Fourie

Introduction

Text to Speech (TTS)

Languages Supported

Speaker Details

List of Speakers

TTS - API

Speech to Text (STT)

STT - API

Translation

Translate Text

Translate Text Batch

Transliteration

Text Transliteration

Text Transliteration Batch

Text Extraction

Text Extraction API

Emotion Recognition

Text Emotion Recognition (TER)

Speech Emotion Recognition (SER)

Gender  Detection

Paraphraser

Summary Generation

Audio Extraction

Music Source Separation

Audio Conversion

backsense-tts-service

Fourie-Documentation

Production

Sandbox

<p class="slate-p" placeholder="Type / for widgets"><span style="color:var(--tw-prose-bold)" class="slate-color"><strong style="color:var(--tw-prose-bold)" class="slate-bold">Welcome to Fourie.ai: Your Comprehensive Solution for Content Localization</strong></span></p><p class="slate-p" placeholder="Type / for widgets">In the ever-evolving landscape of global communication, the need for effective and inclusive content localization is paramount. Fourie.ai stands at the forefront of this challenge, offering an advanced platform that combines the power of AI and machine learning to redefine how content is adapted and delivered across diverse markets. Our services are designed to cater to a multitude of industries, ranging from media and entertainment to educational and corporate sectors, ensuring that your message is not just heard, but resonates deeply with your audience.</p><p class="slate-p" placeholder="Type / for widgets"><span style="color:var(--tw-prose-bold)" class="slate-color"><strong style="color:var(--tw-prose-bold)" class="slate-bold">Key Features of Fourie.ai:</strong></span></p><ol class="slate-ol"><li class="slate-li"><div style="position:relative"><a href="https://app.theneo.io/fourie/api-docs/text-to-speech-tts/languages-supported" target="_self">Multilingual Support:</a> Our platform proudly supports multiple languages in various accents, ensuring that your content is accessible and relatable to a global audience.</div></li><li class="slate-li"><div style="position:relative"><a href="https://app.theneo.io/fourie/api-docs/text-to-speech-tts" target="_self">Text-to-Speech Services: </a>Convert written text into natural, lifelike speech in more than 40 languages and accents, making your content engaging and inclusive.</div></li><li class="slate-li"><div style="position:relative"><a href="https://app.theneo.io/fourie/api-docs/stt-api/speech-to-text-stt" target="_self">Speech-to-Text Conversion:</a> Utilize sophisticated audio processing to transcribe spoken words accurately into text, enhancing content creation and documentation workflows.</div></li><li class="slate-li"><div style="position:relative"><a href="https://app.theneo.io/fourie/api-docs/translation-services" target="_self">Advanced Translation Tools:</a> Overcome language barriers with our state-of-the-art translation services, tailored to maintain the essence of your message in 100+ languages.</div></li><li class="slate-li"><div style="position:relative"><a href="https://app.theneo.io/fourie/api-docs/paraphraser" target="_self">Paraphrasing Engine:</a> Adapt and refine your content while preserving its original meaning, ideal for customizing messages to suit different cultural contexts and markets.</div></li><li class="slate-li"><div style="position:relative"><a href="https://app.theneo.io/fourie/api-docs/detection-techniques" target="_self">Innovative Detection Techniques:</a>  Our platform features cutting-edge detection capabilities, including gender recognition, speech nuances, emotional tone, and environmental context, adding layers of depth and precision to your localization efforts.</div></li><li class="slate-li"><div style="position:relative"><a href="https://app.theneo.io/fourie/api-docs/text-extraction" target="_self">Intelligent Text Extraction:</a> a versatile solution for converting diverse document formats into refined text, catering to a range of applications from data analysis to content standardization.</div></li></ol><p class="slate-p" placeholder="Type / for widgets">At <a href="https://studio.fourie.ai/" target="_self">Fourie.ai</a><strong class="slate-bold">,</strong>  we understand that localization is more than just translation. It&apos;s about creating a connection, evoking emotion, and delivering messages that resonate. Whether you&apos;re looking to expand your reach, enhance accessibility, or streamline content production, Fourie.ai is your partner in this journey, offering tools and services that are as diverse as the audiences you aim to reach.</p><p class="slate-p" placeholder="Type / for widgets">Sign up on<a href="https://studio.fourie.ai/" target="_self"> Fourie.ai</a>, where innovative technology meets the art of communication, and take your content to a new horizon of global engagement.</p><p class="slate-p" placeholder="Type / for widgets">

</p><p class="slate-p" placeholder="Type / for widgets"></p>

Welcome to Fourie.ai: Your Comprehensive Solution for Content Localization

In the ever-evolving landscape of global communication, the need for effective and inclusive content localization is paramount. Fourie.ai stands at the forefront of this challenge, offering an advanced platform that combines the power of AI and machine learning to redefine how content is adapted and delivered across diverse markets. Our services are designed to cater to a multitude of industries, ranging from media and entertainment to educational and corporate sectors, ensuring that your message is not just heard, but resonates deeply with your audience.

  we understand that localization is more than just translation. It's about creating a connection, evoking emotion, and delivering messages that resonate. Whether you're looking to expand your reach, enhance accessibility, or streamline content production, Fourie.ai is your partner in this journey, offering tools and services that are as diverse as the audiences you aim to reach.

, where innovative technology meets the art of communication, and take your content to a new horizon of global engagement.

<div  data-type="success" style="background-color:#DEFBE6;color:#00cb38"><div ><svg width="18" height="18" viewBox="0 0 18 18" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M7.77116 10.8968L5.72949 8.8551C5.60449 8.7301 5.45171 8.6676 5.27116 8.6676C5.0906 8.6676 4.93088 8.73705 4.79199 8.87594C4.6531 9.01482 4.58366 9.17455 4.58366 9.3551C4.58366 9.53566 4.6531 9.68844 4.79199 9.81344L7.33366 12.3551C7.45866 12.4801 7.60449 12.5426 7.77116 12.5426C7.93783 12.5426 8.08366 12.4801 8.20866 12.3551L13.2087 7.3551C13.3337 7.2301 13.3927 7.07732 13.3857 6.89677C13.3788 6.71621 13.3128 6.56344 13.1878 6.43844C13.0628 6.29955 12.9066 6.2301 12.7191 6.2301C12.5316 6.2301 12.3684 6.29955 12.2295 6.43844L7.77116 10.8968ZM9.00033 17.3343C7.81977 17.3343 6.72255 17.1225 5.70866 16.6989C4.69477 16.2752 3.81283 15.6884 3.06283 14.9384C2.31283 14.1884 1.72602 13.3065 1.30241 12.2926C0.878798 11.2787 0.666992 10.1815 0.666992 9.00094C0.666992 7.83427 0.878798 6.74399 1.30241 5.7301C1.72602 4.71621 2.31283 3.83427 3.06283 3.08427C3.81283 2.33427 4.69477 1.74399 5.70866 1.31344C6.72255 0.88288 7.81977 0.667603 9.00033 0.667603C10.167 0.667603 11.2573 0.88288 12.2712 1.31344C13.285 1.74399 14.167 2.33427 14.917 3.08427C15.667 3.83427 16.2573 4.71621 16.6878 5.7301C17.1184 6.74399 17.3337 7.83427 17.3337 9.00094C17.3337 10.1815 17.1184 11.2787 16.6878 12.2926C16.2573 13.3065 15.667 14.1884 14.917 14.9384C14.167 15.6884 13.285 16.2752 12.2712 16.6989C11.2573 17.1225 10.167 17.3343 9.00033 17.3343ZM9.00033 16.0843C11.0142 16.0843 12.6982 15.4072 14.0524 14.053C15.4066 12.6989 16.0837 11.0148 16.0837 9.00094C16.0837 6.98705 15.4066 5.30302 14.0524 3.94885C12.6982 2.59469 11.0142 1.9176 9.00033 1.9176C6.98644 1.9176 5.30241 2.59469 3.94824 3.94885C2.59408 5.30302 1.91699 6.98705 1.91699 9.00094C1.91699 11.0148 2.59408 12.6989 3.94824 14.053C5.30241 15.4072 6.98644 16.0843 9.00033 16.0843Z" fill="#06837A"></path></svg></div><div ><p class="slate-p" placeholder="Type / for widgets"><strong class="slate-bold">Note:</strong> You need to sign up at <a href="https://studio.fourie.ai" target="_blank">fourie.ai</a>, After creating your account, send your email address at <strong class="slate-bold">hello@fourie.ai </strong>to get your API-KEY.</p></div></div><p class="slate-p" placeholder="Type / for widgets"><span style="color:var(--tw-prose-bold)" class="slate-color"><strong style="color:var(--tw-prose-bold)" class="slate-bold">Fourie.ai&apos;s Text-to-Speech Service: Simplifying Speech Synthesis</strong></span></p><p class="slate-p" placeholder="Type / for widgets">Fourie.ai introduces a streamlined Text-to-Speech Service, designed to convert text into realistic spoken words effortlessly. Ideal for creating engaging audio content across various applications, our service enhances accessibility and user engagement. It simplifies integration, allowing you to focus on your product while we handle the speech synthesis.</p><p class="slate-p" placeholder="Type / for widgets">
The Text-to-speech functionality provided by this API can be used in various use cases. For example, you can create voice-overs for videos or presentations, generate audio for accessibility purposes, or even build interactive voice response (IVR) systems. The possibilities are endless.</p><p class="slate-p" placeholder="Type / for widgets">When using this API, keep in mind that the input should be provided as text and the output will be an audio file. The API will handle the conversion process for you, allowing you to focus on the integration itself.

