Qurani.ai
One Clean API for Quranic Text, Audio and Translation
AI for Islamic Knowledge
Islamic knowledge,
at the scholarly source
AI that understands text, context and trust.
What it does
What it gives a builder and a researcher
Quranic text, audio and translation for builders; sourced research for scholars.
Quranic text, audio and translation in one interface
360+ Quran editions and 270 text versions with Uthmanic script and layout matching printed Masahif.
Recitation audio with word-level synchronisation
354,000+ audio files across 34 reciters covering the major Riwayat, with word-level sync for highlighted playback.
Real-time recitation correction
The QRC API, powered by Nabr, catches Tajweed errors at the phoneme level, live as the user recites.
A research agent that does the research
Tbyaan drafts from classical sources, searching the Quran, Hadith and Tafseer together instead of four times over.
Operational outcomes
Operational outcomes
What changes once the corpus is the model's own ground.
Infrastructure stops being the project
Fragmented data and outdated APIs become someone else's problem, work goes into the part that's yours.
Research time goes to analysis
Cross-referencing classical sources by hand is the part that gets removed. The scholarship is not.
Recitation feedback without training a model
A Tajweed-aware correction feature ships without building an acoustic model from scratch first.
Products
Powered by Misraj products
Qurani.ai is one clean API for Quranic text, audio and translation; Tbyaan is Islamic scholarship research, sourced and cited. Both are built on the same Kawn models.
Explore all products
Built on Kawn models
Tbyaan
Islamic Scholarship Research, Sourced and Cited
How it deploys
Through the Qurani.ai API, as an MCP server inside your own agents, or on-premises for an institution that keeps its corpus in.
- Qurani.ai API
- MCP server
- On-premises
Qurani.ai API
The developer interface for Quranic data, semantic search and recitation correction.
MCP server
Connect directly to AI coding environments and describe what you want to build in plain language.
On-premises
The underlying models deploy inside your own environment where an institution requires it.
Proof from across the sectors
Proof from across the sectors
“Manual review effort was reduced as extraction moved from manual re-keying to automated structured output.”
A national statistics authority · Customer case study
Read the case studyWhy this needs its own models
Qurani.ai pulls together Quranic text, audio and translation into one API, with semantic search that outperforms Gemini, Voyage and Cohere on Islamic retrieval at 0.83 average. Tbyaan turns a jurisprudential or historical question into a sourced, structured draft. Our speech research also produced Nabr - a Quranic recitation model analysing 8 acoustic properties per sound at 0.59% character error rate - the strongest evidence we build speech models at the phoneme level rather than fine-tuning someone else's.
- 0.83
- Islamic retrieval average score
- 0.59%
- Character error rate, live in Eqraa app
- 354,000+
- Recitation audio files across 34 reciters
An embedding model trained on the corpus
Kawn-Embed-Islamic trains on Islamic Q&A, Tafseer and Hadith, so retrieval captures context, not just keywords.
Tajweed is an acoustic problem, not a text one
Nabr analyses eight acoustic properties per sound, elongation, nasal resonance and pronunciation, things generic voice models miss.
Sourced output, not authoritative-sounding output
Tbyaan maps every piece of generated text back to its source, so a draft holds up to scholarly scrutiny rather than merely reading as though it would.
Get started
Deploy AI for Islamic Knowledge
Tell us the problem. We will tell you honestly whether this is the right answer, and what it takes to deploy.