fix: stt模型计费

relay/channel/openai/relay-openai.go

@@ -279,7 +279,6 @@ func OpenaiTTSHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 }
 
 func OpenaiSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, responseFormat string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
-	var audioResp dto.AudioResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
@@ -288,11 +287,6 @@ func OpenaiSTTHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
-	err = json.Unmarshal(responseBody, &audioResp)
-	if err != nil {
-		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
-	}
-
 	// Reset response body
 	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
 	// We shouldn't set the header before we parse the response body, because the parse part may fail.

relay/relay-audio.go

@@ -45,6 +45,10 @@ func getAndValidAudioRequest(c *gin.Context, info *relaycommon.RelayInfo) (*dto.
 		if audioRequest.Model == "" {
 			return nil, errors.New("model is required")
 		}
+		audioRequest.ResponseFormat = formData.Get("response_format")
+		if audioRequest.ResponseFormat == "" {
+			audioRequest.ResponseFormat = "json"
+		}
 	}
 	return audioRequest, nil
 }