Feel free to explore the other sections of the documentation for more detailed information on request and response examples, parameters, and any additional features or considerations. We&apos;re here to help you successfully integrate our TTS-Service API into your projects and bring your text to life with ease.</p>

Fourie.ai's Text-to-Speech Service: Simplifying Speech Synthesis

Fourie.ai introduces a streamlined Text-to-Speech Service, designed to convert text into realistic spoken words effortlessly. Ideal for creating engaging audio content across various applications, our service enhances accessibility and user engagement. It simplifies integration, allowing you to focus on your product while we handle the speech synthesis.


The Text-to-speech functionality provided by this API can be used in various use cases. For example, you can create voice-overs for videos or presentations, generate audio for accessibility purposes, or even build interactive voice response (IVR) systems. The possibilities are endless.

When using this API, keep in mind that the input should be provided as text and the output will be an audio file. The API will handle the conversion process for you, allowing you to focus on the integration itself.

Feel free to explore the other sections of the documentation for more detailed information on request and response examples, parameters, and any additional features or considerations. We're here to help you successfully integrate our TTS-Service API into your projects and bring your text to life with ease.

<p class="slate-p" placeholder="Type / for widgets">This languages section allows you to retrieve a list of all languages available for TTS. The response will include information about each language, such as its name, accent, and locale. This can be useful for various use cases, including populating a dropdown menu for language selection or displaying a list of supported languages. 
The language API would be used across multiple services by <a href="https://studio.fourie.ai/" target="_blank">fourie</a> such as <a href="https://app.theneo.io/fourie/api-docs/text-to-speech-tts/tts-api" target="_blank">Text to Speech</a>, and <a href="https://app.theneo.io/fourie/api-docs/text-to-speech-tts/speaker-details" target="_self">Speaker Details</a>.
The endpoint for this API is <code class="slate-code"><strong class="slate-bold">/languages/tts</strong></code><strong class="slate-bold"> </strong>and can be accessed using a <strong class="slate-bold">GET </strong>request.</p><table class="slate-table"><colgroup><col style="width:30.638297872340424%"/><col style="width:29.70212765957447%"/></colgroup><tbody class="slate-TableElement-tbody"><tr class="slate-tr"><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">language</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">This field represents the name of the language in a human-readable format. It is presented in a title case for consistency and easy identification. For instance, &quot;Arabic&quot;, &quot;Amharic&quot;, and &quot;Spanish&quot; are the names of the languages.</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td></tr><tr class="slate-tr"><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">accent</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">This field indicates the specific variation or dialect of the language, often tied to a geographical region or country. It is instrumental in distinguishing between different forms of the same language as spoken or written in various locations. The format typically includes the language name followed by the country or region in parentheses.

</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td></tr><tr class="slate-tr"><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">locale</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">This field contains the locale code associated with the language and its regional variation. The locale code is a standardized code used in computer software and databases to identify languages and their regional dialects. It usually consists of a two-letter language code (following ISO 639-1 standards), a hyphen, and a two-letter country or region code (following ISO 3166-1 alpha-2 standards). Users need to pass on the locale to <a href="https://app.theneo.io/syncsense/fourie-documentation/speaker-details" target="_self">speaker details </a> API as well as the  API provided by Fourietext-to-speech</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td></tr></tbody></table><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p>

This languages section allows you to retrieve a list of all languages available for TTS. The response will include information about each language, such as its name, accent, and locale. This can be useful for various use cases, including populating a dropdown menu for language selection or displaying a list of supported languages. 
The language API would be used across multiple services by 

Essential for authenticating the API call. This header parameter carries the API key or access token.

Authorization

A snippet of how the response is structured. 

<p class="slate-p" placeholder="Type / for widgets">This API endpoint allows you to retrieve details of speakers based on the specified language. By making a <strong class="slate-bold">POST </strong>request to the <code class="slate-code"><strong class="slate-bold">/tts-speakers</strong></code> endpoint, you can obtain relevant information about speakers who speak a particular language.</p><p class="slate-p" placeholder="Type / for widgets">This functionality is particularly useful for applications or services that require language-specific content or services. By using this API, you can easily fetch speaker details based on the language they speak, enabling you to provide tailored experiences to your users.</p><p class="slate-p" placeholder="Type / for widgets">To use this API, include the locale parameter in the body of your <strong class="slate-bold">POST </strong>request. Additionally, you can include the gender parameter to further filter the results. This allows you to retrieve speaker details based not only on language but also on gender.</p><p class="slate-p" placeholder="Type / for widgets">By leveraging this API endpoint, you can seamlessly integrate speaker details into your application or service, ensuring a smooth and efficient user experience, and can further use them for Text-to-speech integration.
</p><p class="slate-p" placeholder="Type / for widgets">You need to pass on the <code class="slate-code">&quot;locale&quot;</code> parameter that you can get from the<strong class="slate-bold"> </strong><a href="https://app.theneo.io/fourie/api-docs/text-to-speech-tts/languages-supported" target="_self">Language </a>API
</p><table class="slate-table"><colgroup></colgroup><tbody class="slate-TableElement-tbody"><tr class="slate-tr"><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">speaker_name</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">The name of the speaker that, you can use the name to display in your application</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td></tr><tr class="slate-tr"><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">speaker_id</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">Speaker Id needs to be passed for Text to Speech Api integration and is one of the most crucial parts of the response</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td></tr><tr class="slate-tr"><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">gender</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">Gender of the speaker or the voice that you can use</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td></tr><tr class="slate-tr"><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">locale</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">The locale of the language that the speaker can speak in.</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td></tr><tr class="slate-tr"><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">locale_code</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">The locale code of the speaker for further use in your application</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td></tr><tr class="slate-tr"><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">language_name</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">Full Name of the language with the Country to check or change the accent.</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td></tr></tbody></table><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p>

This API endpoint allows you to retrieve details of speakers based on the specified language. By making a 

 endpoint, you can obtain relevant information about speakers who speak a particular language.

