Speech to Text API

Advanced speech-to-text conversion with fine-grained control over language models, confidence scores, and output format.

Usage

Provide audio input with optional parameters for language, model, punctuation, and output format.

Examples

• "Transcribe this audio with word-level timestamps"
• "Convert this speech to text with confidence scores"
• "Transcribe in Spanish with automatic punctuation"

Guidelines

• Specify the source language for better accuracy
• Word confidence scores help identify uncertain transcriptions
• Use streaming mode for real-time transcription needs
• Sample rate and encoding affect recognition quality
• Custom vocabulary can improve domain-specific accuracy