New Delhi, Nov. 12 -- AI research lab Chariot is addressing this problem with the launch of Chariot-1-TTS-Multilingual, a text-to-speech model designed to interpret written information before generating speech.

Launched on November 12, 2026, the model supports 11 Indian languages and English, offers more than 50 voices and allows users to combine two supported languages within the same sentence. It also supports voice cloning using a few seconds of reference audio and can process up to 1,000 characters in a single request.

For Chariot, however, the focus is not simply on producing speech in more languages. The company wants its models to understand how written expressions should be spoken in different situations.

Text-to-speech systems...