Explore how Cyanite turns sound into structured metadata: Just upload a couple of songs to our web app.

Managing a music catalog involves more than just storing files. As catalogs grow, teams start running into a different kind of challenge: music becomes harder to find, metadata becomes inconsistent, and strong tracks remain invisible simply because they are described differently than newer material.

Many teams still rely on manual tagging or have inherited metadata systems that were never designed for scale. Over time, this leads to uneven descriptions, slower search, and workflows that depend more on individual knowledge than on shared systems. Creative teams spend valuable time navigating the catalog instead of working with the music itself.

Cyanite’s end-to-end tagging workflow was built to address this challenge. It gives teams a stable, shared foundation they can build on, supporting human judgement—not replacing it. It complements subjective, manual labeling with a consistent, audio-based process that works the same way for every track, whether you’re onboarding new releases or making a legacy catalog more organized.

This article walks through how that workflow functions in practice—from the moment audio enters the system to the point where structured metadata becomes usable across teams and tools.

Why tagging workflows tend to break down as catalogs grow

Most tagging workflows start with care and intention. A small team listens closely, applies descriptive terms, and builds a shared understanding of the catalog. But as volume increases and more people get involved, the system begins to stretch.

As catalogs scale, the same patterns tend to appear across organizations:

• Different editors describe the same sound in different ways.
• Older metadata no longer aligns with newer releases.
• Genre and mood definitions shift over time.
• Search results reflect wording more than sound.

When this happens, teams increasingly rely on memory instead of the systems in place. This leads to strong tracks getting overlooked, response times increasing, and trust in the metadata eroding.

Cyanite’s workflow addresses this fragility by grounding metadata in the audio itself and applying the same logic across the entire catalog.

Preparing your catalog for audio-based tagging

Teams can adopt Cyanite very quickly, as there’s very little preparation involved. The system doesn’t require existing metadata, spreadsheets, or reference information. It listens to the audio file and derives all tags from the sound alone.

Getting started requires very little setup:

• MP3 files up to 15 minutes in length
• No pre-existing metadata
• No manual pre-labeling
• No changes to your current file structure

Even 128 kbit/s MP3s are usually sufficient, which means older archive files can be analyzed as they are—no need for additional audio preparation. Teams can then choose how they want to bring audio into Cyanite based on volume and workflow. Once that’s decided, tagging can begin immediately.

If you’re unsure about uploading copyrighted audio to Cyanite, you can explore our security standards and privacy-first workflows, including options to process audio in a copyright-safe way using encrypted or abstracted data.

Bringing audio into Cyanite in a way that fits your workflow

Different organizations manage music in different ways, so Cyanite supports several ingestion paths that all lead to the same analysis results.

Teams working with smaller batches often start in the web app. This is common for sync teams reviewing submissions, catalog managers auditing older libraries, or teams testing Cyanite before deeper integration. Audio can be uploaded directly, selected from disk, or referenced via a YouTube link, with analysis starting automatically once the file is added.

Platforms and larger catalogs usually integrate via the API. In this setup, tagging runs inside the organization’s own systems. Audio is uploaded programmatically, and results are delivered automatically via webhook as structured JSON as soon as processing is complete. This approach supports continuous ingestion without manual steps and fits naturally into existing pipelines.

For very large catalogs, Cyanite can also provide a dedicated S3 bucket with CLI credentials. This allows high-throughput ingestion without relying on browser-based uploads. It’s often used during initial onboarding of catalogs containing thousands of tracks.

Some teams prefer not to upload files themselves at all. In those cases, audio can be shared via common transfer tools before the material is processed and delivered in the agreed format.

What happens once the analysis is complete?

Cyanite produces a structured, consistent description of how each track sounds, independent of who uploaded it or when it entered the catalog.

Metadata becomes available either in the web app library or directly inside your system via the API. We can also deliver an additional CSV and Google Spreadsheet export on request.

Each track receives a stable set of static tags and values, including:

• Genres and free-genre descriptors
• Moods and emotional dynamics
• Energy and movement
• Instrumentation and instrument presence
• Valence–arousal values
• The most representative part of the track
• An Auto-Description summarizing key characteristics

All tags are generated through audio-only analysis, which ensures that legacy tracks and new releases follow the same logic. Over time, this consistency becomes the foundation for faster search, clearer filtering, and more reliable collaboration across teams.

The full tagging taxonomy is available for teams that want deeper insight into how attributes are defined and structured. Explore Cyanite’s tagging taxonomy here.

Curious how the Google Spreadsheet export looks? Check out this sample.

How long tagging takes at different catalog sizes?

Cyanite processes audio quickly. A typical analysis time is around 10 seconds per track. Because processing runs in parallel, turnaround time depends more on workflow setup than on catalog size.

In practice, teams can expect:

• Small batches to be ready almost instantly
• Medium-sized libraries to complete within hours
• Enterprise-scale catalogs to be onboarded within 5–10 business days, regardless of size

For day-to-day use via the API, results arrive in near real time via webhook as soon as processing finishes. This makes the workflow suitable both for large one-time onboarding projects and continuous ingestion as new music arrives.

Understanding scores, tags, and why both matter

Cyanite’s models produce two complementary layers of information.

Numerical scores describe how strongly an attribute is present, both across the full track and within time-based segments. These values range from zero to one, with 0.5 representing a meaningful threshold.

Cyanite creates final tags by using an additional decision layer that considers how different attributes relate to one another. It doesn’t just apply a simple cutoff. This approach helps resolve ambiguities, stabilize hybrid sounds, and produce tags that make musical sense in context.

This means you get metadata that remains robust even for tracks that blend genres, moods, or production styles—a common challenge in modern catalogs.

Exporting metadata into your existing systems

Once tags are available, your team can export them in the format that best fits your workflow.

