Lahajati AI - API Documentation

Introduction

Welcome to the Lahajati AI API documentation. Here you'll find all the information you need to integrate our advanced text-to-speech, speech-to-speech, and voice cloning technology into your applications.

Making Requests

Authentication

Lahajati AI API uses API keys to authenticate requests. You can obtain your API key from your account dashboard.

All API requests must include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Requests without authentication will fail with status code `401 Unauthorized`.

Error Handling (General)

Lahajati API uses standard HTTP status codes to indicate the success or failure of an API request. Generally: Codes in the `2xx` range indicate success. Codes in the `4xx` range indicate an error caused by the information provided by the client (e.g., a required parameter was missing, authentication failed, etc.). Codes in the `5xx` range indicate an error from our servers.

`400 Bad Request`: The server could not understand the request due to invalid syntax. Check the request body format or query parameters.
`401 Unauthorized`: Your API key is missing, invalid, or expired. Make sure to include a valid `Authorization: Bearer YOUR_API_KEY` header.
`403 Forbidden`: You don't have permission to access this resource or perform this operation (e.g., trying to modify a resource you don't own, or exceeding package limits).
`404 Not Found`: The requested resource was not found (e.g., `id_voice` doesn't exist).
`422 Unprocessable Entity`: The request was well-formed but could not be followed due to semantic errors (input validation failure). The response body will usually include an `errors` object with details of which fields failed validation.
`429 Too Many Requests`: You have exceeded the rate limit (RPM) allowed for your subscription package. Try again later. See the Rate Limits section.
`500 Internal Server Error` / `502 Bad Gateway` / `503 Service Unavailable`: An unexpected error occurred on the server side or the service is temporarily unavailable. If the problem persists, please contact support.

Rate Limits (RPM)

Lahajati AI API enforces limits on the number of requests that can be made per minute (RPM) based on your subscription package. These limits are designed to ensure stable and fair performance for all users. Exceeding these limits will result in a `429 Too Many Requests` error response.

Package	Requests Per Minute (RPM)
Starter Package	100
Content Creator Package	250
Premium Package	400
Business Package	500

Important Note: To request higher rpm limits for the business package, please contact support at: support@lahajati.ai.

Concurrent Request Limits

In addition to RPM limits, there are restrictions on the number of concurrent requests your account can run at the same time. This helps maintain system stability.

Package	Maximum Concurrent Requests
Starter Package	5
Content Creator Package	10
Premium Package	15
Business Package	20

Important Note: To request higher concurrency limits for the business package, please contact support at: support@lahajati.ai.

Voice Cloning Best Practices

To get the best results when using the voice cloning feature, it's essential to provide high-quality audio samples. Here are guidelines and recommendations to help you prepare your audio files:

Audio Quality Guidelines

Single speaker only: Ensure the recording clearly contains one person's voice (no other voices or background music).
Consistent performance: Maintain consistent volume, tone, and emotion levels throughout the recording as much as possible.
Natural pauses: Include short, natural pauses between sentences (0.5 seconds recommended).
Quiet environment: Record in a place free from background noise and echo as much as possible.
Professional quality (ideal): If possible, use professional recording equipment (good microphone) and in an acoustically treated environment (reduced room echo).

Ideal Audio Sample Characteristics

Recommended duration: For the best quality and performance variety (such as the ability to express different emotions), provide an audio sample longer than 60 seconds.
For consistent performance: If you're targeting consistent, specific performance (like news reading), a sample between 30-50 seconds with clear voice and consistent performance may be sufficient.
Clarity and purity: The audio sample should be completely free from noise and distortion (avoid clipping or distortion). Clear, clean audio is key.
Smart training: Our AI system will analyze and train itself on the voice's accent, tone, and performance style (whether happy, enthusiastic, formal, etc.) from the provided sample.

Supported File Formats

We accept a variety of audio file formats (as specified in the `audio_file` parameter for the create cloned voice endpoint).

Recommendation: For a good balance between quality and file size, we recommend using MP3 format with a bit rate of 192kbps or higher. Uncompressed formats (like WAV) may not provide noticeable benefit compared to increased file size and processing time.

Text To Speech

These endpoints provide precise and advanced control over the speech generation process. You can specify dialect and performance style separately or provide custom text prompts to get exactly the audio output you need.

