standalone keeps settings changed during the session. Window and audio device state now live in their own file.
• ●Melodic layers are no longer auto-assigned to channel 10. Manual routing there still works.
• ●A batch is one undo step, starts off after a restart, and unlocks the model picker when you cancel.
• ●Gemini generations include genre again.
• ●Imports fill Key, BPM and Time Sig from every drop route, not only the chat box.

1.3.2

New

• ●Importing your own MIDI now sets the key and tempo. Aether fills the Key and BPM controls from the file and highlights them so you can see where the values came from, and the chat says which ones it took. Both were previously described to the AI but never pinned, so about one variation in three drifted out of key or tempo. Files with no clear key are left alone rather than pinned to a guess.
• ●Timing checks work on imported material. An empty BPM box used to switch off the check that compares a finished clip against the beat it was asked for. A tempo read from your import turns it back on.
• ●Three MIDI references instead of two. Aether also tells you which files did not fit when you drop more.
• ●Multi-track MIDI keeps its parts. Tracks arrive named instead of being merged into one block of notes, so "an alternative guitar idea over the existing harmony" now has something to work with. A multi-track file counts as one reference, so a four-part arrangement does not use up your three slots.
• ●Clear MIDI. A button beside New and Redo, shown whenever files are attached, that detaches them. Removing the wrong file no longer means starting a new chat.
• ●A batch is one card in the library, not one per variation. Expand it to see the variations, each of which plays on its own. None is promoted above the others, because none supersedes anything. Batches saved before this update stay as they are.
• ●A play button on every clip in the library. Every row has one, including the earlier versions under an idea, whether or not the row is selected. Double-clicking still auditions a clip; nothing on the row ever said so.

Fixed

• ●The local model picker no longer lists models you do not have. Ollama offered six popular model names and LM Studio offered one called Default Loaded Model, none of which came from your machine, so choosing one could fail against a model you never installed. The picker now asks you to click Refresh Models, then lists what your server actually reports and remembers it between visits.
• ●Local AI models could not connect from inside a DAW. Ollama and LM Studio worked in the standalone app but reported the server as unreachable when Aether ran as a plugin, even with that server running. Test Connection and Refresh Models now go through Aether's network helper, the way generation already did, instead of opening a connection your DAW blocks. Neither freezes the window while it waits, and if the helper is the missing piece the message says so.
• ●Picking a local model from the refreshed list did nothing. After a refresh, choosing anything below the first entry left the previous model in place. The list is now wired to the models it is showing.
• ●Batch generations were saving nothing at all. Each batch created a folder named after your prompt and left it empty, because the filename Aether built held the model's entire response and was far too long for the filesystem to accept, and the failure went unreported. Single generations were never affected.
• ●Genre, Mood and Texture can be cleared again. All three menus now have a "None" row.
• ●The library tells you which version you are looking at. Expanding an idea with two takes showed a single row labeled v1, which read as though the newer take was gone. It was not: that row was the newer one, and the only one that never said which version it was.
• ●Dropping files one at a time adds them instead of replacing. Each drop used to clear whatever was already attached, so three parts dropped in turn left only the last.
• ●The attachment tag names every file you attached, not just the first.

1.3.1

New

• ●New models arrive with their controls already working. The reasoning-effort setting was only offered for models Aether had been told about by name, so it quietly disappeared every time a provider released something new. Aether now assumes a new model supports it and stops sending it if the provider refuses, so a model released tomorrow gets its controls today.
• ●New OpenAI reasoning models appear in the picker on their own. The model list recognized the o-series one generation at a time, so a new one would not have shown up at all: not missing a feature, missing from the menu, with nothing to explain why.
• ●Every layer has its own channel selector. Output routing lived in Settings and had exactly three rows (Bass, Harmony and Lead), so an arrangement with a pad, an ostinato and a horn section could only have three of its layers pointed anywhere deliberately. Each row in the Layers panel now carries its own channel, and the remaining layers are given free channels around whatever you set, so nothing ever quietly shares one. Your choices are saved with the project and follow the layer, so re-voicing a part keeps it where you put it.
• ●The channel shown next to a layer is the one it exports on. It used to be the preview channel, which stopped matching the file once your routing settings started being applied to it.
• ●Live MIDI output follows your channels too. Monitoring a layered clip out to another instrument or to hardware sent the entire arrangement on a single channel, whatever you had set, because the channel was being dropped before the notes left the piano roll. Every layer now goes out on the channel it is actually assigned, so what you hear while monitoring matches what you get when you drag the clip out.