This functionality is particularly useful for applications or services that require language-specific content or services. By using this API, you can easily fetch speaker details based on the language they speak, enabling you to provide tailored experiences to your users.

To use this API, include the locale parameter in the body of your 

request. Additionally, you can include the gender parameter to further filter the results. This allows you to retrieve speaker details based not only on language but also on gender.

By leveraging this API endpoint, you can seamlessly integrate speaker details into your application or service, ensuring a smooth and efficient user experience, and can further use them for Text-to-speech integration.


locale

gender

A cumulative list of all the speaker details for

 different speaker voices for all your language needs by accents:

<div  data-type="info" style="background-color:#eef1ff;color:#4a59af"><div ><svg width="20" height="20" viewBox="0 0 20 20" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M10.0628 14.1676C10.2434 14.1676 10.3927 14.1086 10.5107 13.9905C10.6288 13.8725 10.6878 13.7232 10.6878 13.5426V9.77177C10.6878 9.6051 10.6253 9.46274 10.5003 9.34469C10.3753 9.22663 10.2295 9.1676 10.0628 9.1676C9.88227 9.1676 9.73296 9.22663 9.61491 9.34469C9.49685 9.46274 9.43783 9.61205 9.43783 9.7926V13.5634C9.43783 13.7301 9.50033 13.8725 9.62533 13.9905C9.75033 14.1086 9.89616 14.1676 10.0628 14.1676ZM10.0003 7.62594C10.1948 7.62594 10.358 7.56344 10.4899 7.43844C10.6219 7.31344 10.6878 7.15371 10.6878 6.95927C10.6878 6.76482 10.6219 6.59816 10.4899 6.45927C10.358 6.32038 10.1948 6.25094 10.0003 6.25094C9.80588 6.25094 9.64269 6.32038 9.51074 6.45927C9.3788 6.59816 9.31283 6.76482 9.31283 6.95927C9.31283 7.15371 9.3788 7.31344 9.51074 7.43844C9.64269 7.56344 9.80588 7.62594 10.0003 7.62594ZM10.0003 18.3343C8.81977 18.3343 7.72255 18.1225 6.70866 17.6989C5.69477 17.2752 4.81283 16.6884 4.06283 15.9384C3.31283 15.1884 2.72602 14.3065 2.30241 13.2926C1.8788 12.2787 1.66699 11.1815 1.66699 10.0009C1.66699 8.83427 1.8788 7.74399 2.30241 6.7301C2.72602 5.71621 3.31283 4.83427 4.06283 4.08427C4.81283 3.33427 5.69477 2.74399 6.70866 2.31344C7.72255 1.88288 8.81977 1.6676 10.0003 1.6676C11.167 1.6676 12.2573 1.88288 13.2712 2.31344C14.285 2.74399 15.167 3.33427 15.917 4.08427C16.667 4.83427 17.2573 5.71621 17.6878 6.7301C18.1184 7.74399 18.3337 8.83427 18.3337 10.0009C18.3337 11.1815 18.1184 12.2787 17.6878 13.2926C17.2573 14.3065 16.667 15.1884 15.917 15.9384C15.167 16.6884 14.285 17.2752 13.2712 17.6989C12.2573 18.1225 11.167 18.3343 10.0003 18.3343ZM10.0003 17.0843C11.9448 17.0843 13.6114 16.3898 15.0003 15.0009C16.3892 13.612 17.0837 11.9454 17.0837 10.0009C17.0837 8.05649 16.3892 6.38982 15.0003 5.00094C13.6114 3.61205 11.9448 2.9176 10.0003 2.9176C8.05588 2.9176 6.38921 3.61205 5.00033 5.00094C3.61144 6.38982 2.91699 8.05649 2.91699 10.0009C2.91699 11.9454 3.61144 13.612 5.00033 15.0009C6.38921 16.3898 8.05588 17.0843 10.0003 17.0843Z" fill="#3960B4"></path></svg></div><div ><p class="slate-p" placeholder="Type / for widgets"><strong class="slate-bold">Note:</strong> Refer to <a href="https://app.theneo.io/syncsense/fourie-documentation/languages-detail" target="_self">Languages</a> API to get a list of supported languages and also for proper locale code needed to be passed in “locale” in the payload also check out the <a href="https://app.theneo.io/syncsense/fourie-documentation/speakers-detail" target="_self">Speakers </a>API to get a detailed list of all the speakers available for supported languages.
<a href="https://fourie.ai/" target="_blank">Fourie</a> provides 500+ different voices and support for 60+ languages with different accents for all 
of your text-to-speech needs</p></div></div><p class="slate-p" placeholder="Type / for widgets">The <strong class="slate-bold">TTS-Service API</strong> endpoint by <a href="https://studio.fourie.ai/" target="_blank">fourie </a>allows you to convert text into spoken words. By making a <strong class="slate-bold">POST </strong>request to, you can send the desired text as input and receive an audio file as output. This <strong class="slate-bold">API </strong>is designed to integrate seamlessly with your applications, enabling you to incorporate speech capabilities into your products or services.

To get started with the TTS-Service API, make a <strong class="slate-bold">POST </strong>request to <code class="slate-code"><strong class="slate-bold">/tts</strong></code> and include the text you want to convert as the request payload. The API will process the request and return the URL of the audio file as the response. You can then use this file as needed within your application.

For the list of all the speakers by language refer to <a href="https://app.theneo.io/syncsense/fourie-documentation/speakers-detail" target="_self">Speakers</a> API.                  
To get a detailed List of all the supported languages, refer to<strong class="slate-bold"> </strong><a href="https://app.theneo.io/syncsense/fourie-documentation/languages-detail" target="_self">Language</a> API.     
You need to use the <code class="slate-code"><strong class="slate-bold">&quot;locale&quot;</strong></code> parameter from the <strong class="slate-bold">Language-List GET</strong> API and pass it in the text-to-speech <code class="slate-code"><strong class="slate-bold">&quot;locale&quot;</strong></code>parameter</p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p>

allows you to convert text into spoken words. By making a 

request to, you can send the desired text as input and receive an audio file as output. This 

is designed to integrate seamlessly with your applications, enabling you to incorporate speech capabilities into your products or services.

To get started with the TTS-Service API, make a 

 and include the text you want to convert as the request payload. The API will process the request and return the URL of the audio file as the response. You can then use this file as needed within your application.

For the list of all the speakers by language refer to 

 API.                  
To get a detailed List of all the supported languages, refer to

A body parameter that contains the text intended for conversion to speech by the service. The text should align with the language specified in the 'locale' parameter.

text

A body parameter that standardizes the language used in the text-to-speech service.

A body parameter that designates the gender of the voice for the text-to-speech conversion. Allowed values are 'male' and 'female'.

