> ## Documentation Index
> Fetch the complete documentation index at: https://docs.chariot.in/llms.txt
> Use this file to discover all available pages before exploring further.

# Welcome to Chariot

> Natural-sounding text-to-speech for English and Indian languages, over REST, HTTP streaming, or WebSocket.

Chariot is a text-to-speech (TTS) platform built for English and Indian voices. Send text, get lifelike speech through a simple REST call, a low-latency HTTP stream, or a real-time WebSocket. Speech-to-text (ASR) is coming soon.

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/guides/quickstart">
    Make your first speech request in a few minutes.
  </Card>

  <Card title="Choose your API" icon="signs-post" href="/guides/text-to-speech/which-api">
    REST vs. HTTP streaming vs. WebSocket, pick the right transport.
  </Card>

  <Card title="Voices" icon="microphone-lines" href="/guides/text-to-speech/voices">
    Browse the stock voice catalog.
  </Card>

  <Card title="API reference" icon="code" href="/api-reference/introduction">
    Every endpoint, parameter, and response.
  </Card>
</CardGroup>

## What you can build

* **Voiceovers and narration**, turn scripts and articles into audio.
* **Conversational agents**, stream speech into IVR, support bots, and voice assistants with low latency.
* **Accessibility**, read content aloud in English and Indian languages.

## How it works

<Steps>
  <Step title="Get an API key">
    Create a key in the [dashboard](https://chariot.in) and send it in the `chariotai-api-key` header. See [Authentication](/guides/authentication).
  </Step>

  <Step title="Pick a voice">
    List the [voice catalog](/guides/text-to-speech/voices) and copy a `voice_id`.
  </Step>

  <Step title="Synthesize">
    Call [`POST /v1/tts`](/api-reference/endpoint/text-to-speech) for a complete file, or stream for low latency.
  </Step>

  <Step title="Track usage">
    Each response reports the credits charged; check your balance any time with [`GET /v1/credits`](/api-reference/endpoint/user-credits).
  </Step>
</Steps>

## Core concepts

| Concept         | Summary                                                                                                                   |
| --------------- | ------------------------------------------------------------------------------------------------------------------------- |
| **Credits**     | Usage is metered in credits. TTS costs 1 credit per input character. See [Credits & pricing](/guides/resources/credits).  |
| **Concurrency** | Each plan allows a fixed number of simultaneous requests. See [Rate limits & concurrency](/guides/resources/rate-limits). |
| **Voices**      | Ready-to-use voices across English and Indian languages and accents.                                                      |
| **Models**      | `v0` is the current TTS model. See [Models](/guides/models).                                                              |