Skip to main content
Describe what you want in plain words and Reagent picks the tool. It has one set of tools for items in your REAPER project and another for audio files on disk.

​
What You Can Ask For

Reagent shows these tool names in the chat while it works. Extract waveform gives Reagent a coarse outline of a file’s amplitude (100 slices by default) so it can compare the shapes of sounds. It doesn’t draw a waveform in the chat. Items in your REAPER project
  • Select items, or name a track, the time selection or a region.
  • REAPER must be open with the Bridge running (a small script that connects Reagent to REAPER) and the SWS extension installed. See Quick Start.
  • Reagent measures the active take’s source file, for the length of the item.
  • Times are in project time.
  • Formats: WAV, MP3, FLAC, Ogg Vorbis, AIFF, and other formats Reagent can decode.
Audio files on disk
  • Type or paste the full path, such as /Users/you/SFX/door_slam_01.wav or D:\SFX\door_slam_01.wav. Don’t drag audio files into the chat box, because Reagent doesn’t attach them. Dragging in a folder gives Reagent its path. See Attaching Files.
  • REAPER can be closed.
  • Reagent measures the raw file.
  • Times are in seconds from the start of the file, or of the section you asked about.
  • Formats: WAV, MP3, FLAC and Ogg Vorbis. For AIFF, name a section to analyze, such as the first 10 seconds. To analyze a whole AIFF file, add it to a REAPER project and ask about the item.
  • The file tools also work on a Wwise project’s source files. See Audio Analysis on Wwise Source Files.
Analysis and metadata reads change nothing, so they run without asking. Marking peaks adds take markers, so Reagent asks first in Default permissions and Auto-review modes. See Permissions.
For items, loudness, silence and transient levels account for the item volume, the take volume and the average level of the take volume envelope, and muted items count as silent. They don’t include fades, track volume, or effects on the track or take.

​
Silence

  • Items: Reagent reports which items are effectively silent (99% or more of the item below -60 dB), not where the silence sits inside them.
  • Files: Reagent lists each silent stretch with its start and end time, plus the total. By default, silence means below -60 dB for at least 100 ms.
To find the gaps inside an item, ask Reagent to check the item’s source file, as in the second example below. It runs Analyze silence on that file, so times count from the start of the file (or of the section it reads) rather than project time, and levels ignore item and take volume. To cut silence out of items, see REAPER Tools. That tool is meant for sound effects and other non-speech audio, not dialogue. It shows as Remove item silence in the chat and Trim item silence on the approval card.

​
Transients and Peak Markers

Reagent reports the time and level of each hit, attack or other onset.
  • Items: By default, each item’s threshold sits about 20 dB below its average (RMS) level, and hits must be at least 50 ms apart.
  • Files: By default, hits must be at or above -40 dBFS and at least 600 ms apart. That gap skips fast repeats such as footsteps or a roll, so ask for a shorter one when hits come close together.
You can ask for other values, such as “ignore anything below -30 dB” or “hits can be as close as 20 ms apart”. Marking peaks adds take markers named “Peak”, which you can undo in REAPER. It shows as Mark peaks on item in the chat and Mark peaks on the approval card. Peak marking runs its own detection, separate from transient analysis. It splits each item into separate sounds at the quiet gaps between them, then marks each sound once: at the attack of a hit, or at the loudest point of a swell such as a whoosh. Sounds with a steady level get no marker. It doesn’t mark every transient, so to find every hit, ask for transients instead.

​
Loudness (RMS)

Reagent measures the average RMS level, in dB, of an item, a file or a section of a file. For several items, it lists them quietest first. RMS isn’t LUFS, the perceived-loudness measure used in delivery specs. To bring takes to a LUFS or peak dB target, use the take volume leveler in Volume Leveling.

​
Frequency Spectrum

For REAPER items only. Reagent splits each item’s energy into six bands. It reports each band’s energy relative to the loudest band, which band dominates, and whether the item is empty (no energy in any band).
  • Reagent analyzes a 16 kHz copy of the audio, so brilliance stops at 8 kHz and content above 8 kHz, such as air or hiss, isn’t measured.
  • Items shorter than about a quarter of a second always read as empty. For very short sounds, such as clicks or UI blips, ask for RMS instead.

​
UCS Classification

The Universal Category System (UCS) is a public standard for naming and sorting sound effects. Each category and subcategory pair has a short code called a CatID, such as VEHCar (Vehicles, Car). Classify items listens to items in your REAPER project and suggests CatIDs for them. On a Mac, classification needs Apple silicon and macOS 14 (Sonoma) or later. On an Intel Mac, or on macOS 12 or 13, Classify items fails, along with the UCS Renamer skill and the track content checks described below. Windows and the other tools on this page aren’t affected. See Troubleshooting.
  • Runs on your computer with a custom-trained model that ships with Reagent. Your audio isn’t uploaded.
  • REAPER items only. To classify files, add them to a REAPER project first.
  • Listens to up to 10 seconds of each item, trying to skip leading silence on longer items.
  • Suggests the top 5 CatIDs per item, each with a confidence score. You can ask for up to 20, or for confident ones only.
  • Also reads track content. Reagent uses classification to work out what kind of audio a track holds, such as dialogue, effects, ambience or music, instead of guessing from file names.
Suggestions stay in Reagent’s working memory for this chat and aren’t saved into your REAPER project. In the same chat, the UCS Renamer skill can give the items UCS take names. It renames takes, not files on disk. See Skills.
Classification returns lowercase codes, such as vehcar. Ask Reagent to look them up in the UCS list for the standard spelling (VEHCar), category and subcategory.The model knows 660 of the 753 CatIDs in the UCS list that ships with Reagent. If the right one isn’t suggested, describe the sound and ask Reagent to look it up with the UCS Category Lookup skill, which searches the full list.

​
Reading Metadata

Extract metadata reads WAV, MP3, FLAC, Ogg Vorbis and AIFF files. It returns technical details, such as duration, sample rate, bit depth, channels and codec, plus tags in these standards: For AIFF files, Reagent doesn’t read BWF or iXML fields.

​
Writing Metadata

Reagent can’t write metadata into audio files yet. If it offers to, the write fails with an error and your files stay as they were. To embed UCS or other tags, use a separate metadata editor.

​
Where the Analysis Runs

  • The analysis, classification and metadata tools on this page run on your computer and don’t upload your audio.
  • Reagent sends the results to the AI model as text, as part of your conversation. That includes levels, times, band values, waveform outlines, category suggestions, the metadata it reads, and file paths. On individual plans, that’s Reagent’s AI service.
  • On Enterprise accounts, the AI model is your organization’s endpoint.
  • Dialogue transcription works differently and uploads audio. See Dialogue.
For the full picture, see Privacy & Security.

REAPER Tools

Act on the results: remove silence, split, move and more.

Dialogue

Level takes to a LUFS or peak target.

Skills

UCS Category Lookup and UCS Renamer.

Wwise

Run the file tools on a Wwise project’s source files.