A body parameter that identifies the speaker whose voice is required for the text-to-speech conversion, denoted by a unique identifier.

speaker_id

A body parameter that determines the pace of the spoken text, adjustable within the range of 0.5 to 2.

speed

A body parameter that manipulates the pitch or tone of the produced speech within the range of -400 to 400.

pitch

A body parameter that controls the loudness of the generated speech, allowing for adjustment within the range of 0.0 to 2.

volume

A response parameter that returns the url of the audio clip created from the provided text.

audio_clip

<p class="slate-p" placeholder="Type / for widgets"><span style="color:var(--tw-prose-bold)" class="slate-color"><strong style="color:var(--tw-prose-bold)" class="slate-bold">Fourie.ai&apos;s Speech-to-Text Service: Effortless Audio-to-Text Conversion</strong></span></p><p class="slate-p" placeholder="Type / for widgets">Fourie.ai proudly introduces its Speech-to-Text Service, a sophisticated solution designed to transform audio content into accurate text. This service is expertly crafted to support a variety of audio formats, providing flexibility and ease of use. Ideal for a multitude of applications, our Speech-to-Text service opens up new possibilities in content creation and analysis.</p><p class="slate-p" placeholder="Type / for widgets">Whether you&apos;re looking to generate subtitles for videos, analyze spoken content for insights, or develop voice-controlled interfaces, our service offers the precision and efficiency you need. It&apos;s a versatile tool suited for everything from transcription services to voice-enabled assistants, enhancing accessibility and user interaction.</p><p class="slate-p" placeholder="Type / for widgets">With our focus on seamless integration, you can easily incorporate this functionality into your applications, enriching your user experience. Explore the transformative potential of speech recognition with <a href="https://studio.fourie.ai/" target="_blank">Fourie.ai&#x27;s </a>Speech-to-Text Service, where audio meets innovation.</p>

Fourie.ai's Speech-to-Text Service: Effortless Audio-to-Text Conversion

Fourie.ai proudly introduces its Speech-to-Text Service, a sophisticated solution designed to transform audio content into accurate text. This service is expertly crafted to support a variety of audio formats, providing flexibility and ease of use. Ideal for a multitude of applications, our Speech-to-Text service opens up new possibilities in content creation and analysis.

Whether you're looking to generate subtitles for videos, analyze spoken content for insights, or develop voice-controlled interfaces, our service offers the precision and efficiency you need. It's a versatile tool suited for everything from transcription services to voice-enabled assistants, enhancing accessibility and user interaction.

With our focus on seamless integration, you can easily incorporate this functionality into your applications, enriching your user experience. Explore the transformative potential of speech recognition with 

Speech-to-Text Service, where audio meets innovation.

<p class="slate-p" placeholder="Type / for widgets"><span style="color:var(--tw-prose-bold)" class="slate-color"><strong style="color:var(--tw-prose-bold)" class="slate-bold">Fourie.ai&apos;s Text Translation: Bridging Language Barriers</strong></span></p><p class="slate-p" placeholder="Type / for widgets">Fourie.ai is excited to present Text Translation, a cutting-edge solution designed to seamlessly integrate translation capabilities into your applications. Our service stands out for its ability to facilitate effortless translation between multiple languages, making it an invaluable tool for reaching a global audience.</p><p class="slate-p" placeholder="Type / for widgets">Whether you are developing a multilingual website, a language learning application, or any platform that requires the translation of text, our service provides a straightforward, user-friendly solution. Our Text Translation excels in handling everything from simple sentences to large batches of text, ensuring efficiency and accuracy in all your translation needs.</p><p class="slate-p" placeholder="Type / for widgets">Additionally, our service supports a wide array of source and target languages, enabling you to connect with a diverse user base. This feature is especially beneficial for applications that cater to international markets, where language inclusivity is key.</p><p class="slate-p" placeholder="Type / for widgets">Discover the power of seamless language translation with <a href="https://studio.fourie.ai" target="_blank">Fourie.ai</a> and take your application to a global stage, where no language barrier can hinder your reach and impact.</p><p class="slate-p" placeholder="Type / for widgets"></p>

Fourie.ai's Text Translation: Bridging Language Barriers

Fourie.ai is excited to present Text Translation, a cutting-edge solution designed to seamlessly integrate translation capabilities into your applications. Our service stands out for its ability to facilitate effortless translation between multiple languages, making it an invaluable tool for reaching a global audience.

Whether you are developing a multilingual website, a language learning application, or any platform that requires the translation of text, our service provides a straightforward, user-friendly solution. Our Text Translation excels in handling everything from simple sentences to large batches of text, ensuring efficiency and accuracy in all your translation needs.

Additionally, our service supports a wide array of source and target languages, enabling you to connect with a diverse user base. This feature is especially beneficial for applications that cater to international markets, where language inclusivity is key.

Discover the power of seamless language translation with 

 and take your application to a global stage, where no language barrier can hinder your reach and impact.

<p class="slate-p" placeholder="Type / for widgets"><a href="https://studio.fourie.ai" target="_blank">Fourie&#x27;s</a> Text Transliteration service is a versatile tool with a broad range of applications. It plays a pivotal role in language learning platforms, facilitating improved pronunciation and comprehension. Content management systems benefit from its ability to ensure uniformity across multilingual datasets, simplifying the handling of diverse linguistic content. In cross-cultural communication, the service reduces language barriers by providing a consistent English script. Additionally, it enhances interactions with digital assistants by converting various language inputs into a unified English format, improving user experience. For advanced content analysis, the service prepares multilingual data for comprehensive processing and insights. Whether in education, communication, or data analytics, Fourie&apos;s Text Transliteration service stands as a reliable and indispensable solution for diverse linguistic requirements.
</p>

 Text Transliteration service is a versatile tool with a broad range of applications. It plays a pivotal role in language learning platforms, facilitating improved pronunciation and comprehension. Content management systems benefit from its ability to ensure uniformity across multilingual datasets, simplifying the handling of diverse linguistic content. In cross-cultural communication, the service reduces language barriers by providing a consistent English script. Additionally, it enhances interactions with digital assistants by converting various language inputs into a unified English format, improving user experience. For advanced content analysis, the service prepares multilingual data for comprehensive processing and insights. Whether in education, communication, or data analytics, Fourie's Text Transliteration service stands as a reliable and indispensable solution for diverse linguistic requirements.


<p class="slate-p" placeholder="Type / for widgets">
Introducing the <strong class="slate-bold">Text Extraction API</strong>—a powerful and versatile solution designed to effortlessly convert a variety of<strong class="slate-bold"> document formats into refined text</strong>. This API streamlines the integration process with a straightforward request, allowing for precise extraction by specifying language nuances. Whether you&apos;re an experienced developer or a non-technical user, the Text Extraction API enhances application versatility. From data analysis to content standardization, its use cases span a wide range of applications, making it a valuable tool for diverse industries. Explore the extensive capabilities of the Text Extraction API to elevate your user experience and streamline content handling. For a deeper understanding, refer to the comprehensive documentation.





</p><p class="slate-p" placeholder="Type / for widgets"></p>

—a powerful and versatile solution designed to effortlessly convert a variety of

. This API streamlines the integration process with a straightforward request, allowing for precise extraction by specifying language nuances. Whether you're an experienced developer or a non-technical user, the Text Extraction API enhances application versatility. From data analysis to content standardization, its use cases span a wide range of applications, making it a valuable tool for diverse industries. Explore the extensive capabilities of the Text Extraction API to elevate your user experience and streamline content handling. For a deeper understanding, refer to the comprehensive documentation.