Changed

• ●Aether remembers which model you use with each provider. Switching from ChatGPT to Grok and back reset you to whatever model was current when the plugin was built, throwing away the choice you made. Each provider now keeps its own, and the built-in default only applies the first time you use that provider.
• ●Grok's model list is current again. xAI retired ten of the models Aether offered, including the one it picked by default, so anyone whose list had not refreshed was choosing from mostly dead options. The list now covers Grok 4.6, 4.5, 4.3 and 4.20, and the default is Grok 4.6.
• ●Cancel in Settings discards the provider and model too. Changing them applied immediately, so "Discard changes and close" kept the very thing you were trying to undo.
• ●Dragging a clip in can no longer change a sound you already chose. Exported files carried a General MIDI patch number at the top of every track. That is an instruction rather than a note, and the instrument already sitting on the track you dropped onto would obey it and switch its own preset, which looks, from where you are sitting, like the plugin reaching into your session and altering your instrument. Aether no longer writes them. If you are exporting for a General MIDI player and want the patch numbers back, there is a new switch in Settings → MIDI under Exported Files.

Fixed

• ●GPT-4 and GPT-4 Turbo failed every single generation. Aether asked for more output than either model allows and the API refused outright. Both work again.
• ●GPT-5 models could stop mid-clip. They were given a quarter of the output budget they support, and because thinking is charged against the same budget, a longer arrangement could run out of room before the music was finished.
• ●Reasoning effort works on the Pro models. GPT-5 Pro and GPT-5.5 Pro were sent the setting in a form Aether could not correct if it was refused, which could leave the model unusable with no control left to switch off.
• ●Changing provider mid-generation no longer throws the result away. A finished, paid-for generation was read by the newly selected provider instead of the one that produced it, and reported to you as an empty response.
• ●Voice, coding and research models are out of the picker. Grok's speech and coding models and OpenAI's deep-research models were all listed and none of them can write MIDI, so picking one failed every time.
• ●A model that gains reasoning support gets it back. When a provider refuses the effort setting Aether remembers and stops sending it, and that memory was permanent, so a model that later gained support would never have offered the control again. It now rechecks periodically.
• ●Your MIDI channel settings now reach the file you drag into your DAW. Part Output Routing was only ever applied to Aether's live MIDI output, while the file the drag hands your DAW numbered its channels by the order the layers came back in, so setting every part to channel 1, or to anything else, changed nothing about what actually landed in your project. Parts now follow the channels you set, and extra layers the model invents, like an ostinato or a named horn section, take the next free channel instead of quietly landing on top of a part you had already routed.
• ●Clips dragged out in Combined mode are the length you asked for. A region ended a quarter note past the last note instead of on the bar the clip was written to, so an eight-bar idea whose final chord stopped early arrived as an awkward eight-and-a-bit. Multi-track drags and clips saved to the library were already correct; this was the one path still guessing the length from wherever the notes happened to stop. Dragging a single layer out on its own was affected the same way.
• ●Combined mode flattens the channels, not just the tracks. The setting reads "Combined (flatten to Output Channel)" and only ever delivered half of that: you got a single track, but the notes inside it kept the separate channels Aether uses internally to tell bass, harmony and lead apart. An instrument listening on one channel heard a fraction of the arrangement, and the only way through was to renumber every item by hand once it was in the DAW. Combined now puts every note on the Output Channel you picked.

