We start where our speaker network is strongest, in southern Punjab, and expand only when we have verified speakers and native reviewers for a language.
We show what is ready today separately from what is planned.
| Language | Status | Scripts | Varieties we target | Typical conditions |
|---|---|---|---|---|
| Saraiki | Launch | Shahmukhi, Latin | Multani, Derawi, Riasti, Thali | Rural homes, markets, phone |
| Urdu + English code-switch | Launch | Nastaliq, Latin (Roman Urdu) | Pakistani urban and regional accents | Offices, phone, contact-centre |
| Pakistani Punjabi | Launch | Shahmukhi, Latin | Majhi, Jhangvi | Homes, markets, phone |
| Sindhi | Next | Perso-Arabic Sindhi | Vicholi, Siroli | Towns, homes |
| Pashto | Next | Pashto script | Yusufzai, Kandahari | Urban, bazaar |
| Balochi | Planned | Balochi script | Rakhshani, Makrani | Urban, highland |
Select a district. A district is marked live only after recordings are verified.
"Assaan ghar wanjna ae": "We have to go home" in Saraiki. Tens of millions speak it, yet written Saraiki barely exists online, so models trained on Urdu text turn it into Urdu.
At launch every dataset is collected to order. Validated off-the-shelf sets will be listed here once they pass QA.
Pilots and projects in Saraiki, Pakistani Punjabi and Urdu.
Licensable sets with data cards, once verified.
Tell us a language or district; we tell you honestly if we can do it.
Ask for a coverage assessment. We will tell you what is realistic, and when.