<p class="slate-p" placeholder="Type / for widgets">
<a href="https://studio.fourie.ai/" target="_blank">Fourie </a>presents<strong class="slate-bold"> advanced emotion detection techniques</strong> through its comprehensive Intelligent Detection Techniques API. This innovative service empowers developers with state-of-the-art capabilities in <strong class="slate-bold">text emotion detection</strong> and <strong class="slate-bold">speech emotion detection</strong>. Leveraging cutting-edge machine learning algorithms, Fourie&apos;s API opens doors to a new era of applications capable of understanding and responding to human expressions with unparalleled accuracy. From discerning gender in visual or textual inputs to interpreting emotional cues in spoken language, this API is a versatile toolset designed to elevate user experiences across a myriad of industries. Join the forefront of AI-driven innovation with Fourie&apos;s Intelligent Detection Techniques API and unlock the potential for creating more empathetic and intuitive digital interactions.</p><p class="slate-p" placeholder="Type / for widgets"><strong class="slate-bold">List of Emotions Recognised by Our API: </strong></p><table class="slate-table"><colgroup><col style="width:14.212765957446807%"/><col/><col/><col/><col/><col/><col/></colgroup><tbody class="slate-TableElement-tbody"><tr class="slate-tr"><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">Anger</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">Joy</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">Sadness</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">Love</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">Fear</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">Surprise</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td><td class="slate-td"><div class="slate-TableCellElement-content"><p class="slate-p" placeholder="Type / for widgets">Neutral</p></div><div class="slate-TableCellElement-resizableWrapper" contenteditable="false"><div style="position:relative;user-select:auto;width:100%;height:100%;box-sizing:border-box;flex-shrink:0" ><div><div  style="position:absolute;user-select:none;width:10px;height:calc(100% + 12px);top:-12px;cursor:col-resize;right:-5px;z-index:20"></div></div></div><div class="slate-TableCellElement-handle"></div></div><div class="slate-TableCellElement-selectedCell" contenteditable="false"></div></td></tr></tbody></table><p class="slate-p" placeholder="Type / for widgets"></p>

 through its comprehensive Intelligent Detection Techniques API. This innovative service empowers developers with state-of-the-art capabilities in 

. Leveraging cutting-edge machine learning algorithms, Fourie's API opens doors to a new era of applications capable of understanding and responding to human expressions with unparalleled accuracy. From discerning gender in visual or textual inputs to interpreting emotional cues in spoken language, this API is a versatile toolset designed to elevate user experiences across a myriad of industries. Join the forefront of AI-driven innovation with Fourie's Intelligent Detection Techniques API and unlock the potential for creating more empathetic and intuitive digital interactions.

<div  data-type="info" style="background-color:#eef1ff;color:#4a59af"><div ><svg width="20" height="20" viewBox="0 0 20 20" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M10.0628 14.1676C10.2434 14.1676 10.3927 14.1086 10.5107 13.9905C10.6288 13.8725 10.6878 13.7232 10.6878 13.5426V9.77177C10.6878 9.6051 10.6253 9.46274 10.5003 9.34469C10.3753 9.22663 10.2295 9.1676 10.0628 9.1676C9.88227 9.1676 9.73296 9.22663 9.61491 9.34469C9.49685 9.46274 9.43783 9.61205 9.43783 9.7926V13.5634C9.43783 13.7301 9.50033 13.8725 9.62533 13.9905C9.75033 14.1086 9.89616 14.1676 10.0628 14.1676ZM10.0003 7.62594C10.1948 7.62594 10.358 7.56344 10.4899 7.43844C10.6219 7.31344 10.6878 7.15371 10.6878 6.95927C10.6878 6.76482 10.6219 6.59816 10.4899 6.45927C10.358 6.32038 10.1948 6.25094 10.0003 6.25094C9.80588 6.25094 9.64269 6.32038 9.51074 6.45927C9.3788 6.59816 9.31283 6.76482 9.31283 6.95927C9.31283 7.15371 9.3788 7.31344 9.51074 7.43844C9.64269 7.56344 9.80588 7.62594 10.0003 7.62594ZM10.0003 18.3343C8.81977 18.3343 7.72255 18.1225 6.70866 17.6989C5.69477 17.2752 4.81283 16.6884 4.06283 15.9384C3.31283 15.1884 2.72602 14.3065 2.30241 13.2926C1.8788 12.2787 1.66699 11.1815 1.66699 10.0009C1.66699 8.83427 1.8788 7.74399 2.30241 6.7301C2.72602 5.71621 3.31283 4.83427 4.06283 4.08427C4.81283 3.33427 5.69477 2.74399 6.70866 2.31344C7.72255 1.88288 8.81977 1.6676 10.0003 1.6676C11.167 1.6676 12.2573 1.88288 13.2712 2.31344C14.285 2.74399 15.167 3.33427 15.917 4.08427C16.667 4.83427 17.2573 5.71621 17.6878 6.7301C18.1184 7.74399 18.3337 8.83427 18.3337 10.0009C18.3337 11.1815 18.1184 12.2787 17.6878 13.2926C17.2573 14.3065 16.667 15.1884 15.917 15.9384C15.167 16.6884 14.285 17.2752 13.2712 17.6989C12.2573 18.1225 11.167 18.3343 10.0003 18.3343ZM10.0003 17.0843C11.9448 17.0843 13.6114 16.3898 15.0003 15.0009C16.3892 13.612 17.0837 11.9454 17.0837 10.0009C17.0837 8.05649 16.3892 6.38982 15.0003 5.00094C13.6114 3.61205 11.9448 2.9176 10.0003 2.9176C8.05588 2.9176 6.38921 3.61205 5.00033 5.00094C3.61144 6.38982 2.91699 8.05649 2.91699 10.0009C2.91699 11.9454 3.61144 13.612 5.00033 15.0009C6.38921 16.3898 8.05588 17.0843 10.0003 17.0843Z" fill="#3960B4"></path></svg></div><div ><p class="slate-p" placeholder="Type / for widgets"><strong class="slate-bold">Note:</strong> The Gender Detection API supports audio files in English and Indian languages. It is also capable of language-agnostic detection.</p></div></div><p class="slate-p" placeholder="Type / for widgets">The <strong class="slate-bold">Gender Detection from Audios API</strong> by <a href="https://studio.fourie.ai/" target="_blank">Fourie </a>offers a streamlined solution for gender detection from audio data, supporting both <strong class="slate-bold">.mp3 </strong>and<strong class="slate-bold"> .wav </strong>formats. The endpoint for gender detection is a <strong class="slate-bold">POST</strong> request to <code class="slate-code"><strong class="slate-bold">/gender-detection</strong></code>. Developers can utilize two mutually exclusive input parameters: <code class="slate-code"><strong class="slate-bold">“audio_url”</strong></code>, a URL pointing to the <strong class="slate-bold">audio file</strong>, or  <code class="slate-code"><strong class="slate-bold">“audio_file”</strong></code> parameter, an audio file uploaded directly to the API. It&apos;s important to note that <strong class="slate-bold">either </strong><code class="slate-code"><strong class="slate-bold">&quot;audio_url&quot;</strong></code> <em class="slate-italic"><strong class="slate-bold">or</strong></em><code class="slate-code"><strong class="slate-bold">“audio_file”</strong></code> can be passed at a time, but not both. The API supports common audio formats, like .<strong class="slate-bold">mp3</strong> and<strong class="slate-bold"> .wav</strong>. The response includes the detected gender and an optional confidence level. In case of errors, detailed error messages help diagnose issues. This API is a valuable addition for applications aiming to tailor user experiences based on gender-specific attributes. Integrate the Gender Detection from Audios API to unlock the potential for personalized and gender-aware interactions in your voice-enabled systems.</p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p>

offers a streamlined solution for gender detection from audio data, supporting both 

formats. The endpoint for gender detection is a 

. Developers can utilize two mutually exclusive input parameters: 

 parameter, an audio file uploaded directly to the API. It's important to note that 

 can be passed at a time, but not both. The API supports common audio formats, like .

. The response includes the detected gender and an optional confidence level. In case of errors, detailed error messages help diagnose issues. This API is a valuable addition for applications aiming to tailor user experiences based on gender-specific attributes. Integrate the Gender Detection from Audios API to unlock the potential for personalized and gender-aware interactions in your voice-enabled systems.