1.3.0

Highlights

• ●Clips land in time. This was several separate faults, not one. The section editor was silently dropping the timing reference Aether sends. Some styles asked every part to sit behind the beat, which just makes a clip late. Quantize offered straight and swung grids at once, so tightening a note could change its rhythm. And Aether trusted the tempo written into each response: a clip written correctly at your project tempo but labeled with the genre's usual tempo got stretched to match the label, sometimes to twice its length.
• ●Aether checks its own work. Every generation is measured against your project's bars and beats before you see it. If the notes and the reported tempo disagree, the notes win and the label is corrected. If a clip cannot be verified, Aether says so instead of handing it over quietly. Deliberate feel is safe: a bass on the beat with keys leaning behind it is a pocket, not an error. Styles with no fixed pulse, like ambient and cinematic, are exempt.
• ●The sustain pedal works. Aether has been writing pedal markings all along and every one was discarded before it reached playback, the piano roll or an exported file. Ballads, ambient, classical and gospel lost the sustain the writing assumed. It now survives everywhere, including both kinds of drag-out.

Fixed

• ●Sections stay in time from the first bar to the last. With the section editor on, longer forms drifted further out with every section. Each section now gets its own start and end time instead of adding bar counts up.
• ●Laid-back styles feel laid-back instead of late. R&B / Neo-Soul, lo-fi and ballads put every part behind the beat at once, and nothing anchors a groove if everything moves. The bass now holds the beat while the keys and lead lean back against it.
• ●Dragging out gives you what you were hearing. Dragging a multi-part clip as separate tracks rebuilt it from the untouched original, so your Clean or Enhance settings were missing. Dragging the same clip as one track included them.
• ●Asking for a bassline no longer means asking for only a bassline. Naming a layer anywhere in your message was read as a restriction, so "drum and bass, rolling sub bassline and atmospheric pads" gave you a bass part and nothing else. "Just bass", "melody only" and "chords only" still mean what they say.
• ●Aether remembers the style you asked for. Naming a genre set it for that message only, so following up with "make the bass busier" lost the style. It now carries through a conversation until you change it.
• ●Clips are the length you asked for, and loops loop. A clip whose last note stopped before the final bar arrived in your DAW short, and loop mode waited out the last note instead of returning at the bar line. Both now follow your bar count, whether you set it in the Bars field or wrote "an 8 bar loop".
• ●Changing your project tempo no longer stutters playback. Automating tempo in your DAW made Aether rebuild and restart the clip twice a second while you were listening.
• ●Electronic styles fit the length you asked for. Trance, drum & bass, dubstep and festival each described a full arrangement with fixed section lengths, so a shorter clip squeezed that whole shape into the space available. A 32-bar trance spent half its length in breakdown with the rolling bassline missing.
• ●No more drum parts. Aether does not write drums, but nothing in its instructions said so, and drum & bass kept adding a breakbeat layer you had to delete. Styles still write around the drums you will add, which is why a trance bassline leaves the downbeat clear.
• ●Quantize snaps to the grid your music is on. It offered straight and triplet grids together, so a slightly early sixteenth could get pulled onto a triplet, changing the rhythm instead of tightening it. It now uses the one grid the style works on, and styles with no fixed pulse get the sparsest option rather than the densest.
• ●Dropped MIDI keeps its starting position. A file beginning with a bar of rest had that bar removed. Recordings you make in Aether still snap to your first note.
• ●The BPM box shows your real project tempo. With Host on, a session at 128.5 read as "128". Only the display was rounding.
• ●Trance leads hold their hook. The lead was picking up stray notes a sixteenth off the pulse, which against a rolling bassline reads as a stumble.
• ●Chord preservation works with the section editor on, clip names count bars correctly in 6/8, and changing your audio device's sample rate no longer leaves a loaded clip playing at the wrong speed.

Changed

• ●Time signature defaults to 4/4 instead of "Let AI Choose". Aether can only send its timing reference when it knows the meter, so the old default left generations without one. "Let AI Choose" is still there.
• ●UK garage's shuffle is a little tighter, and holds steady across a clip instead of varying note to note.

