About Veena

Veena is a speech to text application built for India's languages. It turns spoken words into written text in all 22 scheduled languages of the Indian Constitution — from Telugu, Hindi, Tamil, Bengali and Marathi to Bodo, Santali, Konkani and Sanskrit.

Speech recognition for Indian languages has historically meant sending your voice to a cloud server. That is a poor fit for sensitive conversations, for people with unreliable internet, and for languages that big cloud providers ignore. Veena takes the opposite approach: everything runs on your own device.

Tap the microphone, speak in your language, and Veena converts your words into editable text you can copy or share. The app downloads a speech model once during setup; after that it works completely offline.

Built Telugu first, open to all 22 languages

Veena started as a Telugu speech to text app — that is still how the mobile stores describe it. Telugu gets its own dedicated recognition model, tuned for the language. Every other scheduled language is covered by one multilingual model, built on IndicConformer from AI4Bharat, where each language decodes through its own vocabulary so a sentence in Kannada does not drift into Marathi.

Private by design

No account. No cloud transcription. No telemetry. Your recordings and transcripts are stored locally and never uploaded anywhere. The mobile apps ask for microphone permission, plus network access for that first model download, and nothing else. The full story is on the privacy page.

On the devices you own

Veena is available today for Android and iPhone, and as a Windows desktop app that types into whatever you are working in. Desktop builds for macOS and Linux are in development. Whatever the device, your speech stays on it.

Made by an independent developer

Veena is developed by Nikhil Reddy Avuthu. It is a small, independent project — feedback, feature requests, and bug reports are welcome at anr.appcontact@gmail.com.