GETGET Get Absolute Control Voices

https://lahajati.ai/api/v1/voices-absolute-control

Retrieves a list of voices available specifically for use with the "Generate Speech with Absolute Control" endpoint.

Query Parameters

Optional parameters for filtering, sorting, and paginating results.

Parameter	Type	Required	Description
`page`	integer	No (default 1)	The page number of results to retrieve.
`per_page`	integer	No (default 15, max 100)	Number of voices to return per page.
`gender`	string	No	Filter by gender. Allowed values: `1` (male), `2` (female), `3` (children).
`voice_name`	string (text)	No	Filter by voice name

Successful Response (200 OK)

Returns a paginated list of compatible voice objects.

GETGET Get Performance Styles

https://lahajati.ai/api/v1/performance-absolute-control

Retrieves a list of available performance styles (such as dramatic, news, advertising) that can be used to guide the speech generation model.

Query Parameters

Parameter	Type	Required	Description
`page`	integer	No (default 1)	The page number of results to retrieve.
`per_page`	integer	No (default 15, max 100)	Number of voices to return per page.
`performance_name`	string (text)	No	Filter by performance name

Successful Response (200 OK)

Returns a paginated list of performance style objects.

GETGET Get Dialects

https://lahajati.ai/api/v1/dialect-absolute-control

Retrieves a list of available dialects (such as Egyptian, Saudi Najdi) that can be used to guide the speech generation model.

Query Parameters

Parameter	Type	Required	Description
`page`	integer	No (default 1)	The page number of results to retrieve.
`per_page`	integer	No (default 15, max 100)	Number of voices to return per page.
`dialect_name`	string (text)	No	Filter by dialect name

Successful Response (200 OK)

Returns a paginated list of dialect objects.

POSTPOST Generate Speech with Absolute Control

https://lahajati.ai/api/v1/text-to-speech-absolute-control

Generates speech from text using a specified voice and precise performance control via two modes: structured mode (using performance and dialect IDs) or custom prompt mode.

Understanding the `input_mode` Parameter

This parameter is the key control for this endpoint. It has two modes:

Mode `0` (Structured): In this mode, you pass `performance_id` and/or `dialect_id` (optional). The system will generate the appropriate AI prompt based on your choices. This is the recommended option for most use cases.
Mode `1` (Custom): In this mode, `performance_id` and `dialect_id` are ignored. Instead, you pass a detailed free-text prompt in `custom_prompt_text`, giving you complete control. Example: "Speak slowly and calmly, with pauses between sentences, as if you're telling a children's story."

Request Body Parameters (JSON)

Parameter	Type	Required	Description
`text`	string	Yes	The text to be converted to speech.
`id_voice`	string (ID)	Yes	GET Get Absolute Control Voices: The unique identifier of the desired voice performer. Can be obtained via the Get Voices endpoint.
`input_mode`	string ("0" or "1")	Yes	Specifies the control mode. `0` for structured mode (using IDs), `1` for custom prompt mode.
`performance_id`	string (ID)	No (required if `input_mode` is `0`)	Performance style identifier. Obtained from the Get Performance Styles endpoint.
`dialect_id`	string (ID)	No (required if `input_mode` is `0`)	Dialect identifier. Obtained from the Get Dialects endpoint.
`custom_prompt_text`	string	No (required if `input_mode` is `1`)	A detailed custom text prompt describing the desired performance.
`temperature`	numeric	Value between 0.1 - 2	A setting that controls how creative and varied the output voice is; lower values make it more consistent, higher values increase its variety

Successful Response

On success (`200 OK`), the response body will contain raw audio data. The `Content-Type` header will be `audio/mpeg`.

Error Responses

In addition to the general errors, you may encounter the following errors specific to this endpoint:

401 You don't have the permission or package required to use this voice.
401 Your points balance is insufficient to complete the voice generation operation.
404 The specified `id_voice` does not exist.
422 Input validation failed. Make sure the required parameters for each `input_mode` are present.

POSTPOST Convert Speech with Absolute Control

https://lahajati.ai/api/v1/speech-to-speech-absolute-control

Converts an audio file to speech with another specified voice with advanced control over quality and performance parameters.

