Skip to main content
Today the engine speaks Hindi, English, and the Hinglish most real calls actually are. Over the next two months it learns six more: Telugu, Tamil, Marathi, Kannada, Gujarati and Bengali. Roadmap: Hindi, Hinglish and English code-switch are live today; Bengali, Marathi, Telugu, Tamil, Gujarati and Kannada arrive over the next two months, dates to be announced per language. Per-language dates are announced as each one clears evaluation — the same rule as everything else on the roadmap: dates are targets, quality wins every time. A language does not ship because the calendar says so; it ships when it sounds like a person.

​
Why these six

Together these languages are the mother tongue of 429 million people — roughly every third Indian. And Hindi is not a substitute for most of them: the census records, for each language, how many of its speakers also speak Hindi, and for four of the six the answer is almost none. Bar chart of first-language speakers per language, with the portion that does not speak Hindi highlighted: Bengali 97.2M of whom 88.9M, Marathi 83.0M of whom 48.4M, Telugu 81.1M of whom 76.5M, Tamil 69.0M of whom 68.0M, Gujarati 55.5M of whom 33.8M, Kannada 43.7M of whom 41.7M. 357 million people cannot be called in Hindi at all. Only 1.5% of Tamil speakers report speaking Hindi; for Telugu it is 5.7%, Kannada 4.7%, Bengali 8.6%. A voice agent that speaks only Hindi does not reach these customers badly — it does not reach them. With Hindi and these six together, an agent can speak the mother tongue of about four in five Indians.
Speaker counts are first-language speakers from the 2011 Census of India; “also speak Hindi” is Hindi reported as a second language (table C-17). These are the most recent official figures — the next census is due in 2027.

​
What support means

  • Same endpoint, same request shape. The speech endpoint does not change — you send text in the language’s own script, code-switched with English the way real conversation is, and get audio back. No new API to learn.
  • Native voices, not accents. Each language ships with its own voices in the voice gallery, evaluated by native speakers — not a Hindi voice reading Tamil.
  • TTS ships first. This page tracks the voice. A full agent conversation in a language also needs our speech recognition and LLM to clear the same bar, and that follows the voice — the speech endpoint is where each language lands first.

​
Get early access

Each language runs an alpha with a small set of customers before it reaches the gallery. If calls in one of these languages matter to your business, tell your account contact which one — alpha slots are allocated in order of ask, and alpha customers’ text is what we tune the final voices on.