Audio Predictions
The audio
component provides methods for processing and analyzing audio files using VLM Run’s models.
Process Audio
import { VlmRun } from "vlmrun";
const client = new VlmRun({
apiKey: "your-api-key",
});
// Upload and process an audio file
const file = await client.files.upload({
filePath: "path/to/audio.mp3",
});
// Process audio using file ID
const response = await client.audio.generate({
fileId: file.id,
domain: "audio.transcription",
});
TypeScript Interfaces
interface FilePredictionParams extends PredictionGenerateParams {
batch?: boolean;
fileId?: string;
url?: string;
}
Error Handling
try {
const response = await client.audio.generate({
url: "invalid-url",
model: "vlm-1",
});
} catch (error) {
if (error instanceof ApiError) {
console.error("API Error:", error.message);
// Handle API-specific errors
} else {
console.error("File system error:", error);
// Handle local file system errors
}
}
Best Practices
-
Audio Formats
- Supported formats: MP3, WAV
- Ensure proper audio quality
- Consider file size limits
-
Performance
- Use URLs for remote audio files when possible
- Handle timeouts appropriately
- Consider audio length and complexity
-
Error Handling
- Validate audio files before processing
- Handle both API and file system errors
- Implement proper error recovery