Important Note: Requests to this endpoint must be sent using `multipart/form-data` due to audio file upload.

Request Body Parameters (JSON)

Parameter	Type	Required	Description
`audio_file`	file (audio file)	Yes	The audio file to be converted. Supported types: `mp3, wav, aac, ogg`. Maximum size: 50 MB (20 minutes).
`id_voice`	string (ID)	Yes	The unique identifier of the desired voice performer. Can be obtained via the <a href="#get-voices">Get Voices</a> endpoint.
`professional_quality`	boolean	No (default `0`)	Set to `1` to enable enhanced processing for professional-quality audio output.
`stability`	numeric	No (default `50`)	Controls the stability of the output voice. Range: `0` to `100`.
`similarity_boost`	numeric	No (default `95`)	Enhances similarity to the target voice. Range: `0` to `100`.
`style`	numeric	No (default `0`)	Affects the style and strength of performance. Range: `0` to `100`.

Successful Response

On success (`200 OK`), the response body will contain raw audio data. The `Content-Type` header will be `audio/mpeg`.

Error Responses

In addition to the general errors, you may encounter the following errors specific to this endpoint:

400 Invalid request, usually due to missing `audio_file` or incorrect `Content-Type`.
401 You don't have the permission or package required to use this voice.
402 Insufficient points balance to perform the conversion operation.
404 The specified `id_voice` does not exist.
422 Input validation failed. Make sure the required parameters for each `input_mode` are present.

Large Language Model (LLM)

These endpoints provide AI conversational and text processing capabilities in Arabic with support for customization and performance control.

POSTPOST Chat Completions

https://lahajati.ai/api/v1/chat/completions

Generates intelligent responses to text messages using large language models specialized for Arabic with advanced customization capabilities.

Request Body Parameters (JSON)

Parameter	Type	Required	Description
`message`	string	Yes	The text or question to be sent to the AI model.
`custom_prompt_message`	string	No	Additional instructions to customize the model's behavior and response style.
`temperature`	numeric	No (default `1.0`)	Controls the creativity and variability of the response. Range: `0.1` to `2.0`.
`model`	string (model)	No (default `lahajati_llm_basic`)	The model to use. Allowed values: `lahajati_llm_basic`, `lahajati_llm_pro`.

Successful Response (200 OK)

On success, the model's response is returned in the `message` field.

Error Responses

In addition to the general errors, you may encounter the following errors specific to this endpoint:

401 You do not have a subscription package to use this feature. Subscribe to use the feature.
401 Your points balance is insufficient to complete the voice generation operation.
422 Input validation failed. Make sure the required parameters for each `input_mode` are present.
500 The AI model failed to execute your request after several attempts.

Voice Cloning

These endpoints provide advanced voice cloning capabilities for creating, managing, and deleting custom voices.

POSTPOST Create Cloned Voice

https://lahajati.ai/api/v1/voices/cloned

Allows creating a new cloned voice by uploading an audio file for training and providing necessary metadata. The cloned voice will be available for use in text-to-speech after processing is complete.

Important Note: Requests to this endpoint must be sent using `multipart/form-data`.

See the Voice Cloning Best Practices section for optimal results.

Request Parameters (Form Data)

Parameter	Type	Required	Description
`voice_name`	string	Yes	The name to be given to the cloned voice. (Maximum: 25 characters).
`gender`	integer	Yes	Voice gender. Allowed values: `1` (male), `2` (female), `3` (child).
`model`	string	Yes	The cloning model to use. Allowed values: `lahajati-classic`, `lahajati-neural`, `lahajati-adaptive`.
`audio_file`	file (audio file)	Yes	A single audio file for voice cloning training. Supported types: `mp3, wav, aac, ogg, flac, m4a`. Maximum size: 50 MB. (Good quality and clarity without background noise gives the best results).
`enhance_audio`	boolean	No (default `false`)	Set to `true` to enhance the quality of the training audio file before sending it to the cloning model (may increase processing time).
`voice_tags`	string	No	Optional keywords or classifications for the cloned voice, separated by commas (example: "calm, formal"). (Maximum: 255 characters).

Successful Response (201 Created)

On successful creation, details of the created cloned voice are returned. The voice may take some time to become fully active.

