Anghami, a leading music and entertainment streaming platform in the MENA region, has partnered with Cyanite to enrich 2.5 million songs using AI-generated music metadata.
By integrating Cyanite’s auto-tagging API, Anghami has enhanced its catalogue with detailed audio-based metadata across mood, genre, energy, instrumentation, and more. This structured data layer feeds directly into Anghami’s internal recommendation systems, enabling more precise and scalable music discovery.
Bringing more than 120 million registered users a catalogue scale of millions of tracks, metadata quality allows enhanced personalisation. Structured and consistent tagging enables streaming platforms to better match songs with listeners, surface long-tail content, and improve personalisation across diverse repertoires.
For Anghami, the partnership also underscores its commitment to accurately representing the richness of Arabic music.
“Arabic music carries immense depth, emotion and cultural nuance,” said Elias El Khoury, VP Information & Content Systems at Anghami.
“Through our partnership with Cyanite, we’re ensuring that this richness is understood at a data level, allowing us to power more accurate personalisation and elevate discovery for millions of listeners,” he added.
A significant share of Anghami’s catalogue consists of regional content that is often underrepresented in Western-centric AI systems. Because Cyanite analyses audio directly, rather than relying on behavioural signals or language-based metadata, its models operate consistently across musical cultures and languages.
“Anghami operates one of the most culturally diverse music catalogues in the world,” said Markus Schwarzer, CEO at Cyanite. “Ensuring that Arabic repertoire is tagged with the same precision as Western music is not trivial. We’re proud that our audio-based AI can support music discovery at this scale and across such a rich regional landscape.”
The scalable metadata infrastructure aims to power personalisation and discovery using Cyanite’s AI-powered auto-tagging.