This body parameter accepts binary audio data that the API uses to identify gender. The file should be in a format accepted by the service, such as .wav or .mp3.

audio_file

This body parameter takes in a URL pointing to an audio file hosted externally. The API will download the audio file from the provided URL and use it to detect gender. The audio file should be in a recognized format such as .wav or .mp3.

audio_url

<div  data-type="info" style="background-color:#eef1ff;color:#4a59af"><div ><svg width="20" height="20" viewBox="0 0 20 20" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M10.0628 14.1676C10.2434 14.1676 10.3927 14.1086 10.5107 13.9905C10.6288 13.8725 10.6878 13.7232 10.6878 13.5426V9.77177C10.6878 9.6051 10.6253 9.46274 10.5003 9.34469C10.3753 9.22663 10.2295 9.1676 10.0628 9.1676C9.88227 9.1676 9.73296 9.22663 9.61491 9.34469C9.49685 9.46274 9.43783 9.61205 9.43783 9.7926V13.5634C9.43783 13.7301 9.50033 13.8725 9.62533 13.9905C9.75033 14.1086 9.89616 14.1676 10.0628 14.1676ZM10.0003 7.62594C10.1948 7.62594 10.358 7.56344 10.4899 7.43844C10.6219 7.31344 10.6878 7.15371 10.6878 6.95927C10.6878 6.76482 10.6219 6.59816 10.4899 6.45927C10.358 6.32038 10.1948 6.25094 10.0003 6.25094C9.80588 6.25094 9.64269 6.32038 9.51074 6.45927C9.3788 6.59816 9.31283 6.76482 9.31283 6.95927C9.31283 7.15371 9.3788 7.31344 9.51074 7.43844C9.64269 7.56344 9.80588 7.62594 10.0003 7.62594ZM10.0003 18.3343C8.81977 18.3343 7.72255 18.1225 6.70866 17.6989C5.69477 17.2752 4.81283 16.6884 4.06283 15.9384C3.31283 15.1884 2.72602 14.3065 2.30241 13.2926C1.8788 12.2787 1.66699 11.1815 1.66699 10.0009C1.66699 8.83427 1.8788 7.74399 2.30241 6.7301C2.72602 5.71621 3.31283 4.83427 4.06283 4.08427C4.81283 3.33427 5.69477 2.74399 6.70866 2.31344C7.72255 1.88288 8.81977 1.6676 10.0003 1.6676C11.167 1.6676 12.2573 1.88288 13.2712 2.31344C14.285 2.74399 15.167 3.33427 15.917 4.08427C16.667 4.83427 17.2573 5.71621 17.6878 6.7301C18.1184 7.74399 18.3337 8.83427 18.3337 10.0009C18.3337 11.1815 18.1184 12.2787 17.6878 13.2926C17.2573 14.3065 16.667 15.1884 15.917 15.9384C15.167 16.6884 14.285 17.2752 13.2712 17.6989C12.2573 18.1225 11.167 18.3343 10.0003 18.3343ZM10.0003 17.0843C11.9448 17.0843 13.6114 16.3898 15.0003 15.0009C16.3892 13.612 17.0837 11.9454 17.0837 10.0009C17.0837 8.05649 16.3892 6.38982 15.0003 5.00094C13.6114 3.61205 11.9448 2.9176 10.0003 2.9176C8.05588 2.9176 6.38921 3.61205 5.00033 5.00094C3.61144 6.38982 2.91699 8.05649 2.91699 10.0009C2.91699 11.9454 3.61144 13.612 5.00033 15.0009C6.38921 16.3898 8.05588 17.0843 10.0003 17.0843Z" fill="#3960B4"></path></svg></div><div ><p class="slate-p" placeholder="Type / for widgets"><strong class="slate-bold">Note:</strong> Currently, the Paraphraser endpoint supports <strong class="slate-bold">only English</strong>. Future updates are anticipated to expand this support to include over 40+ languages. 
The Paraphrase API only supports a maximum <strong class="slate-bold">50 </strong>elements at a time.</p></div></div><p class="slate-p" placeholder="Type / for widgets">The <code class="slate-code"><strong class="slate-bold">/paraphrase</strong></code> endpoint of the API is designed to provide a convenient and efficient way to paraphrase text. Accessible via a <strong class="slate-bold">POST </strong>request, this endpoint requires users to include what <code class="slate-code"><strong class="slate-bold">&quot;text&quot;</strong></code> they wish to paraphrase within the request body. Primarily aimed at applications in content creation, language learning, and text uniqueness enhancement, the Paraphraser uses a default algorithm to deliver accurate and coherent paraphrases without additional configuration options. Users should ensure proper formatting and encoding of the text parameter as per the API guidelines and be prepared to handle potential errors or exceptions during integration. This endpoint seamlessly integrates into applications, offering a straightforward solution for generating paraphrased versions of text.
</p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p>

 endpoint of the API is designed to provide a convenient and efficient way to paraphrase text. Accessible via a 

request, this endpoint requires users to include what 

 they wish to paraphrase within the request body. Primarily aimed at applications in content creation, language learning, and text uniqueness enhancement, the Paraphraser uses a default algorithm to deliver accurate and coherent paraphrases without additional configuration options. Users should ensure proper formatting and encoding of the text parameter as per the API guidelines and be prepared to handle potential errors or exceptions during integration. This endpoint seamlessly integrates into applications, offering a straightforward solution for generating paraphrased versions of text.


This body parameter accepts the text input that is to be paraphrased by the "Paraphraser" endpoint in the backsense-tts-service. The input should be a string value representing the sentence or paragraph for paraphrasing.

paraphrased_sentences

<div  data-type="info" style="background-color:#eef1ff;color:#4a59af"><div ><svg width="20" height="20" viewBox="0 0 20 20" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M10.0628 14.1676C10.2434 14.1676 10.3927 14.1086 10.5107 13.9905C10.6288 13.8725 10.6878 13.7232 10.6878 13.5426V9.77177C10.6878 9.6051 10.6253 9.46274 10.5003 9.34469C10.3753 9.22663 10.2295 9.1676 10.0628 9.1676C9.88227 9.1676 9.73296 9.22663 9.61491 9.34469C9.49685 9.46274 9.43783 9.61205 9.43783 9.7926V13.5634C9.43783 13.7301 9.50033 13.8725 9.62533 13.9905C9.75033 14.1086 9.89616 14.1676 10.0628 14.1676ZM10.0003 7.62594C10.1948 7.62594 10.358 7.56344 10.4899 7.43844C10.6219 7.31344 10.6878 7.15371 10.6878 6.95927C10.6878 6.76482 10.6219 6.59816 10.4899 6.45927C10.358 6.32038 10.1948 6.25094 10.0003 6.25094C9.80588 6.25094 9.64269 6.32038 9.51074 6.45927C9.3788 6.59816 9.31283 6.76482 9.31283 6.95927C9.31283 7.15371 9.3788 7.31344 9.51074 7.43844C9.64269 7.56344 9.80588 7.62594 10.0003 7.62594ZM10.0003 18.3343C8.81977 18.3343 7.72255 18.1225 6.70866 17.6989C5.69477 17.2752 4.81283 16.6884 4.06283 15.9384C3.31283 15.1884 2.72602 14.3065 2.30241 13.2926C1.8788 12.2787 1.66699 11.1815 1.66699 10.0009C1.66699 8.83427 1.8788 7.74399 2.30241 6.7301C2.72602 5.71621 3.31283 4.83427 4.06283 4.08427C4.81283 3.33427 5.69477 2.74399 6.70866 2.31344C7.72255 1.88288 8.81977 1.6676 10.0003 1.6676C11.167 1.6676 12.2573 1.88288 13.2712 2.31344C14.285 2.74399 15.167 3.33427 15.917 4.08427C16.667 4.83427 17.2573 5.71621 17.6878 6.7301C18.1184 7.74399 18.3337 8.83427 18.3337 10.0009C18.3337 11.1815 18.1184 12.2787 17.6878 13.2926C17.2573 14.3065 16.667 15.1884 15.917 15.9384C15.167 16.6884 14.285 17.2752 13.2712 17.6989C12.2573 18.1225 11.167 18.3343 10.0003 18.3343ZM10.0003 17.0843C11.9448 17.0843 13.6114 16.3898 15.0003 15.0009C16.3892 13.612 17.0837 11.9454 17.0837 10.0009C17.0837 8.05649 16.3892 6.38982 15.0003 5.00094C13.6114 3.61205 11.9448 2.9176 10.0003 2.9176C8.05588 2.9176 6.38921 3.61205 5.00033 5.00094C3.61144 6.38982 2.91699 8.05649 2.91699 10.0009C2.91699 11.9454 3.61144 13.612 5.00033 15.0009C6.38921 16.3898 8.05588 17.0843 10.0003 17.0843Z" fill="#3960B4"></path></svg></div><div ><p class="slate-p" placeholder="Type / for widgets"><strong class="slate-bold">Note :</strong> Currently, the Summary Generation endpoint supports <strong class="slate-bold">only English</strong>. Future updates are anticipated to expand this support to include over 40+ languages. 
Please ensure that you input text of sufficient length for summarization.</p></div></div><p class="slate-p" placeholder="Type / for widgets">The <strong class="slate-bold">Summary Generation API</strong> by <a href="https://studio.fourie.ai/" target="_self">Fourie </a>presents a robust solution for distilling extensive textual content into concise and informative summaries. Through a simple <strong class="slate-bold">POST </strong>request to the <code class="slate-code"><strong class="slate-bold">/summary-generation</strong></code> endpoint, developers can leverage the efficiency of this tool by providing a <code class="slate-code"><strong class="slate-bold">&quot;text&quot;</strong></code> parameter as input. Whether you&apos;re aiming to condense lengthy articles, documents, or paragraphs into easily digestible summaries, this API offers a seamless and effective solution. Designed to enhance information extraction, the <strong class="slate-bold">Summary Generation API</strong> is a valuable addition to applications seeking to streamline content comprehension. By integrating this tool, developers can effortlessly generate insightful and succinct summaries, optimizing the efficiency of their text-based applications.</p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p>