Error Responses (Create Cloned Voice)

In addition to the general errors, you may encounter the following errors specific to this endpoint:

403 Maximum allowed number of cloned voices has been reached.
422 Input validation failed (e.g., missing name, invalid file type, file too large).
500 Error while contacting external voice cloning service or failed to process the request there.

POSTPUT Update Cloned Voice

https://lahajati.ai/api/v1/voices/cloned/{id_voice}

Allows updating metadata of an existing cloned voice (such as name, gender, image, tags). The original training audio sample cannot be modified.

Important Note: Note: Use `multipart/form-data` only if you are uploading a new `voice_image` file. Otherwise, data can be sent as `application/x-www-form-urlencoded` or `application/json`. If using `multipart/form-data`, do not set the `Content-Type` header manually in JavaScript or similar libraries.

Path Parameter

Parameter	Type	Required	Description
`{id_voice}`	string (ID)	Yes	The unique identifier of the cloned voice to be updated (starting with `lvc_`). Passed as part of the URL path.

Optional Request Parameters (Form Data / JSON)

All parameters in the request body are optional. Send only those you want to update.

Parameter	Type	Required	Description
`voice_name`	string	No	The name to be given to the cloned voice. (Maximum: 25 characters).
`gender`	integer	No	Voice gender. Allowed values: `1` (male), `2` (female), `3` (child).

Successful Response (200 OK)

On successful update, details of the updated cloned voice are returned.

Error Responses (Update Cloned Voice)

404 Cloned voice not found, or you don't have permission to update it.
422 Input validation failed (e.g., missing name, invalid file type, file too large).

DELETEDELETE Delete Cloned Voice

https://lahajati.ai/api/v1/voices/cloned/{id_voice}

Permanently deletes a cloned voice from the system and from any associated external services.

Path Parameter

Parameter	Type	Required	Description
`{id_voice}`	string (ID)	Yes	The unique identifier of the cloned voice to be updated (starting with `lvc_`). Passed as part of the URL path.

Successful Response (200 OK)

Confirmation message of successful deletion.

Error Responses (Delete Cloned Voice)

404 Cloned voice not found, or you don't have permission to update it.
500 Failed to delete cloned voice (may be due to external service issue).

Generate Speech with Absolute Control

Example of Structured Mode (`input_mode: "0"`)

curl -X POST "https://lahajati.ai/api/v1/text-to-speech-absolute-control" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-H "Accept: audio/mpeg" \
-d '{
  "text": "هذا اختبار للوضع المنظم.",
  "id_voice": "ac_voice_xyz789",
  "input_mode": "0",
  "performance_id": "perf_1",
  "dialect_id": "dialect_10"
}' \
--output structured_output.mp3

Example of Custom Prompt Mode (`input_mode: "1"`)

curl -X POST "https://lahajati.ai/api/v1/text-to-speech-absolute-control" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-H "Accept: audio/mpeg" \
-d '{
  "text": "هذا اختبار للتوجيه المخصص.",
  "id_voice": "ac_voice_xyz789",
  "input_mode": "1",
  "custom_prompt_text": "اقرأ النص التالي بصوت عالٍ وواضح، كأنك تقدم نشرة إخبارية عاجلة."
}' \
--output custom_prompt_output.mp3

Example of Structured Mode (`input_mode: "0"`)

use Illuminate\Support\Facades\Http;
use Illuminate\Support\Facades\Storage;

$response = Http::withToken('YOUR_API_KEY')
    ->accept('audio/mpeg')
    ->post('https://lahajati.ai/api/v1/text-to-speech-absolute-control', [
        'text'           => 'هذا اختبار للوضع المنظم.',
        'id_voice'       => 'ac_voice_xyz789',
        'input_mode'     => '0',
        'performance_id' => 'perf_1',
        'dialect_id'     => 'dialect_10'
    ]);

if ($response->successful()) {
    Storage::disk('public')->put('structured_output.mp3', $response->body());
}

Example of Custom Prompt Mode (`input_mode: "1"`)