API users typically work with structured JSON, delivered automatically via webhook and accessible through authenticated requests. Cyanite’s Query Builder allows teams to explore available fields and preview real outputs before integration.

For one-time projects or larger deliveries, metadata can also be provided as CSV files. Web app users can request CSV export through Cyanite’s internal tools, which is especially useful during catalog cleanups or migrations.

Because the structure remains consistent across formats, metadata can be reused across systems without rework.

Learn how to quickly build your queries for the Cyanite API with our Query Builder.

How teams use tagged metadata in practice

Once audio-based tagging is in place, teams tend to notice changes quickly. Search becomes faster and more predictable. Creative teams can filter by sound instead of guessing keywords. Catalog managers spend less time fixing metadata and more time shaping the catalog strategically.

In practice, tagged metadata supports workflows such as:

• Catalog management and cleanup
• Creative search and curation
• Ingestion pipelines
• Licensing and rights
• Sync briefs and pitching
• Internal discovery tools
• Audits and reporting

Over time, consistent metadata reduces friction between departments and makes catalog operations more resilient as libraries continue to grow.

Best practices from real-world usage

Teams see the smoothest results when they work with clean audio sources, batch large uploads, manage API credentials carefully, and switch to S3-based ingestion as catalogs become larger. Thinking about export formats early also helps avoid rework during onboarding projects.

None of this changes the outcome of the analysis itself, but it does make the overall process more predictable and easier to manage at scale.

Final thoughts

Cyanite’s tagging workflow is designed to scale with your catalog without making your day-to-day work more complex. Whether you upload a handful of tracks through the web app or process tens of thousands via the API, the result will be the same: structured, consistent metadata that reflects how your music actually sounds.

If you’re ready to move away from manual tagging and toward a more stable foundation for search and discovery, explore the different ways to work with Cyanite and choose the setup that fits your workflow.

Want to work with Cyanite? Explore your options, and get in touch with our business team, who can provide guidance if you’re unsure how to start.

A new industry report from Cyanite, MediaTracks, and Marmoset reveals how professionals are navigating the rise of AI-generated music. Read here.

AI’s move to the mainstream has changed what people expect from music catalogs. Licensing teams now look for clearer data about the music they review. They want to know whether it’s human-made or AI-generated, and they also look for details that help place the music in the right creative or cultural setting. Many check these cues first, then move on to mood or tone.

At Cyanite, we partnered with MediaTracks and Marmoset to understand the level of transparency and cultural context music licensing professionals expect when reviewing AI-generated music. MediaTracks and Marmoset surveyed 144 people across their professional communities—including music supervisors, filmmakers, advertisers, and producers—and we worked with them to interpret the findings and publish this report.

The responses revealed that most people want clear labeling when AI is involved. Yet, despite this shared desire for transparency, only about half of the respondents said they would only work with human-made music.

The full study goes deeper into these findings and shows how they play out in real licensing work.

Why we ran this study

We wanted a clear view of how people make decisions when AI enters the picture. The conversation around AI in music moves fast, and many teams now ask for context that helps them explain their selections to clients. This study aimed to find out which parts of the metadata give them that confidence.

It also looked at how origin details and creator context guide searches and reviews. We wanted to see where metadata supports the day-to-day licensing process and where there are gaps.

Transparency is now a baseline expectation

97% of respondents said they want AI-generated music to be clearly labeled, and 37% used the word “transparency” in their written responses. They want a straightforward read on what they’re listening to. Some tied this to copyright worries. One person put it simply: 

“I’m concerned that if it were AI-generated, where did the AI take the themes or phrases from? Possible copyright infringement issues.”

Transparency doesn’t just apply to the AI label. We found that respondents also see context as part of that clarity—knowing who made the music and where it comes from. This information helps them assess whether the music is a good fit for the project. They use it during searches to filter for cultural background or anything else that’s relevant to the brief.

What these findings mean for the industry

These findings show how much clarity now shapes day-to-day work in music catalogs. People expect AI music to be labeled accordingly, and they lean on context to move through searches and briefs without second-guessing their choices. Human-made music is still highly valued. The real change has been in how teams use origin details to feel sure about their selection.

This sets a new bar for how catalogs present their music. Teams want dependable information, including context that helps them avoid missteps in projects that depend on cultural accuracy or narrative alignment.

This finding ties into how Cyanite supports catalogs today. Our audio-first analysis gives people a clear read of the music itself, which sits alongside the cultural or creative context they already rely on. It helps teams search with more clarity and meet the expectations that are now shaping the industry.

How Cyanite’s advanced search fits in

The study showed how important cultural background and creator context are when people review music. Teams often keep their own notes and metadata for this reason. Cyanite’s Advanced Search supports that need by letting catalogs add and use their own custom information in the search.

Custom Metadata Upload – one of many features of our new Advanced Search, lets you upload your own tags – such as cultural or contextual details that don’t come from the audio analysis – and use them as filters. You can set your own metadata criteria first, and the system will search only within the tracks that match those inputs.

When you then run a Similarity- or Free Text Search, the model evaluates musical similarity inside that filtered subset. As a result, search and discovery reflects both the sound of a track and the context around it.

You can search your catalog for “upbeat indie rock” but you can also search for “upbeat indie rock, human-produced, female-led, one-stop cleared, independent.“

Read the full report

The survey drew responses from people who license music often as part of their work and feel the impact of unclear metadata. Their answers show how they think about AI involvement, creator background, and the context they need when they search.

The full report brings these findings together with information about the study—who took part, how often they search, the questions they answered, and how responses differed by role. It also includes partner insights from MediaTracks and Marmoset, along with charts and quotes that show how transparency and context shape real choices in licensing.

You can read the full study here.