presents a robust solution for distilling extensive textual content into concise and informative summaries. Through a simple 

 endpoint, developers can leverage the efficiency of this tool by providing a 

 parameter as input. Whether you're aiming to condense lengthy articles, documents, or paragraphs into easily digestible summaries, this API offers a seamless and effective solution. Designed to enhance information extraction, the 

 is a valuable addition to applications seeking to streamline content comprehension. By integrating this tool, developers can effortlessly generate insightful and succinct summaries, optimizing the efficiency of their text-based applications.

A body parameter that contains the content to be summarized by the Summary Generation service.

summary

<p class="slate-p" placeholder="Type / for widgets"></p><div  data-type="info" style="background-color:#eef1ff;color:#4a59af"><div ><svg width="20" height="20" viewBox="0 0 20 20" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M10.0628 14.1676C10.2434 14.1676 10.3927 14.1086 10.5107 13.9905C10.6288 13.8725 10.6878 13.7232 10.6878 13.5426V9.77177C10.6878 9.6051 10.6253 9.46274 10.5003 9.34469C10.3753 9.22663 10.2295 9.1676 10.0628 9.1676C9.88227 9.1676 9.73296 9.22663 9.61491 9.34469C9.49685 9.46274 9.43783 9.61205 9.43783 9.7926V13.5634C9.43783 13.7301 9.50033 13.8725 9.62533 13.9905C9.75033 14.1086 9.89616 14.1676 10.0628 14.1676ZM10.0003 7.62594C10.1948 7.62594 10.358 7.56344 10.4899 7.43844C10.6219 7.31344 10.6878 7.15371 10.6878 6.95927C10.6878 6.76482 10.6219 6.59816 10.4899 6.45927C10.358 6.32038 10.1948 6.25094 10.0003 6.25094C9.80588 6.25094 9.64269 6.32038 9.51074 6.45927C9.3788 6.59816 9.31283 6.76482 9.31283 6.95927C9.31283 7.15371 9.3788 7.31344 9.51074 7.43844C9.64269 7.56344 9.80588 7.62594 10.0003 7.62594ZM10.0003 18.3343C8.81977 18.3343 7.72255 18.1225 6.70866 17.6989C5.69477 17.2752 4.81283 16.6884 4.06283 15.9384C3.31283 15.1884 2.72602 14.3065 2.30241 13.2926C1.8788 12.2787 1.66699 11.1815 1.66699 10.0009C1.66699 8.83427 1.8788 7.74399 2.30241 6.7301C2.72602 5.71621 3.31283 4.83427 4.06283 4.08427C4.81283 3.33427 5.69477 2.74399 6.70866 2.31344C7.72255 1.88288 8.81977 1.6676 10.0003 1.6676C11.167 1.6676 12.2573 1.88288 13.2712 2.31344C14.285 2.74399 15.167 3.33427 15.917 4.08427C16.667 4.83427 17.2573 5.71621 17.6878 6.7301C18.1184 7.74399 18.3337 8.83427 18.3337 10.0009C18.3337 11.1815 18.1184 12.2787 17.6878 13.2926C17.2573 14.3065 16.667 15.1884 15.917 15.9384C15.167 16.6884 14.285 17.2752 13.2712 17.6989C12.2573 18.1225 11.167 18.3343 10.0003 18.3343ZM10.0003 17.0843C11.9448 17.0843 13.6114 16.3898 15.0003 15.0009C16.3892 13.612 17.0837 11.9454 17.0837 10.0009C17.0837 8.05649 16.3892 6.38982 15.0003 5.00094C13.6114 3.61205 11.9448 2.9176 10.0003 2.9176C8.05588 2.9176 6.38921 3.61205 5.00033 5.00094C3.61144 6.38982 2.91699 8.05649 2.91699 10.0009C2.91699 11.9454 3.61144 13.612 5.00033 15.0009C6.38921 16.3898 8.05588 17.0843 10.0003 17.0843Z" fill="#3960B4"></path></svg></div><div ><p class="slate-p" placeholder="Type / for widgets"><strong class="slate-bold">Note:</strong>  The maximum video duration should be of  Video duration limit of <strong class="slate-bold">10 minutes / 600 seconds.</strong></p></div></div><p class="slate-p" placeholder="Type / for widgets"><a href="https://studio.fourie.ai/" target="_blank">Fourie&#x27;s</a><strong class="slate-bold"> Audio Extraction service</strong> introduces a straightforward API endpoint for audio extraction, accessible through a POST request to <code class="slate-code"><strong class="slate-bold">/audio-extraction</strong></code>. Users can choose between two exclusive parameters: <code class="slate-code"><strong class="slate-bold">“video_url”</strong></code> for extracting audio from an online video by providing its URL, or <code class="slate-code"><strong class="slate-bold">“video_file”</strong></code> for uploading a local video file directly. It&apos;s important to note that only one of these parameters should be included in a single request.</p><p class="slate-p" placeholder="Type / for widgets">Users also have the option to include additional parameters for customized extraction:</p><ul class="slate-ul"><li class="slate-li"><div style="position:relative"><span style="color:var(--tw-prose-bold)" class="slate-color"><strong style="color:var(--tw-prose-bold)" class="slate-bold">sample_rate (integer, optional):</strong></span> Specifies the desired sample rate of the extracted audio. This parameter allows users to adjust the quality and characteristics of the output audio.</div></li><li class="slate-li"><div style="position:relative"><span style="color:var(--tw-prose-bold)" class="slate-color"><strong style="color:var(--tw-prose-bold)" class="slate-bold">sample_width (integer, optional):</strong></span> Defines the sample width or bit depth of the extracted audio. Users can use this parameter to control the precision of the audio data.</div></li><li class="slate-li"><div style="position:relative"><span style="color:var(--tw-prose-bold)" class="slate-color"><strong style="color:var(--tw-prose-bold)" class="slate-bold">n_channels (integer, optional):</strong></span> Specifies the number of channels in the extracted audio, allowing users to control the audio&apos;s stereo or mono configuration.</div></li></ul><p class="slate-p" placeholder="Type / for widgets">The supported video formats for extraction are .<strong class="slate-bold">mp4</strong>, <strong class="slate-bold">.mov</strong>, <strong class="slate-bold">.mkv</strong>, <strong class="slate-bold">.webm</strong>, <strong class="slate-bold">.mpeg</strong>,  <strong class="slate-bold">.mpg</strong>, <strong class="slate-bold">.avi</strong>, <strong class="slate-bold">.flv</strong> and <strong class="slate-bold">.m4v</strong>, with the output in <strong class="slate-bold">.wav</strong> file format. Users can further convert the output using the <a href="https://app.theneo.io/fourie/api-docs/audio-conversion" target="_self">Audio Conversion API</a>.</p><p class="slate-p" placeholder="Type / for widgets">This versatile service caters to a range of use cases. Content creators can utilize the API to extract audio for creating podcasts or snippets, while developers can integrate it for enhancing multimedia applications. Moreover, in scenarios where only the audio component is relevant, such as transcription services or voice recognition, Fourie&apos;s Audio Extraction API proves invaluable. Ensure proper authentication headers are included in the request, and handle the response accordingly to enjoy seamless audio extraction with Fourie.</p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p>

