Workers AI Whisper documentation needs clarification on acceptable audio formats

[dharmab]

Existing documentation URL(s)

https://developers.cloudflare.com/workers-ai/models/whisper/#API%20Schemas

What changes are you suggesting?

• One of the examples uses an MP3 file as binary data. No details are included on supported codecs, bitrates, or file sizes. Furthermore, because the example file is not included, the user cannot reproduce this example.
• The API schema refers to "An array of integers that represent the audio data constrained to 8-bit unsigned integer values". This sounds like 8-bit linear PCM, but it's unclear. It's also unclear if the audio needs to be mono or if stereo is supported. Or is this an encoded format, like in the other MP3 example? There is no example for this schema, so the user cannot reproduce this example.

Additional information

No response