1.2.2

Improved

• ●Every genre now writes like itself. Each of the 16 styles carries exact note placements, velocity shapes and layering rules of its own, instead of generic advice. Trap leaves the 808 hitting alone, funk's bass and chords interlock instead of stacking, bossa uses its real two-bar comping pattern, and gospel's vamp escalates each time round.
• ●House / EDM is now Electronic, and it understands what you asked for. One setting used to cover house, techno, drum & bass, dubstep, garage and trance with a single set of festival-oriented instructions and no sense of tempo, so asking for drum & bass gave you house-speed drum & bass. Say what you want and you get it: warehouse techno stays hypnotic and hookless, liquid drum & bass rolls at 174, UK garage swings and skips, dubstep sits in half-time, trance gets its long breakdown, and asking for nothing in particular still gives you house.
• ●Sections sound like sections. A bridge or solo that previously only moved higher and louder while reusing the same rhythm is now required to change where the notes land.
• ●Quiet genres are allowed to be quiet. Ambient, lo-fi and trap were being pushed toward pop density and dynamics by rules written for pop. Those rules are now defaults a style can override, so sparse music stays sparse and a pad layer can breathe.
• ●Mood and tempo now affect the writing itself. Asking for something dark or bright, or working well outside a style's usual tempo, changes the harmony, register and note placement rather than just the description.
• ●Classical understands specific forms. Ask for a waltz, nocturne, fugue, sonata or a particular era and you get guidance for that form instead of a summary of all of them at once.

Fixed

• ●Naming a style in your prompt actually works. Genre detection was reading the message box after it had already been cleared, so free-text requests for house, drum & bass, a jazz ballad or a waltz were ignored and fell back to general songwriting. They now reach the right style.
• ●Velocity color is visible in the piano roll again. Multi-part clips were rendering with almost no difference between soft and hard notes.
• ●Renaming a clip no longer flattens it. A renamed clip was reloading as a single merged layer and losing its version history.
• ●The playhead now plays from where you put it. After pausing, moving the playhead and pressing play was resuming from the old position.

1.2.1

Improved

• ●Generations are substantially faster. Aether now reuses the unchanging part of its instructions between requests instead of paying to re-read them every time, and lets you tell each model how long to deliberate before writing. The longer you stay in one session, the more of the work is already cached.
• ●Pro Mode is dramatically faster when editing. Asking Pro Mode to change an existing clip made its planning pass quietly write a whole arrangement and throw it away before composing the real one, so every edit did the work twice and the wasted attempt was carried into the second pass. The planning pass now plans. Edit turns finish in a fraction of the time, and the plan itself is unchanged in quality: it still studies every note of your clip.
• ●Reasoning-effort selector now appears for Gemini. The Low / Medium / High control shows for Gemini 2.5 and later. On Gemini, Low switches the model's deliberation off entirely, which is the fastest setting available; Medium stays the default, so nothing changes unless you choose it.

Fixed

• ●Pro Mode no longer stops with a "rate limit" message on fast generations. Now that a generation can finish in a couple of seconds, Pro Mode's composing pass could arrive too soon after its planning pass and be turned away by Aether's own request throttle. The plugin was rate-limiting itself. That throttle now applies only to requests you start.
• ●Clearer message when a provider returns nothing. If a model takes so long that the connection closes before it replies, Aether reported "Invalid JSON response from API", which pointed at a formatting problem that did not exist. It now says the provider returned an empty response, and suggests retrying or switching to a faster model.
• ●Saved sessions no longer carry unnecessary MIDI data. The routine that trims note data out of saved conversations was still looking for an older format and had quietly stopped matching anything, so session files were larger than intended.
• ●Adding a layer no longer sometimes merges your existing layers. When you asked to add a new layer, the existing arrangement could occasionally collapse into a single combined track instead of staying as separate layers. Edits now build on your real, named layers every time.
• ●Reasoning-effort selector now appears for Grok. The Low / Medium / High control that trades speed for depth now shows for the Grok models that support it (such as Grok 4.5), so you can dial in how hard Grok thinks before composing.
• ●Attached MIDI files now land at your project tempo. MIDI exported from Ableton Live carries no tempo information, so Aether read those clips at a fixed 120 BPM while telling the model your session tempo. A 4-bar idea dropped into a 140 BPM project came through as roughly 4.7 bars, and whatever Aether wrote back sat off the grid. Attached files now use your session tempo when the file does not specify one, and their own tempo when it does. Files that happened to be at 120 BPM were always fine and are unchanged.

