***

title: Overview
description: >-
Convert text to natural-sounding speech with the Waves TTS API - ultra-low
latency synthesis with voice cloning and streaming support
icon: waveform-lines
--------------------

The Waves Text-to-Speech (TTS) API converts text into natural, expressive audio via `https://waves-api.smallest.ai/api/v1`. With low latencies and support for 16+ languages, it's built for real-time applications like voice assistants, interactive bots, and live content generation.

<Card title="Quickstart" icon="rocket" href="/waves/documentation/text-to-speech/quickstart">
  Get started in minutes. Learn how to get your API key and generate your first audio.
</Card>

## Synthesis Modes

Choose the synthesis mode that best fits your application's needs:

<CardGroup cols={2}>
  <Card title="Synchronous" icon="file-audio" href="/waves/documentation/text-to-speech/how-to-tts">
    Generate complete audio files with a single HTTP request. Ideal for pre-rendering content, batch processing, and applications where immediate streaming isn't required.
  </Card>

  <Card title="Streaming" icon="broadcast-tower" href="/waves/documentation/text-to-speech/stream-tts">
    Receive audio chunks as they're generated via WebSocket. Perfect for real-time voice assistants, live narration, and low-latency conversational AI.
  </Card>
</CardGroup>

## Available Models

<CardGroup cols={2}>
  <Card title="Lightning v2" icon="bolt">
    High-quality multilingual TTS with 100ms TTFB. Supports 16+ languages including English, Hindi, and European languages. Includes voice cloning support.
  </Card>

  <Card title="Lightning v3.1" icon="sparkles">
    Our most natural-sounding model with 44 kHz audio output. Ultra-low latency with expressive, human-like speech. Supports English, Hindi, Tamil, and Spanish with voice cloning.
  </Card>
</CardGroup>

## Feature Highlights

<AccordionGroup>
  <Accordion title="Ultra-Low Latency">
    Optimized streaming pipeline delivers sub-100ms time-to-first-byte (TTFB) for real-time applications. Lightning v3.1 achieves even faster response times for conversational AI.
  </Accordion>

  <Accordion title="Voice Cloning">
    Create custom voice profiles by uploading audio samples. Instant voice cloning works with just a few seconds of audio, while professional voice cloning delivers studio-quality results.
  </Accordion>

  <Accordion title="16+ Languages">
    Comprehensive language support including English, Hindi, Tamil, Kannada, Malayalam, Telugu, Gujarati, Bengali, Marathi, German, French, Spanish, Italian, Polish, Dutch, and Russian.
  </Accordion>

  <Accordion title="Multiple Output Formats">
    Choose from PCM, WAV, MP3, or μ-law encoding. Configurable sample rates from 8kHz to 44kHz to match your application's requirements.
  </Accordion>

  <Accordion title="Speed Control">
    Adjust speech rate with a simple multiplier. Slow down for clarity or speed up for faster content delivery without pitch distortion.
  </Accordion>

  <Accordion title="Pronunciation Dictionaries">
    Define custom pronunciations for brand names, technical terms, and acronyms. Ensure consistent, accurate pronunciation across all synthesized audio.
  </Accordion>

  <Accordion title="High-Quality Audio">
    Lightning v3.1 produces 44 kHz audio with natural prosody and expressiveness. Perfect for audiobooks, podcasts, and premium voice experiences.
  </Accordion>

  <Accordion title="WebSocket Streaming">
    Persistent connections for continuous audio streaming. Ideal for voice bots and interactive applications where latency is critical.
  </Accordion>
</AccordionGroup>

## Supported Languages

<table>
  <thead>
    <tr>
      <th>
        Language
      </th>

      <th>
        Code
      </th>

      <th>
        Lightning v2
      </th>

      <th>
        Lightning v3.1
      </th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td>
        English
      </td>

      <td>
        <code>en</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        Yes
      </td>
    </tr>

    <tr>
      <td>
        Hindi
      </td>

      <td>
        <code>hi</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        Yes
      </td>
    </tr>

    <tr>
      <td>
        Tamil
      </td>

      <td>
        <code>ta</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        Yes
      </td>
    </tr>

    <tr>
      <td>
        Kannada
      </td>

      <td>
        <code>kn</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        —
      </td>
    </tr>

    <tr>
      <td>
        Malayalam
      </td>

      <td>
        <code>ml</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        —
      </td>
    </tr>

    <tr>
      <td>
        Telugu
      </td>

      <td>
        <code>te</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        —
      </td>
    </tr>

    <tr>
      <td>
        Gujarati
      </td>

      <td>
        <code>gu</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        —
      </td>
    </tr>

    <tr>
      <td>
        Bengali
      </td>

      <td>
        <code>bn</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        —
      </td>
    </tr>

    <tr>
      <td>
        Marathi
      </td>

      <td>
        <code>mr</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        —
      </td>
    </tr>

    <tr>
      <td>
        German
      </td>

      <td>
        <code>de</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        —
      </td>
    </tr>

    <tr>
      <td>
        French
      </td>

      <td>
        <code>fr</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        —
      </td>
    </tr>

    <tr>
      <td>
        Spanish
      </td>

      <td>
        <code>es</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        Yes
      </td>
    </tr>

    <tr>
      <td>
        Italian
      </td>

      <td>
        <code>it</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        —
      </td>
    </tr>

    <tr>
      <td>
        Polish
      </td>

      <td>
        <code>pl</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        —
      </td>
    </tr>

    <tr>
      <td>
        Dutch
      </td>

      <td>
        <code>nl</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        —
      </td>
    </tr>

    <tr>
      <td>
        Russian
      </td>

      <td>
        <code>ru</code>
      </td>

      <td>
        Yes
      </td>

      <td>
        —
      </td>
    </tr>
  </tbody>
</table>

## Next Steps

* Generate your first audio in the [TTS Quickstart](/waves/documentation/text-to-speech/quickstart)
* Learn synchronous and async synthesis in [How to use TTS](/waves/documentation/text-to-speech/how-to-tts)
* Set up real-time streaming with [WebSocket TTS](/waves/documentation/text-to-speech/stream-tts)
* Clone a voice with our [Voice Cloning guide](/waves/documentation/voice-cloning/how-to-voice-clone)
* Add custom pronunciations with [Pronunciation Dictionaries](/waves/documentation/text-to-speech/pronunciation-dictionaries)