Spoken prompts · Question 12 of 12
A developer sends a 3 MB WAV file as Base64 to a text model without audio capability and gets an error. What is the right solution?
1 answer is correct. Hard Created with AI
Show answer
Answer
- D Deploying an audio-capable model or transcribing the recording first
Explanation
Only models with audio input understand audio content. For a pure text model, the recording must first be converted to text via transcription. Splitting or changing other parameters doesn't add the missing capability.