audio: add items to AudioResponseFormat enum

[romazu]

Added "text" and "verbose_json" output formats.

See reference:
https://platform.openai.com/docs/api-reference/audio/create

[codecov]

Codecov Report

Merging #382 (2f9c083) into master (0bd14f9) will not change coverage.
The diff coverage is 100.00%.

@@           Coverage Diff           @@
##           master     #382   +/-   ##
=======================================
  Coverage   95.22%   95.22%           
=======================================
  Files          17       17           
  Lines         670      670           
=======================================
  Hits          638      638           
  Misses         22       22           
  Partials       10       10           

Impacted Files	Coverage Δ
audio.go	88.31% <100.00%> (ø)

[vvatanabe]

@romazu What format is verbose_json? If it is json, you may need to add it to the conditions of the function below.

// HasJSONResponse returns true if the response format is JSON.
func (r AudioRequest) HasJSONResponse() bool {
	return r.Format == "" || r.Format == AudioResponseFormatJSON
}

Refs:
https://github.com/sashabaranov/go-openai/blob/master/audio.go#L97-L100

[romazu]

Yes, you are right, it's a json in the following format:

{
  "task": "transcribe",
  "language": "english",
  "duration": 10.0,
  "segments": [
    {
      "id": 0,
      "seek": 0,
      "start": 0.0,
      "end": 10.16,
      "text": " Chapter 1 Looming",
      "tokens": [
        50364,
        18874,
        502,
        6130,
        10539,
        50872
      ],
      "temperature": 0.0,
      "avg_logprob": -0.6817335401262555,
      "compression_ratio": 0.68,
      "no_speech_prob": 0.01032273843884468,
      "transient": false
    }
  ],
  "text": "Chapter 1 Looming"
}

I also expanded AudioResponse struct to accommodate for this.

[sashabaranov]

Thank you for the PR! 🙌🏻