$response = Http::withToken('YOUR_API_KEY')
    ->accept('audio/mpeg')
    ->post('https://lahajati.ai/api/v1/text-to-speech-absolute-control', [
        'text'               => 'هذا اختبار للتوجيه المخصص.',
        'id_voice'           => 'ac_voice_xyz789',
        'input_mode'         => '1',
        'custom_prompt_text' => 'اقرأ النص التالي بصوت عالٍ وواضح، كأنك تقدم نشرة إخبارية عاجلة.'
    ]);

if ($response->successful()) {
    Storage::disk('public')->put('custom_prompt_output.mp3', $response->body());
}

Example of Structured Mode (`input_mode: "0"`)

const structuredData = {
    text: "هذا اختبار للوضع المنظم.",
    id_voice: "ac_voice_xyz789",
    input_mode: "0",
    performance_id: "perf_1",
    dialect_id: "dialect_10"
};

fetch('https://lahajati.ai/api/v1/text-to-speech-absolute-control', {
    method: 'POST',
    headers: {
        'Authorization': 'Bearer YOUR_API_KEY',
        'Content-Type': 'application/json',
        'Accept': 'audio/mpeg'
    },
    body: JSON.stringify(structuredData)
})
.then(response => response.blob())
.then(blob => console.log('Structured audio received!'))
.catch(error => console.error('Error:', error));

Example of Custom Prompt Mode (`input_mode: "1"`)

const customData = {
    text: "هذا اختبار للتوجيه المخصص.",
    id_voice: "ac_voice_xyz789",
    input_mode: "1",
    custom_prompt_text: "اقرأ النص التالي بصوت عالٍ وواضح، كأنك تقدم نشرة إخبارية عاجلة."
};

fetch('https://lahajati.ai/api/v1/text-to-speech-absolute-control', {
    method: 'POST',
    headers: {
        'Authorization': 'Bearer YOUR_API_KEY',
        'Content-Type': 'application/json',
        'Accept': 'audio/mpeg'
    },
    body: JSON.stringify(customData)
})
.then(response => response.blob())
.then(blob => console.log('Custom prompt audio received!'))
.catch(error => console.error('Error:', error));

Example of Structured Mode (`input_mode: "0"`)

import requests

headers = {
    'Authorization': f'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
    'Accept': 'audio/mpeg'
}
structured_data = {
    "text": "هذا اختبار للوضع المنظم.",
    "id_voice": "ac_voice_xyz789",
    "input_mode": "0",
    "performance_id": "perf_1",
    "dialect_id": "dialect_10"
}
response = requests.post('https://lahajati.ai/api/v1/text-to-speech-absolute-control', headers=headers, json=structured_data)

if response.status_code == 200:
    with open('structured_output.mp3', 'wb') as f:
        f.write(response.content)
    print("Structured audio saved.")

Example of Custom Prompt Mode (`input_mode: "1"`)

custom_data = {
    "text": "هذا اختبار للتوجيه المخصص.",
    "id_voice": "ac_voice_xyz789",
    "input_mode": "1",
    "custom_prompt_text": "اقرأ النص التالي بصوت عالٍ وواضح، كأنك تقدم نشرة إخبارية عاجلة."
}
response = requests.post('https://lahajati.ai/api/v1/text-to-speech-absolute-control', headers=headers, json=custom_data)

if response.status_code == 200:
    with open('custom_prompt_output.mp3', 'wb') as f:
        f.write(response.content)
    print("Custom prompt audio saved.")

Response Examples

Successful Response (200 OK)

HTTP/1.1 200 OK
Content-Type: audio/mpeg
Content-Length: 98765

[... raw binary audio data ...]

Input validation failed. Make sure the required parameters for each `input_mode` are present.

{
    "success": false,
    "errors": {
        "input_mode": [
            "The input mode field is required."
        ],
        "custom_prompt_text": [
            "The custom prompt text field is required when input mode is 1."
        ]
    }
}

Convert Speech with Absolute Control

curl -X POST "https://lahajati.ai/api/v1/speech-to-speech-absolute-control" \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "audio_file=@/path/to/audio.mp3" \
-F "id_voice=voice_abc123" \ 
-F "stability=75" \
-F "similarity_boost=85" \
-F "style=25" \
--output converted_audio.mp3

use Illuminate\Support\Facades\Http;
use Illuminate\Http\File;

