Merge 7ed4bc29a0 into ae1cd29f94

relay/adaptor/openai/adaptor.go

@@ -32,6 +32,14 @@ func (a *Adaptor) GetRequestURL(meta *meta.Meta) (string, error) {
 			// https://{resource_name}.openai.azure.com/openai/deployments/dall-e-3/images/generations?api-version=2024-03-01-preview
 			fullRequestURL := fmt.Sprintf("%s/openai/deployments/%s/images/generations?api-version=%s", meta.BaseURL, meta.ActualModelName, meta.Config.APIVersion)
 			return fullRequestURL, nil
+		} else if meta.Mode == relaymode.AudioTranscription {
+			// https://learn.microsoft.com/en-us/azure/ai-services/openai/whisper-quickstart?tabs=command-line#rest-api
+			fullRequestURL := fmt.Sprintf("%s/openai/deployments/%s/audio/transcriptions?api-version=%s", meta.BaseURL, meta.ActualModelName, meta.Config.APIVersion)
+			return fullRequestURL, nil
+		} else if meta.Mode == relaymode.AudioSpeech {
+			// https://learn.microsoft.com/en-us/azure/ai-services/openai/text-to-speech-quickstart?tabs=command-line#rest-api
+			fullRequestURL := fmt.Sprintf("%s/openai/deployments/%s/audio/speech?api-version=%s", meta.BaseURL, meta.ActualModelName, meta.Config.APIVersion)
+			return fullRequestURL, nil
 		}
 
 		// https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line#rest-api
@@ -57,6 +65,9 @@ func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, meta *me
 	adaptor.SetupCommonRequestHeader(c, req, meta)
 	if meta.ChannelType == channeltype.Azure {
 		req.Header.Set("api-key", meta.APIKey)
+		if meta.Mode == relaymode.AudioTranscription || meta.Mode == relaymode.AudioSpeech {
+			req.ContentLength = c.Request.ContentLength
+		}
 		return nil
 	}
 	req.Header.Set("Authorization", "Bearer "+meta.APIKey)
@@ -81,6 +92,13 @@ func (a *Adaptor) ConvertImageRequest(request *model.ImageRequest) (any, error)
 	return request, nil
 }
 
+func (a *Adaptor) ConvertTextToSpeechRequest(request *model.TextToSpeechRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return request, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, meta *meta.Meta, requestBody io.Reader) (*http.Response, error) {
 	return adaptor.DoRequestHelper(a, c, meta, requestBody)
 }
@@ -100,6 +118,8 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, meta *meta.Met
 		switch meta.Mode {
 		case relaymode.ImagesGenerations:
 			err, _ = ImageHandler(c, resp)
+		case relaymode.AudioSpeech:
+			err, _ = TextToSpeechHandler(c, resp)
 		default:
 			err, usage = Handler(c, resp, meta.PromptTokens, meta.ActualModelName)
 		}

relay/adaptor/openai/audio.go

@@ -0,0 +1,26 @@
+package openai
+
+import (
+	"github.com/gin-gonic/gin"
+	"github.com/songquanpeng/one-api/relay/model"
+	"io"
+	"net/http"
+)
+
+func TextToSpeechHandler(c *gin.Context, resp *http.Response) (*model.ErrorWithStatusCode, *model.Usage) {
+	var err error
+	for k, v := range resp.Header {
+		c.Writer.Header().Set(k, v[0])
+	}
+	c.Writer.WriteHeader(resp.StatusCode)
+
+	_, err = io.Copy(c.Writer, resp.Body)
+	if err != nil {
+		return ErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return ErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	return nil, nil
+}