> 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

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

- [Quickstart](/quickstart) — Make your first request and save an audio file in a few minutes.



- [Authentication](/authentication) — Create an API key and learn how to send it.



- [Voices & languages](/concepts/voices-and-languages) — Browse the voices and languages Raaga 1 supports.



- [API Reference](/api-reference/speech) — Full endpoint, parameter, and schema details.

## Ways to generate speech

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

- [Full audio](/guides/http-generation) — One request, one complete audio file returned as base64 JSON.



- [HTTP streaming](/guides/http-streaming) — Stream audio bytes as they are generated over a single HTTP response.



- [Realtime WebSocket](/guides/realtime-websocket) — Sentence-by-sentence synthesis with binary audio chunks over a socket.

## Prefer an SDK?

Skip the raw HTTP calls with an official client:

- [Python SDK](/sdks/python) — `pip install vakyamai`



- [JavaScript / TypeScript SDK](/sdks/javascript) — `pnpm add @vakyam-ai/tts`

## Building a voice agent?

Drop Vakyam TTS into a realtime voice-agent framework:

- [LiveKit Agents](/integrations/livekit) — Add `vakyam.TTS` from `livekit-plugins-vakyam` to a pipeline.



- [Pipecat](/integrations/pipecat) — Add `VakyamTTSService` from `pipecat-vakyam` to a pipeline.

## 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** — monthly character allotments by [plan](/pricing),
  plus optional extra credits at ₹0.75 per 1,000 characters, counted by Unicode
  character (aksara), not by byte.
* **Plan-based limits** — Free, Developer, and Growth tiers set your monthly
  characters, requests per minute, and concurrency.

---

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