$response = Http::withToken('YOUR_API_KEY')
    ->attach('audio_file', file_get_contents('/path/to/audio.mp3'), 'audio.mp3')
    ->post('https://lahajati.ai/api/v1/speech-to-speech-absolute-control', [
        'id_voice' => 'voice_abc123', 
        'stability' => 75,
        'similarity_boost' => 85,
        'style' => 25
    ]);

if ($response->successful()) {
    file_put_contents('converted_audio.mp3', $response->body());
    echo "Audio converted successfully!";
}

const formData = new FormData();
formData.append('audio_file', audioFile); // File from input
formData.append('id_voice', 'voice_abc123'); 
formData.append('stability', '75');
formData.append('similarity_boost', '85');
formData.append('style', '25');

fetch('https://lahajati.ai/api/v1/speech-to-speech-absolute-control', {
    method: 'POST',
    headers: {
        'Authorization': 'Bearer YOUR_API_KEY'
    },
    body: formData
})
.then(response => response.blob())
.then(blob => {
    const url = URL.createObjectURL(blob);
    console.log('Converted audio available at:', url);
})
.catch(error => console.error('Error:', error));

import requests

headers = {
    'Authorization': 'Bearer YOUR_API_KEY'
}

files = {
    'audio_file': open('/path/to/audio.mp3', 'rb')
}

data = {
    'id_voice': 'voice_abc123', 
    'stability': '75',
    'similarity_boost': '85',
    'style': '25'
}

response = requests.post('https://lahajati.ai/api/v1/speech-to-speech-absolute-control', 
                        headers=headers, files=files, data=data)

if response.status_code == 200:
    with open('converted_audio.mp3', 'wb') as f:
        f.write(response.content)
    print("Audio converted successfully!")

files['audio_file'].close()

Response Examples

Successful Response (200 OK)

HTTP/1.1 200 OK
Content-Type: audio/mpeg
Content-Length: 156234

[... raw binary audio data ...]

Input validation failed. Make sure the required parameters for each `input_mode` are present.

{
    "success": false,
    "errors": {
        "audio_file": [
            "The audio file field is required."
        ],
        "stability": [
            "The stability must be between 0 and 100."
        ]
    }
}

Chat Completions

Basic Example

curl -X POST "https://lahajati.ai/api/v1/chat/completions" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "message": "ما هي أفضل طريقة لتعلم البرمجة؟",
  "model": "lahajati_llm_basic",
  "temperature": 1.0
}'

Example with Custom Prompt

curl -X POST "https://lahajati.ai/api/v1/chat/completions" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "message": "اشرح لي مفهوم الذكاء الاصطناعي",
  "custom_prompt_message": "أنت خبير في التقنية، أجب بأسلوب تعليمي مبسط مناسب للمبتدئين",
  "model": "lahajati_llm_pro",
  "temperature": 0.7
}'

Basic Example

use Illuminate\Support\Facades\Http;

$response = Http::withToken('YOUR_API_KEY')
    ->post('https://lahajati.ai/api/v1/chat/completions', [
        'message' => 'ما هي أفضل طريقة لتعلم البرمجة؟',
        'model' => 'lahajati_llm_basic',
        'temperature' => 1.0
    ]);

if ($response->successful()) {
    $data = $response->json();
    echo $data['message'];
}

Example with Custom Prompt

$response = Http::withToken('YOUR_API_KEY')
    ->post('https://lahajati.ai/api/v1/chat/completions', [
        'message' => 'اشرح لي مفهوم الذكاء الاصطناعي',
        'custom_prompt_message' => 'أنت خبير في التقنية، أجب بأسلوب تعليمي مبسط مناسب للمبتدئين',
        'model' => 'lahajati_llm_pro',
        'temperature' => 0.7
    ]);

if ($response->successful()) {
    $data = $response->json();
    echo $data['message'];
}

Basic Example

const basicData = {
    message: "ما هي أفضل طريقة لتعلم البرمجة؟",
    model: "lahajati_llm_basic",
    temperature: 1.0
};

fetch('https://lahajati.ai/api/v1/chat/completions', {
    method: 'POST',
    headers: {
        'Authorization': 'Bearer YOUR_API_KEY',
        'Content-Type': 'application/json'
    },
    body: JSON.stringify(basicData)
})
.then(response => response.json())
.then(data => {
    if (data.status) {
        console.log('Response:', data.message);
    }
})
.catch(error => console.error('Error:', error));

