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

# Overview

> Text to Voice is an advanced feature that converts written text into natural-sounding speech using AI technology. This service enables dynamic content creation with high-quality voice synthesis for various applications including video narration, audiobooks, and more.

## Getting Started

<Steps>
  <Step title="Get Available Voices">
    First, retrieve the list of available voices by making a GET request to:

    ```bash theme={null}
    GET https://mango.quickreel.io/api/v2/constants/voices
    ```

    This will return over 800 voices with their details including:

    * voiceId (required for next step)
    * name
    * gender
    * languageCode
    * style
    * sampleVoiceUrl

    <Info>
      For Getting the list of voices, Please refer to the [Voices Page](/api-reference/tts/voices).
    </Info>
  </Step>

  <Step title="Create Text-to-Voice Request">
    **Base URL:** `https://mango.quickreel.io/api/v2`

    **Endpoint:** `/tts`

    **Method:** `POST`

    **Headers:**

    ```markdown theme={null}
    Content-Type: application/json
    x-api-key: <your_api_key>
    ```

    **Request Body Parameters:**

    | Key           | Data Type | Description                                                      | Mandatory              |
    | ------------- | --------- | ---------------------------------------------------------------- | ---------------------- |
    | script/prompt | STRING    | Either provide a script directly or a prompt to generate content | Required (one of them) |
    | voiceId       | STRING    | ID of the selected voice for synthesis                           | Required               |
    | webhookUrl    | STRING    | URL to receive processing updates                                | Required               |

    <Note>
      For optimal results, we recommend: - Maximum script length of 100 words per
      request - Clear, well-structured prompts - High-quality reference materials
      when needed
    </Note>
  </Step>
</Steps>

## Key Features

<CardGroup cols={2}>
  <Card title="Natural Voice Synthesis" icon="waveform">
    Advanced AI models generate human-like speech with natural intonation and
    pronunciation.
  </Card>

  <Card title="Multiple Voice Options" icon="microphone">
    Choose from a diverse selection of voices with different accents, ages, and
    styles.
  </Card>

  <Card title="Multi-language Support" icon="language">
    Support for multiple languages and regional accents to serve global
    audiences.
  </Card>

  <Card title="Customizable Speech" icon="sliders">
    Control speech parameters like speed, pitch, and emphasis for perfect
    delivery.
  </Card>
</CardGroup>

<Note>
  High-quality voice synthesis is crucial for creating engaging audio content
  that maintains listener attention.
</Note>

### Voice Processing Features

* Advanced text preprocessing for optimal pronunciation
* Natural prosody and emotional expression
* Support for SSML tags for fine-tuned control
* Real-time processing status updates

### Voice Customization

* Adjustable speaking rate and pitch
* Multiple accent options per language
* Custom pronunciation dictionary support
* Voice cloning capabilities (premium feature)

### Output Options

* Multiple audio format support (MP3, WAV, OGG)
* Various quality settings
* Batch processing capability
* Streaming audio output

<Card title="Need Support?" icon="question" href="https://discord.com/invite/HXQ92SDamV">
  Join our Discord community for technical support and usage tips.
</Card>