PHP code example of b7s / fluentvox

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

    

b7s / fluentvox example snippets

$result = FluentVox::make()
    ->text('Hello, world! This is FluentVox speaking.')
    ->generate();

return [
    'python_path' => '/path/to/venv/bin/python',  // Linux/macOS
    // or
    'python_path' => 'C:\\path\\to\\venv\\Scripts\\python.exe',  // Windows
    // ...
];

use B7s\FluentVox\FluentVox;

$result = FluentVox::make()
    ->text('Hello, world! This is FluentVox speaking.')
    ->generate();

echo "Audio saved to: " . $result->outputPath;
echo "Duration: " . $result->getFormattedDuration();

$result = FluentVox::make()
    ->text('Hello, I sound just like the reference!')
    ->voiceFrom('/path/to/reference.wav')
    ->generate();

use B7s\FluentVox\Enums\Language;

$result = FluentVox::make()
    ->multilingual()
    ->text('Bonjour le monde!')
    ->language(Language::French)
    ->generate();

$result = FluentVox::make()
    ->text('Wow, this is absolutely amazing!')
    ->expressive()
    ->slow()
    ->generate();

// Generate audio at CD quality (44.1kHz)
$result = FluentVox::make()
    ->text('High quality audio output')
    ->sampleRate(44100)
    ->generate();

// Professional audio (48kHz)
$result = FluentVox::make()
    ->text('Professional quality')
    ->sampleRate(48000)
    ->generate();

// Standard English model (500M params)
FluentVox::make()->standard()  // Best for general use with emotion controls

// Turbo model - faster, with paralinguistic tags (350M params)
FluentVox::make()->turbo()  // Fastest, supports [laugh], [cough] tags

// Multilingual model - 23+ languages (500M params)
FluentVox::make()->multilingual()  // For non-English languages

// Clone voice from reference audio
->voiceFrom('/path/to/reference.wav')  // Use this person's voice

// Alias
->cloneVoice('/path/to/reference.wav')

// Use default voice
->defaultVoice()  // Use model's built-in voice

use B7s\FluentVox\Enums\Language;

->language(Language::French)
->language(Language::Japanese)
->language(Language::Portuguese)

// Shortcuts for common languages
->english()
->french()
->spanish()
->german()
->portuguese()
->japanese()
->chinese()

// Exaggeration (0.25-2.0, neutral=0.5)
->exaggeration(0.7)

// Presets
->neutral()      // 0.5 - Balanced, natural expression
->expressive()   // 0.7 - More animated and emotional
->dramatic()     // 1.0 - Highly expressive, theatrical
->subtle()       // 0.3 - Understated, calm delivery

// CFG weight (0.2-1.0, default=0.5)
->cfgWeight(0.4)
->pace(0.4)  // alias

// Presets
->slow()        // 0.3 - Deliberate, measured pacing
->normalPace()  // 0.5 - Natural speaking speed
->fast()        // 0.7 - Quick, energetic delivery

// Temperature (0.05-5.0, default=0.8)
->temperature(0.6)

// Presets
->deterministic()  // 0.3 - Consistent, predictable output
->creative()       // 1.2 - More varied, spontaneous speech

// Seed for reproducibility (0 = random)
->seed(42)  // Use same seed to get identical results

// Trim silence from reference audio
->trimSilence()  // Remove silence/noise from voice sample

// Keep silence (default)
->keepSilence()  // Use reference audio as-is

// Auto-detect best device (default)
->autoDevice()  // Automatically selects CUDA > MPS > CPU

// Force CUDA (NVIDIA GPU)
->cuda()  // Use NVIDIA GPU (Linux/Windows)

// Force MPS (Apple Silicon)
->mps()  // Use Apple Metal (M1/M2/M3 Macs)

// Force CPU
->cpu()  // Use CPU only (slower but always available)

// Set output path
->saveTo('/path/to/output.wav')  // Save to specific location
->output('/path/to/output.wav')  // alias

// Set sample rate (Hz)
->sampleRate(44100)  // Resample to 44.1kHz (CD quality)
->sampleRate(48000)  // Resample to 48kHz (professional audio)
->nativeSampleRate()  // Use model's native rate (24kHz, default)

// Set timeout (seconds)
->timeout(600)  // Maximum time to wait for generation

// Enable verbose output
->verbose()  // Show detailed generation logs

// Progress callback
->onProgress(function (string $output, bool $isError) {
    echo $output;  // Monitor generation progress in real-time
})

// Narration: clear, neutral, consistent
->forNarration()  // Audiobook narration, documentation

