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

# Convert Text to Natural Speech with AI

> Turn written text into natural speech audio with Artnex VoiceZen. Choose from 20+ AI voices across multiple languages and download the result instantly.

Text-to-Speech converts your written content into natural-sounding audio in seconds. Powered by ElevenLabs and Kling TTS, you can generate voiceovers for videos, podcasts, accessibility content, and more — without recording equipment or a voice actor.

## Navigate to Text to Speech

Go to **Tools > Audio > VoiceZen > Text to Speech**.

## Generate speech

<Steps>
  <Step title="Enter your text">
    Type or paste the text you want to convert into the input field. You can also click the **Sparkles** icon to automatically enhance your text, or the **Pencil** icon to open the full prompt editor.
  </Step>

  <Step title="Choose a model">
    Select your TTS engine from the model dropdown:

    * **ElevenLabs** — 20 voices across American, British, and Australian accents. Supports 28 languages. Best for natural-sounding, expressive speech.
    * **Kling TTS** — 30+ voices with Chinese, British, and American accents. Best for multilingual and regional character voices.

    <Note>Switching models resets your voice selection to the first available voice in that model's library.</Note>
  </Step>

  <Step title="Select a voice">
    Click the **voice button** (showing the current voice name) to open the Voice Selector. Browse voices by gender and accent, then click one to select it.

    **ElevenLabs voices include:**

    | Voice     | Gender     | Accent     |
    | --------- | ---------- | ---------- |
    | Aria      | Female     | American   |
    | Sarah     | Female     | American   |
    | Charlotte | Female     | British    |
    | Alice     | Female     | British    |
    | Lily      | Female     | British    |
    | Roger     | Male       | American   |
    | George    | Male       | British    |
    | Daniel    | Male       | British    |
    | Charlie   | Male       | Australian |
    | River     | Non-binary | American   |

    *And 10+ more voices available in the selector.*
  </Step>

  <Step title="Choose a language (ElevenLabs only)">
    When using the ElevenLabs model, select your target language from the language dropdown. Supported languages include English, Spanish, French, German, Italian, Portuguese, Hindi, Arabic, Japanese, Korean, Chinese, and 17 more.

    <Note>Setting the language to anything other than English automatically switches to the multilingual model for accurate pronunciation.</Note>
  </Step>

  <Step title="Adjust advanced settings (optional)">
    Click **Settings** to fine-tune the output:

    **ElevenLabs settings:**

    * **Similarity** (0–2) — Higher values match the voice's natural characteristics more closely.
    * **Stability** (0–1) — Higher values produce more consistent, predictable delivery. Lower values introduce variation.
    * **Speaker Boost** — Toggle on to enhance voice clarity and presence.

    **Kling TTS settings:**

    * **Speed** (0.8×–2×) — Controls playback speed of the generated audio.
  </Step>

  <Step title="Generate">
    Click **Create**. Generation takes a few seconds. Your audio appears in the player when ready.
  </Step>

  <Step title="Download">
    Click the download button on the audio player to save your file as an MP3.
  </Step>
</Steps>

## Credit costs

| Model      | Cost per generation |
| ---------- | ------------------- |
| ElevenLabs | 10 credits          |
| Kling TTS  | 100 credits         |

<Tip>Use ElevenLabs for most projects — it costs 10 credits and supports 28 languages with expressive, natural voices.</Tip>

## Use cases

<CardGroup cols={2}>
  <Card title="Video voiceovers" icon="video">
    Add professional narration to explainer videos, tutorials, and social content without recording a voiceover.
  </Card>

  <Card title="Podcasts and audio content" icon="microphone">
    Convert blog posts or scripts into podcast episodes, or produce audio versions of written articles.
  </Card>

  <Card title="Accessibility" icon="universal-access">
    Generate audio versions of written content so users with visual impairments or reading difficulties can consume it.
  </Card>

  <Card title="Marketing and ads" icon="bullhorn">
    Produce ad spots, product demos, and promotional audio for campaigns without hiring voice talent.
  </Card>
</CardGroup>