Example with Custom Prompt

const customData = {
    message: "اشرح لي مفهوم الذكاء الاصطناعي",
    custom_prompt_message: "أنت خبير في التقنية، أجب بأسلوب تعليمي مبسط مناسب للمبتدئين",
    model: "lahajati_llm_pro",
    temperature: 0.7
};

fetch('https://lahajati.ai/api/v1/chat/completions', {
    method: 'POST',
    headers: {
        'Authorization': 'Bearer YOUR_API_KEY',
        'Content-Type': 'application/json'
    },
    body: JSON.stringify(customData)
})
.then(response => response.json())
.then(data => {
    if (data.status) {
        console.log('Response:', data.message);
    }
})
.catch(error => console.error('Error:', error));

Basic Example

import requests

headers = {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
}

basic_data = {
    "message": "ما هي أفضل طريقة لتعلم البرمجة؟",
    "model": "lahajati_llm_basic",
    "temperature": 1.0
}

response = requests.post('https://lahajati.ai/api/v1/chat/completions', 
                        headers=headers, json=basic_data)

if response.status_code == 200:
    data = response.json()
    if data['status']:
        print("Response:", data['message'])

Example with Custom Prompt

custom_data = {
    "message": "اشرح لي مفهوم الذكاء الاصطناعي",
    "custom_prompt_message": "أنت خبير في التقنية، أجب بأسلوب تعليمي مبسط مناسب للمبتدئين",
    "model": "lahajati_llm_pro",
    "temperature": 0.7
}

response = requests.post('https://lahajati.ai/api/v1/chat/completions', 
                        headers=headers, json=custom_data)

if response.status_code == 200:
    data = response.json()
    if data['status']:
        print("Response:", data['message'])

Response Examples

Successful Response (200 OK) (200 OK)

{
    "status": true,
    "message": "تعلم البرمجة يتطلب الصبر والممارسة المستمرة. أنصحك بالبدء بلغة برمجة مناسبة للمبتدئين مثل Python، ثم التدرب على مشاريع صغيرة وزيادة التعقيد تدريجياً. المصادر التعليمية المجانية متوفرة بكثرة على الإنترنت."
}

You do not have a subscription package to use this feature. Subscribe to use the feature.

{
    "success": false,
    "message": "You do not have a subscription package to use this feature. Subscribe to use the feature."
}

Create Cloned Voice

curl -X POST "https://lahajati.ai/api/v1/voices/cloned" \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "voice_name=My Cloned Voice" \
-F "gender=1" \
-F "model=lahajati-neural" \
-F "audio_file=@/path/to/voice_sample.mp3" \
-F "enhance_audio=true" \
-F "voice_tags=professional,calm"

use Illuminate\Support\Facades\Http;

$response = Http::withToken('YOUR_API_KEY')
    ->attach('audio_file', file_get_contents('/path/to/voice_sample.mp3'), 'voice_sample.mp3')
    ->post('https://lahajati.ai/api/v1/voices/cloned', [
        'voice_name' => 'My Cloned Voice',
        'gender' => 1,
        'model' => 'lahajati-neural',
        'enhance_audio' => true,
        'voice_tags' => 'professional,calm'
    ]);

if ($response->successful()) {
    $data = $response->json();
    echo "Voice cloned successfully: " . $data['voice']['id_voice'];
}

const formData = new FormData();
formData.append('voice_name', 'My Cloned Voice');
formData.append('gender', '1');
formData.append('model', 'lahajati-neural');
formData.append('audio_file', audioFile); // File from input
formData.append('enhance_audio', 'true');
formData.append('voice_tags', 'professional,calm');

fetch('https://lahajati.ai/api/v1/voices/cloned', {
    method: 'POST',
    headers: {
        'Authorization': 'Bearer YOUR_API_KEY'
    },
    body: formData
})
.then(response => response.json())
.then(data => {
    if (data.success) {
        console.log('Voice cloned successfully:', data.voice.id_voice);
    }
})
.catch(error => console.error('Error:', error));

import requests

headers = {
    'Authorization': 'Bearer YOUR_API_KEY'
}

files = {
    'audio_file': open('/path/to/voice_sample.mp3', 'rb')
}

data = {
    'voice_name': 'My Cloned Voice',
    'gender': '1',
    'model': 'lahajati-neural',
    'enhance_audio': 'true',
    'voice_tags': 'professional,calm'
}

response = requests.post('https://lahajati.ai/api/v1/voices/cloned', 
                        headers=headers, files=files, data=data)

if response.status_code == 201:
    data = response.json()
    print(f"Voice cloned successfully: {data['voice']['id_voice']}")

files['audio_file'].close()

