refactor: audio relay

dto/audio.go

@@ -1,13 +1,34 @@
 package dto
 
-type TextToSpeechRequest struct {
-	Model          string  `json:"model" binding:"required"`
-	Input          string  `json:"input" binding:"required"`
-	Voice          string  `json:"voice" binding:"required"`
-	Speed          float64 `json:"speed"`
-	ResponseFormat string  `json:"response_format"`
+type AudioRequest struct {
+	Model          string  `json:"model"`
+	Input          string  `json:"input"`
+	Voice          string  `json:"voice"`
+	Speed          float64 `json:"speed,omitempty"`
+	ResponseFormat string  `json:"response_format,omitempty"`
 }
 
 type AudioResponse struct {
 	Text string `json:"text"`
 }
+
+type WhisperVerboseJSONResponse struct {
+	Task     string    `json:"task,omitempty"`
+	Language string    `json:"language,omitempty"`
+	Duration float64   `json:"duration,omitempty"`
+	Text     string    `json:"text,omitempty"`
+	Segments []Segment `json:"segments,omitempty"`
+}
+
+type Segment struct {
+	Id               int     `json:"id"`
+	Seek             int     `json:"seek"`
+	Start            float64 `json:"start"`
+	End              float64 `json:"end"`
+	Text             string  `json:"text"`
+	Tokens           []int   `json:"tokens"`
+	Temperature      float64 `json:"temperature"`
+	AvgLogprob       float64 `json:"avg_logprob"`
+	CompressionRatio float64 `json:"compression_ratio"`
+	NoSpeechProb     float64 `json:"no_speech_prob"`
+}