$10 a month or $100 a year. Unlimited runs, cancel any time. 2 free runs to try it first.
Hear it
One target sound, resynthesised to both synths. The renders are the presets Audial returned, unedited; the Serum 2 patch scored 0.987 for similarity.
Pick your synth: Vital gives you a .vital preset that opens in Vital or in Audial Synth, Audial's free GPLv3 fork of it, and Serum 2 gives you a .SerumPreset that opens in Xfer Serum 2 with nothing to install.
Upload one isolated sound of up to 20 seconds and Audial's hosted engine returns a preset whose oscillators, filters and envelopes are set to reproduce it, plus a render so you can hear how close the match came. Because the result is a preset and not a sample, every parameter stays editable: detune it, filter it, re-envelope it, play it across the keyboard.
Each run also returns two keyboard renders and a JSON report with a similarity score for the match. Vital jobs typically finish in 60 to 250 seconds; Serum 2 takes about 2½ minutes, plus up to 2½ minutes if a machine has to start. Run it from the Resynth tab, from audial.sound2vital or audial.sound2serum in Python, from /functions/run/sound2vital and /functions/run/sound2serum, or as the sound2vital and sound2serum MCP tools.
What you get
- Any single sound up to 20 seconds becomes an editable preset
- Two targets: a .vital preset for Vital or Audial Synth, or a .SerumPreset for Xfer Serum 2
- Parameters stay editable, so this is a patch and not a sampler instrument
- Returns the preset, a render, two keyboard renders and a similarity score
- Audial Synth, a free GPLv3 fork of Vital, runs the same resynthesis from inside your DAW on the same subscription
- Vital jobs finish in 60 to 250 seconds; Serum 2 takes about 2½ minutes, plus a cold start
Use it from code
curl -X POST "https://api.audialmusic.ai/api/functions/run/sound2vital" \
-H "X-API-Key: your_api_key" -H "X-User-ID: your_user_id" \
-F "userId=your_user_id" \
-F "original=@/path/to/clip.wav"import audial
audial.config.set_api_key("your_api_key")
audial.config.set_user_id("your_user_id")
result = audial.sound2vital("clip.wav")
print(result["preset"]) # the .vital preset built from the clip
serum = audial.sound2serum("clip.wav")
print(serum["preset"]) # the .SerumPreset built from the same clip# In Claude, Cursor or any MCP client with audial-mcp installed:
"Resynthesize ~/Samples/bass_oneshot.wav into a Serum 2 preset and tell me the similarity score."Frequently asked questions
Rebuilding a sound out of synthesizer parameters instead of storing it as a sample. Audial listens to your clip and sets a synth's oscillators, filters and envelopes so it plays that sound back, which leaves you free to change any of it.
Two: Vital, which returns a .vital preset, and Serum 2, which returns a .SerumPreset. Pick the target above the uploader on the Resynth tab; Vital is the default and the last choice is remembered.
A preset file (.vital for Vital, .SerumPreset for Serum 2), a render of the preset, two keyboard renders, and a JSON report with a similarity score for how close the match came.
Up to 20 seconds, for both targets, and ideally 1 to 4 seconds. Resynthesis models one isolated sound, so a loop, melody or drum pattern gives a poor preset even under 20 seconds. Trim a loop to one note first.
A Vital preset opens in Vital, or in Audial Synth, a GPLv3 fork of the Vital synthesizer with a Resynth panel added, on the downloads page for macOS (VST3, AU and standalone) and Windows (VST3 and standalone). A Serum 2 preset needs no download at all: drop the file into Serum 2's user presets folder, or drag it onto the Serum 2 window.
Yes. Post the clip to /functions/run/sound2vital or /functions/run/sound2serum, call audial.sound2vital or audial.sound2serum from the Python SDK, or use the sound2vital and sound2serum tools through the Audial MCP server.
Yes. Every resynthesis run goes through the Audial engine, so after your 2 free runs it needs an active subscription — the same on the website, in the Audial Synth plugin, through the API, the SDK and MCP. Audial Synth is free to download and plays presets without a subscription, but it cannot resynthesise without one.