Response Examples

Successful Response (201 Created) (201 Created)

{
    "success": true,
    "voice": {
        "id_voice": "lvc_abc123def456ghi789",
        "name": "My Cloned Voice",
        "gender": "male",
        "tags": "professional,calm",
        "created_at": "2024-01-15T10:30:00.000000Z"
    }
}

Update Cloned Voice

curl -X POST "https://lahajati.ai/api/v1/voices/cloned/{id_voice}" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "voice_name": "Updated Voice Name",
    "gender": 2
}'

Response Examples

{
    "success": true,
    "voice": {
        "id_voice": "lvc_abc123def456ghi789",
        "name": "Updated Voice Name", 
        "gender": "female",
        "tags": "professional,calm",
        "updated_at": "2024-01-15T11:30:00.000000Z"
    }
}

Delete Cloned Voice

curl -X DELETE "https://lahajati.ai/api/v1/voices/cloned/{id_voice}" \
-H "Authorization: Bearer YOUR_API_KEY"

Response Examples

{
    "success": true,
    "message": "Cloned voice deleted successfully."
}

Get Absolute Control Voices

curl -X GET "https://lahajati.ai/api/v1/voices-absolute-control" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Accept: application/json"

Response Examples

{
  "success": true,
  "data": [
    {
      "id_voice": "ac_voice_xyz789",
      "display_name": "صوت تحكم مطلق - أحمد",
      "gender": "male",
      "is_cloned": false,
      "average_rating": null
    }
  ],
  "meta": { /* ... pagination info ... */ }
}

Get Performance Styles

curl -X GET "https://lahajati.ai/api/v1/performance-absolute-control" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Accept: application/json"

Response Examples

{
  "success": true,
  "data": [
    {
      "performance_id": "perf_1",
      "display_name": "أداء درامي"
    },
    {
      "performance_id": "perf_2",
      "display_name": "أداء إخباري"
    }
  ],
  "meta": { /* ... pagination info ... */ }
}

Get Dialects

curl -X GET "https://lahajati.ai/api/v1/dialect-absolute-control" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Accept: application/json"

Response Examples

{
  "success": true,
  "data": [
    {
      "dialect_id": "dialect_10",
      "display_name": "اللهجة المصرية"
    },
    {
      "dialect_id": "dialect_12",
      "display_name": "اللهجة السعودية (نجدية)"
    }
  ],
  "meta": { /* ... pagination info ... */ }
}

Introduction

Authentication

Error Handling (General)

Rate Limits (RPM)

Concurrent Request Limits

Voice Cloning Best Practices

Audio Quality Guidelines

Ideal Audio Sample Characteristics

Supported File Formats

Text To Speech

GETGET Get Absolute Control Voices

Query Parameters

Successful Response (200 OK)

GETGET Get Performance Styles

Query Parameters

Successful Response (200 OK)

GETGET Get Dialects

Query Parameters

Successful Response (200 OK)

POSTPOST Generate Speech with Absolute Control

Understanding the `input_mode` Parameter

Request Body Parameters (JSON)

Successful Response

Error Responses

POSTPOST Convert Speech with Absolute Control

Request Body Parameters (JSON)

Successful Response

Error Responses

Large Language Model (LLM)

POSTPOST Chat Completions

Available Models

Request Body Parameters (JSON)

Successful Response (200 OK)

Error Responses

Voice Cloning

POSTPOST Create Cloned Voice

Request Parameters (Form Data)

Successful Response (201 Created)

Error Responses (Create Cloned Voice)

POSTPUT Update Cloned Voice

Path Parameter

Optional Request Parameters (Form Data / JSON)

Successful Response (200 OK)

Error Responses (Update Cloned Voice)

DELETEDELETE Delete Cloned Voice

Path Parameter

Successful Response (200 OK)

Error Responses (Delete Cloned Voice)