1.2.0

New

• ●Compose in layers, not just Bass / Harmony / Lead. Aether now builds arrangements from any number of named, instrument-tagged parts. Ask for "a horns section" or "an ostinato under the piano" and the new layer is added alongside what you already have instead of replacing it. Each layer carries the instrument name the model chose, normalized to a General MIDI sound.
• ●Layers view. A toggle in the toolbar opens a dedicated panel listing every layer with its instrument, a mini piano-roll preview, and per-layer Solo / Mute. A header shows the detected key, tempo, and layer count, and you can flip the labels between instrument names and part roles.
• ●Named, GM-mapped MIDI export. Dragging or exporting a multi-layer clip now writes one named track per layer with the matching General MIDI program change, so your DAW loads each part onto the right instrument automatically.
• ●Drag a single layer to your DAW. Alongside the whole-clip drag, each layer has its own colored handle you can drag out on its own.
• ●Per-layer colors in the piano roll. Every layer gets its own color so overlapping parts stay readable at a glance.
• ●Layers work on every provider. Claude, ChatGPT, and Gemini are now asked for layered output through their own structured-output formats, so named, instrument-tagged layers come back whichever model you pick. (Older Gemini models, such as 2.0 Flash and the 1.5 family, still return the classic Bass / Harmony / Lead trio.)
• ●Custom layers get the same polish as the main parts. Note clean-up, pitch clamping, and humanization now run on every layer you create, including instrument-tagged ones, not just Bass / Harmony / Lead.
• ●GPT-5 Pro models now work. OpenAI's "pro" models (such as GPT-5.5 Pro and GPT-5.4 Pro) run on a different endpoint from the standard chat models and previously failed to generate. Aether now talks to that endpoint automatically when you pick a pro model, so they compose like any other.

Improved

• ●Reasoning-effort control now covers OpenAI, and Pro models start fast. The Low / Medium / High reasoning selector, previously Grok-only, now also appears for OpenAI's o-series and GPT-5 models (including the Pro tiers). Each provider keeps its own setting, and OpenAI reasoning models default to Medium, so GPT-5 Pro composes in a couple of minutes instead of running its default High effort for many minutes on a short idea. Turn it up when you want maximum depth.
• ●Solo reflects what you actually hear. Soloing a layer now dims the other layer buttons in the toolbar, so the top bar always shows what is currently audible.
• ●Seamless muting for overlapping layers. Muting or unmuting one layer while parts share pitches no longer briefly cuts or re-triggers the notes held by the other layers.
• ●Onboarding tutorial covers layers. The walkthrough gained dedicated steps for the layer controls and the Layers view.

Fixed

• ●Runs on macOS 11 (Big Sur) and later, on both Apple Silicon and Intel Macs. A build setting had raised Aether's minimum to the very newest macOS, so on earlier systems the standalone app would not open ("cannot use this version of the application with this version of macOS") and the plug-in failed to load in your DAW. Aether now installs and runs across supported macOS versions again.

1.1.5

New

• ●Choose which OpenRouter providers you see. OpenRouter exposes hundreds of models, so the list could be overwhelming. In Settings, a “Providers” picker lets you tick exactly which upstream providers (Anthropic, OpenAI, Google, and so on) appear in the model dropdowns, with Select all / Clear all and Save.
• ●Per-version actions in the Library. When a saved idea has multiple versions (v1, v2, v3...), each version now has its own actions menu: Add to Chat, Show in Finder, and Delete.

Improved

• ●Seamless part muting. Muting or unmuting Bass, Harmony, or Lead during playback no longer briefly doubles the other parts' notes; only the part you toggled changes.
• ●Clearer Library buttons. Action buttons now have tooltips, the redundant “Chat” and “Variation” buttons are merged into a single “Add to Chat”, and deleting a clip now asks you to confirm, since it removes the file from disk.
• ●Better onboarding tutorial. The Raw / Clean / Enhance step is easier to read, the Library and Toolbar steps now explain the action buttons and the Bass / Harmony / Lead controls, and the Settings step covers custom system prompts, temperature, and Pro Mode reasoning.

