> Agent-readable docs index: /llms.txt. Download /docs.zip to grep all markdown files locally.

---
title: Welcome
description: Text-to-speech for Indian languages, powered by Raaga 1.
---

# Welcome to Vakyam AI

<Aside>
  <TableOfContentsPanel />
</Aside>

Vakyam AI is a developer platform for natural, human-sounding speech in Indian
languages. Our text-to-speech model, **Raaga 1**, turns text in English, Hindi,
Tamil, Telugu, Kannada, Marathi, Gujarati, and Bengali into lifelike audio
through a simple HTTP and WebSocket API.

These docs will take you from your first API call to streaming real-time audio
in production.

## New here? Start with these

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Make your first request and save an audio file in a few minutes.
  </Card>

  <Card title="Authentication" icon="key" href="/authentication">
    Create an API key and learn how to send it.
  </Card>

  <Card title="Voices & languages" icon="microphone" href="/concepts/voices-and-languages">
    Browse the voices and languages Raaga 1 supports.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/speech">
    Full endpoint, parameter, and schema details.
  </Card>
</CardGroup>

## Ways to generate speech

Pick the approach that fits your product's latency and integration needs:

<CardGroup cols={3}>
  <Card title="Full audio" icon="file-audio" href="/api-reference/speech">
    One request, one complete audio file returned as base64 JSON.
  </Card>

  <Card title="HTTP streaming" icon="wave-square" href="/guides/http-streaming">
    Stream audio bytes as they are generated over a single HTTP response.
  </Card>

  <Card title="Realtime WebSocket" icon="bolt" href="/guides/realtime-websocket">
    Sentence-by-sentence synthesis with binary audio chunks over a socket.
  </Card>
</CardGroup>

## Prefer an SDK?

Skip the raw HTTP calls with an official client:

<CardGroup cols={2}>
  <Card title="Python SDK" icon="python" href="/sdks/python">
    `pip install vakyamai`
  </Card>

  <Card title="JavaScript / TypeScript SDK" icon="js" href="/sdks/javascript">
    `pnpm add @vakyam-ai/tts`
  </Card>
</CardGroup>

## Good to know

* **Eight Indian languages** — `en-IN`, `hi-IN`, `ta-IN`, `te-IN`, `kn-IN`,
  `mr-IN`, `gu-IN`, `bn-IN`.
* **Multiple voices per language** — the same person can speak across languages.
* **Flexible output** — `mp3`, `wav`, raw `pcm`, or `mulaw`, at sample rates from
  8 kHz to 48 kHz.
* **Fair credit counting** — billed by Unicode character, not by byte, so Indian
  scripts are counted by aksara.


---

*Powered by [holocron.so](https://holocron.so)*