Text-to-Speech Options
Model Configuration Options
| Option | Type | Default | Description |
|---|---|---|---|
| quality | string | 'medium' | Model quality preset |
| onProgress | function | - | Callback for loading progress updates |
| onComplete | function | - | Callback when loading completes |
| onError | function | - | Callback for error handling |
Speech Generation Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
| voice | string | 'female_a' | Voice selection |
| speed | number | 1.0 | Speech rate (0.5 - 2.0) |
| pitch | number | 1.0 | Voice pitch adjustment |
| language | string | 'en-US' | Language code |
| quality | string | 'medium' | Audio quality preset |
| format | string | 'wav' | Output format |
Example
const browserAI = new BrowserAI();
// Load TTS model with options
await browserAI.loadModel('speecht5-tts', {
onProgress: (progress) => {
console.log('Loading TTS model:', progress.progress + '%');
// "Loading TTS model: 75%"
}
});
// Generate speech with custom parameters
const audioBuffer = await browserAI.textToSpeech('Hello, how are you today?', {
voice: 'female_a',
speed: 1.2,
pitch: 1.0,
language: 'en-US',
quality: 'high',
format: 'wav'
});
console.log('Audio Status:', 'Generated successfully');
// "Audio Status: Generated successfully"