An AI that listens to your song and gives you notes
A live concept demo at songllm.com. An audio-native model hears a track and returns a producer's reading pinned to the waveform, with three suggested changes and the instruction for the tool that would make them.
Visit songllm.com
The purpose
Music generators and editors are plentiful. What a songwriter lacks is a critic: something that hears the track, says where it goes flat and why, and hands over a change they can act on without a producer in the room.
How it works
Heard by a model, measured by tools, chosen by you
A track goes through a model reading and tool measurements. The listener chooses one change and takes the instruction to the tool they already use.
Explore an example route
Example route: a listener picks a change and hears it applied.
Arrow keys step through the route. Home returns to the full process. Follow keeps the current step in view.
-
Listener Step 1: Choose a track Track list
- Hands off
- Audio file to step 2, Read the audioAudio file to step 3, Measure the track
-
Model Step 2: Read the audio Audio-native model
Output is corrected against the lyric sheet and file length.
- Receives
- Audio file from step 1
- Hands off
- Model reading to step 4, Label each number
-
From step 1 · Audio file Tools Step 3: Measure the track Tempo and loudness
- Receives
- Audio file from step 1
- Hands off
- Measurements to step 4, Label each number
-
Also from step 2 · Model reading Fred Step 4: Label each number Measured, model, disputed
- Receives
- Model reading from step 2Measurements from step 3
- Hands off
- Labelled facts to step 5, Show the reading
-
SongLLM Step 5: Show the reading Waveform and notes
- Receives
- Labelled facts from step 4
- Hands off
- Three changes to step 6, Pick one change
-
Listener Step 6: Pick one change Heard, changes, stays
- Receives
- Three changes from step 5
- Hands off
- Applied change to step 7, Hear it appliedCopied instruction to step 8, Copy to a tool
-
Listener Step 7: Hear it applied A/B player
- Receives
- Applied change from step 6
- Ends here
- One possible ending of the process.
-
From step 6 · Copied instruction Listener Step 8: Copy to a tool Suno, ElevenLabs, DAW
- Receives
- Copied instruction from step 6
- Ends here
- One possible ending of the process.
- One example route. All alternatives stay visible.
- Dashed while playing: not on this route
Read the process and handoffs
- Choose a track
Listener · Track list.
- Audio file: Read the audio.
- Audio file: Measure the track.
- Read the audio
Model · Audio-native model. Output is corrected against the lyric sheet and file length.
- Model reading: Label each number.
- Measure the track
Tools · Tempo and loudness.
- Measurements: Label each number.
- Label each number
Fred · Measured, model, disputed.
- Labelled facts: Show the reading.
- Show the reading
SongLLM · Waveform and notes.
- Three changes: Pick one change.
- Pick one change
Listener · Heard, changes, stays.
- Applied change: Hear it applied.
- Copied instruction: Copy to a tool.
- Hear it applied
Listener · A/B player.
- Copy to a tool
Listener · Suno, ElevenLabs, DAW.
My part
I set the critic-not-editor frame, ran the model readings and the measurement scripts, wrote the corrections ledger, applied the audio change, and built and shipped the page.
In practice
Live and in a first round of tester feedback. The upload flow is scoped for now: the page explains what a live build would run instead of pretending to run it.
The readings come from a model and are labelled as such. Key detection is marked disputed where the tools disagree. Nothing on the page claims more than it can show.
Want to know more?
This one is public. The source stays private, but the product is live and you can try it. Get in touch if you would like to discuss how it was built.
Ask about this project