Speech-to-Text Tool
Domain: Tools & Function Calling
🎯 Motivation
A tool that converts audio to text. Lets the agent understand spoken input.
📋 Concrete Example
User sends a voice message. Agent calls: speech_to_text(audio_file) -> ‘What time is it in Tokyo?’ The agent processes the transcribed text and responds.
🔗 Analogy
A secretary taking dictation - the boss speaks, the secretary types it out. Speech-to-text tools let agents convert spoken words into text they can process.