// Dialogue: expressive, varied
->forDialogue()  // Character voices, conversations

// Voice agents: fast, clear, low latency
->forVoiceAgent()  // Chatbots, virtual assistants

// Audiobooks: dramatic, varied pacing
->forAudiobook()  // Long-form storytelling

// Generate and save to file
$result = FluentVox::make()
    ->text('Hello!')
    ->generate();  // Returns GenerationResult object

// Generate and get raw audio data
$audioData = FluentVox::make()
    ->text('Hello!')
    ->generateRaw();  // Returns raw WAV bytes as string

// Universal method - format detected from extension
$result = FluentVox::make()
    ->text('Hello!')
    ->convertTo('/path/to/output.mp3');  // Auto-detects MP3

$result = FluentVox::make()
    ->text('Hello!')
    ->convertTo('/path/to/output.m4a', ['bitrate' => 128]);

// Specific format methods
$result = FluentVox::make()
    ->text('Hello!')
    ->convertToMp3('/path/to/output.mp3', bitrate: 192);

$result = FluentVox::make()
    ->text('Hello!')
    ->convertToM4a('/path/to/output.m4a', bitrate: 128);

$result = FluentVox::make()
    ->text('Hello!')
    ->convertToOgg('/path/to/output.ogg', quality: 5);

$result = FluentVox::make()
    ->text('Hello!')
    ->convertToOpus('/path/to/output.opus', bitrate: 96);

$result = FluentVox::make()
    ->text('Hello!')
    ->convertToFlac('/path/to/output.flac');

// Convert and delete original WAV
$result = FluentVox::make()
    ->text('Hello!')
    ->convertTo('/path/to/output.mp3', deleteOriginal: true);

// Manual conversion of existing file
FluentVox::convertAudio(
    'input.wav',
    'output.mp3',
    'mp3',
    ['bitrate' => 320]
);

// Get audio file information
$info = FluentVox::getAudioInfo('audio.mp3');
// Returns: ['duration', 'sample_rate', 'channels', 'codec', 'bitrate']

$result = FluentVox::make()->text('Hello!')->generate();

$result->isSuccessful();           // bool - Check if generation succeeded
$result->getPath();                // string - Output file path
$result->getDuration();            // float - Duration in seconds
$result->getFormattedDuration();   // string - "00:02.50" format
$result->sampleRate;               // int - 24000 Hz
$result->text;                     // string - Original input text
$result->error;                    // string|null - Error message if failed
$result->metadata;                 // array - Generation parameters used
$result->toArray();                // array - All data as array

// Check system ntVox::checkRequirements();  // Verify Python, PyTorch, etc.

// Install Chatterbox TTS
FluentVox::install(function ($output, $isError) {
    echo $output;  // Monitor installation progress
});

// List available models
$models = FluentVox::listModels();  // Get all models with download status

// Convert existing audio file
FluentVox::convertAudio('input.wav', 'output.mp3', 'mp3', ['bitrate' => 192]);

// Get audio file information
$info = FluentVox::getAudioInfo('audio.mp3');
// Returns: ['duration' => 5.2, 'sample_rate' => 44100, 'channels' => 2, ...]

return [
    // Python executable path (null = auto-detect)
    // FluentVox automatically detects venv, but you can specify manually:
    // 'python_path' => '/path/to/venv/bin/python',  // Linux/macOS
    // 'python_path' => 'C:\\path\\to\\venv\\Scripts\\python.exe',  // Windows
    'python_path' => null,

    // Directory where models will be stored
    'models_path' => null, // null = ~/.cache/huggingface/hub

    // Default model: 'chatterbox', 'chatterbox-turbo', 'chatterbox-multilingual'
    // This model will be used automatically by CLI commands and FluentVox instances
    'default_model' => 'chatterbox',

    // Default device: 'auto', 'cuda', 'mps', 'cpu'
    'device' => 'auto',

    // Default output directory
    'output_path' => null, // null = current working directory

    // Default audio format
    'audio_format' => 'wav',

    // Default sample rate (Hz)
    // null = use model's native rate (24000 Hz)
    // Common values: 16000 (telephony), 24000 (native), 44100 (CD), 48000 (professional)
    'sample_rate' => null,

    // Generation defaults
    'defaults' => [
        'exaggeration' => 0.5,
        'temperature' => 0.8,
        'cfg_weight' => 0.5,
        'seed' => 0,
    ],

    // Process timeout in seconds
    'timeout' => 300,

    // Enable verbose output
    'verbose' => false,
];