 introduces a straightforward API endpoint for audio extraction, accessible through a POST request to 

. Users can choose between two exclusive parameters: 

 for extracting audio from an online video by providing its URL, or 

 for uploading a local video file directly. It's important to note that only one of these parameters should be included in a single request.

Users also have the option to include additional parameters for customized extraction:

The supported video formats for extraction are .

 file format. Users can further convert the output using the 

This versatile service caters to a range of use cases. Content creators can utilize the API to extract audio for creating podcasts or snippets, while developers can integrate it for enhancing multimedia applications. Moreover, in scenarios where only the audio component is relevant, such as transcription services or voice recognition, Fourie's Audio Extraction API proves invaluable. Ensure proper authentication headers are included in the request, and handle the response accordingly to enjoy seamless audio extraction with Fourie.

The video file parameter represents the video file to be used for audio extraction.

video_file

The video URL parameter represents the URL of the video file to be used for audio extraction. It should be a direct URL to the video file and accessible to the service.

video_url

The sample width parameter specifies the number of bytes used to represent each audio sample. It determines the range and precision of the audio data.

sample_width

The n_channels parameter specifies the number of audio channels to be extracted from the video. This parameter determines the audio output format and should be set to a positive integer value.

n_channels

The sample rate parameter specifies the number of audio samples per second. It determines the audio quality and should be set to a valid sample rate, such as 44100 or 48000.

sample_rate

<p class="slate-p" placeholder="Type / for widgets"><a href="https://studio.fourie.ai/" target="_blank">Fourie&#x27;s</a><strong class="slate-bold"> Music Source Separation</strong> service introduces a versatile endpoint at <code class="slate-code"><strong class="slate-bold">/music-source-separation</strong></code>, offering two exclusive parameters: <code class="slate-code"><strong class="slate-bold">“audio_url”</strong></code> for specifying the <strong class="slate-bold">URL </strong>of the audio source, and <code class="slate-code"><strong class="slate-bold">“audio_file” </strong></code>for uploading audio files in <strong class="slate-bold">.mp3</strong> or <strong class="slate-bold">.wav</strong> format. It&apos;s important to note that only one parameter, either <code class="slate-code"><strong class="slate-bold">&quot;audio_url&quot;</strong></code><strong class="slate-bold"> </strong><em class="slate-italic"><strong class="slate-bold">or  </strong></em><code class="slate-code"><strong class="slate-bold">“audio_file”</strong></code>, can be included in a single request. The output of this API comes in an <strong class="slate-bold">.mp3</strong> format only, you can convert it into <strong class="slate-bold">.wav</strong> using <a href="https://app.theneo.io/fourie/api-docs/audio-conversion" target="_self">Audio Conversion API</a>. 

This unique capability enables content creators and developers to separate vocals from music tracks in various audio and video content. Whether enhancing audio editing by isolating vocals or creating custom soundtracks, the API serves as a powerful tool for a diverse range of applications. Users can leverage this functionality to achieve precise control over music and vocals components in their creative projects. Additional use cases include podcast production, karaoke enhancements, audio mixing, and language learning.   </p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p><p class="slate-p" placeholder="Type / for widgets"></p>

 service introduces a versatile endpoint at 

 format. It's important to note that only one parameter, either 

, can be included in a single request. The output of this API comes in an 

. 

This unique capability enables content creators and developers to separate vocals from music tracks in various audio and video content. Whether enhancing audio editing by isolating vocals or creating custom soundtracks, the API serves as a powerful tool for a diverse range of applications. Users can leverage this functionality to achieve precise control over music and vocals components in their creative projects. Additional use cases include podcast production, karaoke enhancements, audio mixing, and language learning.   

The audio file to be processed for music source separation.

The URL of the audio file to be processed for music source separation.

vocals

music

<p class="slate-p" placeholder="Type / for widgets"><a href="https://studio.fourie.ai/" target="_blank">Fourie&#x27;s</a> <strong class="slate-bold">Audio Conversion API</strong>, accessible through the <code class="slate-code"><strong class="slate-bold">/audio-conversion</strong></code><strong class="slate-bold"> </strong>endpoint, seamlessly transforms audio files with flexibility in input formats, including <strong class="slate-bold">.mp3</strong>,<strong class="slate-bold"> .wav</strong>, <strong class="slate-bold">.flac</strong>, <strong class="slate-bold">.ogg</strong>, and <strong class="slate-bold">.aiff</strong>. Users can submit a <strong class="slate-bold">POST </strong>request with <em class="slate-italic"><strong class="slate-bold"> </strong></em><code class="slate-code"><strong class="slate-bold">“audio_file”</strong></code> for local uploads. The converted audio file is delivered in the user&apos;s choice of either <strong class="slate-bold">.mp3</strong> or <strong class="slate-bold">.wav</strong> format.</p><p class="slate-p" placeholder="Type / for widgets">This versatile API extends its utility across various applications, serving as a foundational tool for <a href="https://studio.fourie.ai/" target="_blank">Fourie&#x27;s </a><a href="https://app.theneo.io/fourie/api-docs/text-to-speech-tts" target="_blank">Text-to-Speech (TTS),</a> <a href="https://app.theneo.io/fourie/api-docs/speech-to-text-stt" target="_blank">Speech-to-Text (STT)</a>, <a href="https://app.theneo.io/fourie/api-docs/gender-detection" target="_blank">Gender Detection</a>, <a href="https://app.theneo.io/fourie/api-docs/emotion-recognition/speech-emotion-recognition-ser" target="_blank">Speech Emotion Detection (SER)</a> APIs. Whether preparing audio data for analysis, converting formats for different applications, or integrating with other Fourie services, this API provides a central hub for seamless audio file conversion and supports a broad spectrum of audio processing functionalities.</p><p class="slate-p" placeholder="Type / for widgets"></p>

endpoint, seamlessly transforms audio files with flexibility in input formats, including 

 for local uploads. The converted audio file is delivered in the user's choice of either 

This versatile API extends its utility across various applications, serving as a foundational tool for 

 APIs. Whether preparing audio data for analysis, converting formats for different applications, or integrating with other Fourie services, this API provides a central hub for seamless audio file conversion and supports a broad spectrum of audio processing functionalities.

The URL of the audio file that needs to be converted.

The desired file extension for the converted audio file. Acceptable extensions include mp3 and wav

target_extension

The audio file that needs to be converted. This parameter should be provided as the body of the POST request.

Sections