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

# Intro to Realtime TTS

> Generate natural, expressive speech in real time.

Inworld's Realtime TTS models offer ultra-realistic, context-aware speech synthesis, zero data retention, and precise voice cloning capabilities, enabling developers to build natural and engaging experiences with human-like speech quality at an accessible price point.

Our models can be accessed via API ([streaming](/api-reference/ttsAPI/texttospeech/synthesize-speech-stream) and [non-streaming](/api-reference/ttsAPI/texttospeech/synthesize-speech)) or the [TTS Playground](http://platform.inworld.ai/tts-playground).

<CardGroup cols={3}>
  <Card title="Developer quickstart" icon="bolt" href="/quickstart-tts">
    Learn how to make your first API call with a guided tutorial.
  </Card>

  <Card title="TTS Playground" icon="play" href="/tts/tts-playground">
    Try different TTS models and voice cloning in TTS Playground.
  </Card>

  <Card title="Code Examples" icon="play" href="https://github.com/inworld-ai/inworld-api-examples/tree/main/tts">
    Browse ready-to-use GitHub samples for common use cases.
  </Card>
</CardGroup>

<Tip>
  **Using AI to code?** Paste `https://docs.inworld.ai/llms.txt` into your assistant so it knows every page on this site. Want live search? [Add the MCP server](https://docs.inworld.ai/tts/resources/vibe-coding).

  **Prefer the terminal?** `npm install -g @inworld/cli` — synthesize speech, clone and design voices, and generate audiobooks with the [Inworld CLI](/tts/resources/inworld-cli). AI agents can use it too.
</Tip>

## Models

<CardGroup cols={1}>
  <Card title="Realtime TTS-2" icon="wand-magic-sparkles">
    ### Our flagship, top-ranked model — the best choice for production

    * Best quality and steerability, with natural language steering for more contextually aware speech
    * Support for 200+ languages and locales
    * Ultra-low latency (100 ms TTFB<sup>\*</sup>) at high concurrency
    * High quality instant voice cloning
    * Enhanced timestamps with phonetic details and visemes
  </Card>

  <Card title="Realtime TTS-2 Flash" icon="bolt">
    ### Our fastest, most cost-efficient model — built for latency-critical, high-volume workloads

    * Our lowest latency — 20 ms TTFB<sup>\*</sup>, 5× faster than `inworld-tts-2`
    * Lowest cost per character
    * Same 200+ languages and locales as `inworld-tts-2`
    * High quality instant voice cloning
  </Card>
</CardGroup>

<sup>\*</sup> P90 time to first audio byte, measured server-side — excludes network latency.

See the [Models](/tts/tts-models) page for model IDs and full details.

## Features

| **Feature**                                                                                                                       | **Realtime TTS-2**                                               | **Realtime TTS-2 Flash**                                    |
| :-------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------- | :---------------------------------------------------------- |
| Best for                                                                                                                          | Production workloads that need the best quality and steerability | Latency-critical, high-volume, and cost-sensitive workloads |
| Quality                                                                                                                           | Top-ranked flagship — best quality and steerability              | High quality at the lowest latency and cost                 |
| Latency (TTFB) <sup>\*</sup>                                                                                                      | 100 ms                                                           | 20 ms                                                       |
| [Instant voice cloning](/tts/instant-voice-cloning)                                                                               | <Icon icon="check" size={18} />                                  | <Icon icon="check" size={18} />                             |
| [Professional voice cloning](/tts/professional-voice-cloning) <span className="research-preview-pill">Beta</span>                 | <Icon icon="check" size={18} />                                  | <Icon icon="dash" size={18} />                              |
| [Custom pronunciation](/tts/capabilities/custom-pronunciation)                                                                    | <Icon icon="check" size={18} />                                  | <Icon icon="check" size={18} />                             |
| [Multilingual](/tts/capabilities/multilingual)                                                                                    | 200+ languages                                                   | 200+ languages                                              |
| [Steering](/tts/capabilities/steering)                                                                                            | <Icon icon="check" size={18} />                                  | <Icon icon="dash" size={18} />                              |
| [Pause controls](/tts/capabilities/pause-controls)                                                                                | <Icon icon="check" size={18} />                                  | <Icon icon="check" size={18} />                             |
| [Timestamp alignment](/tts/capabilities/timestamps)                                                                               | <Icon icon="check" size={18} />                                  | <Icon icon="check" size={18} />                             |
| [On-premises deployments](/tts/on-premises)                                                                                       | <Icon icon="check" size={18} />                                  | <Icon icon="check" size={18} />                             |
| [Zero data retention](/portal/zero-data-retention#tts)                                                                            | <Icon icon="check" size={18} />                                  | <Icon icon="check" size={18} />                             |

<sup>\*</sup> P90 time to first audio byte, measured server-side — excludes network latency.