Fixed

• ●Custom system prompt text now saves. Editing a custom system prompt's name or body and then closing Aether no longer discards what you typed; any in-progress edit is committed to disk on close and restored on the next launch.
• ●Grok's model list no longer shows the code-only and multi-agent models, which are not applicable to music generation.
• ●In System Prompt settings, clicking a prompt in the list now moves the highlight to match the prompt shown in the editor.
• ●Fixed the tutorial's Enhance step, where the navigation buttons could overlap the popover and the step appeared to show twice.

1.1.4

Fixed

• ●Some models (most often Claude routed through OpenRouter) could print a large block of raw JSON into the chat instead of the usual plain-language summary, which could also make the interface feel sluggish. Generation responses are now parsed cleanly no matter how the model formats them, so you only ever see the summary.
• ●The Pro Mode plan view (the “Thought” panel and the reasoning card) now shows the readable composition plan for every model. Previously, models that wrap their output in code fences (most often Claude routed through OpenRouter) could display a block of raw JSON here instead of the formatted plan.

1.1.3

Improved

• ●More reliable licensing. Activation and license checks now retry automatically through brief network hiccups, so an unstable connection is far less likely to cause a failed activation or a false “couldn't reach the server” message.

1.1.2

New

• ●Return to playhead. When you scroll the piano roll away from the playhead, a small “↩ Playhead” button appears so you can jump the view straight back.

Improved

• ●Smoother seek. After double-clicking to set a start point, pressing play now glides the view to the playhead instead of snapping to it instantly.

Fixed

• ●Auditioning a variation while a batch is still generating no longer cuts out when the next variation finishes.
• ●The piano-roll playhead now stays locked to what you're actually hearing after you scroll the view. Previously it could drift out of sync with the audio.

1.1.1

New

• ●Automatic update notifications. Aether now checks for new versions on launch and shows a small, dismissible banner when one is available, with a direct link to download. No more missing an update.

Improved

• ●Better Grok results. Reworked the composition prompting for Grok models so they produce denser, more complete parts instead of sparse or repetitive ones.

Fixed

• ●Fixed an error when using the reasoning-effort setting with Grok models that don't support it.
• ●Stopped occasional false “generation failed” messages that could appear after you canceled or resent a request.

1.1.0

New

• ●Reasoning effort for Grok. A Low / Medium / High selector in Settings lets you trade speed for depth on Grok models that support it. It only appears when the selected model offers it.

Improved

• ●Cleaner Pro Mode. The plan and result now appear together in a single “Composition plan” card.
• ●Stronger Grok composition prompting for more musical, less generic output.

Fixed

• ●The reasoning card no longer clips its content when expanded.
• ●The reasoning card now appears in the right place: after your message, not before it.

1.0.1

New

• ●See the AI’s reasoning. Aether can now show the plan it’s working from as it composes, for both standard and Pro Mode generations. Turn it on or off with the new “Show AI reasoning” setting.
• ●Per-variation Pro Mode. When generating a batch, each variation now gets its own independent plan and composition, so the options feel more distinct.

Improved

• ●Smarter edits. Mentioning a part in an edit (e.g. “make the bass busier”) now focuses on that part instead of removing the others.
• ●Tidied the interface: fixed the Quick Params clear button icon and removed a setting that no longer did anything.
• ●Hardened privacy in the reasoning view so internal planning context stays internal.

Fixed

• ●Canceling a generation now stops cleanly, with no leftover “Planning…” spinner.
• ●Pro Mode now saves your actual prompt to history instead of its internal planning text.
• ●Windows: resolved an installer hang on reinstall, made the background helper exit automatically when your DAW closes, fixed a port conflict that could block AI requests, and corrected a packaging issue with the bundled piano instrument.

1.0.0

Highlights

• ●Generate bass, harmony, and lead parts from natural-language descriptions.
• ●Choose your AI provider (ChatGPT, Claude, Grok, Gemini, and more) with your own API key.
• ●Chat-based workflow: ask for changes, regenerate, and refine in context.
• ●Pro Mode for a plan-then-compose approach to more deliberate results.
• ●Built-in piano-roll preview and one-drag export straight into your DAW.
• ●Save and reuse your favorite generations from the library.