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

# Text-to-Speech Overview

> Generate natural speech in English and Indian languages with Plivo Text-to-Speech, in batch or realtime.

> [!NOTE]
>
> Plivo Text-to-Speech turns text into natural speech in English and seven Indian languages. Get a whole file over REST, or stream audio over a WebSocket for voice agents.

## What you can build

* **Voice agents**: stream your LLM's reply as audio with low time-to-first-audio.
* **IVR prompts and notifications**: generate prompts and alerts in the caller's language.
* **Telephony-ready audio**: get 8 kHz μ-law or A-law directly, with no transcoding.

## Batch and realtime

| Mode | How it works | Best for |
| - | - | - |
| **Batch** | `POST` text, get the whole audio file back. | Prompts, notifications, pre-generated audio |
| **Realtime** | Send text as it's generated, receive audio frames as they're ready. Up to 8 replies on one socket. | Voice agents and live calls |

## Features

| Feature | Batch | Realtime | Learn more |
| - | - | - | - |
| Telephony formats: μ-law and A-law 8 kHz | ✅ | ✅ | [Output formats](https://plivo.com/docs/models/text-to-speech/api/batch.md#output-format) |
| PCM 8 / 16 / 24 kHz, WAV, MP3 | ✅ | ✅ | [Output formats](https://plivo.com/docs/models/text-to-speech/api/batch.md#output-format) |
| Pace (0.7–1.2) and volume (0.5–2.0) | ✅ | ✅ | [Batch](https://plivo.com/docs/models/text-to-speech/api/batch.md) |
| Custom pronunciations and lexicons (IPA, ARPAbet, respelling) | ✅ | ✅ | [Pronunciation](https://plivo.com/docs/models/text-to-speech/concepts/pronunciation.md) |
| Repeatable output (`seed`, `continuation`) | ✅ | ✅ | [Batch](https://plivo.com/docs/models/text-to-speech/api/batch.md) |
| Multiple replies per socket, flush and cancel | — | ✅ | [Realtime](https://plivo.com/docs/models/text-to-speech/concepts/realtime.md) |
| Character timestamps | — | ✅ | [Realtime](https://plivo.com/docs/models/text-to-speech/api/realtime.md) |

## Languages

| Language | Code |
| - | - |
| English (US) | `en-US` |
| English (UK) | `en-GB` |
| English (India) | `en-IN` |
| English (Australia) | `en-AU` |
| Hindi | `hi` |
| Bengali | `bn` |
| Tamil | `ta` |
| Telugu | `te` |
| Marathi | `mr` |
| Gujarati | `gu` |
| Kannada | `kn` |

`language` defaults to `auto`. Each voice speaks one language: pick a voice for the language you need. See [Voices and languages](https://plivo.com/docs/models/text-to-speech/concepts/voices.md).

## Next steps

> [card] [Quickstart](https://plivo.com/docs/models/text-to-speech/quickstart.md)
>
> Generate your first audio file and stream speech.

> [card] [API reference](https://plivo.com/docs/models/text-to-speech/api/overview.md)
>
> Endpoints, parameters, messages and limits.
