增加MiniMax语音合成TTS支持

common/api_type.go

@@ -69,6 +69,8 @@ func ChannelType2APIType(channelType int) (int, bool) {
 		apiType = constant.APITypeMoonshot
 	case constant.ChannelTypeSubmodel:
 		apiType = constant.APITypeSubmodel
+	case constant.ChannelTypeMiniMax:
+		apiType = constant.APITypeMiniMax
 	}
 	if apiType == -1 {
 		return constant.APITypeOpenAI, false

constant/api_type.go

@@ -33,5 +33,6 @@ const (
 	APITypeJimeng
 	APITypeMoonshot
 	APITypeSubmodel
+	APITypeMiniMax
 	APITypeDummy // this one is only for count, do not add any channel after this
 )

relay/channel/minimax/adaptor.go

@@ -0,0 +1,132 @@
+package minimax
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/relay/channel"
+	"github.com/QuantumNous/new-api/relay/channel/openai"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/QuantumNous/new-api/relay/constant"
+	"github.com/QuantumNous/new-api/types"
+
+	"github.com/gin-gonic/gin"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertGeminiRequest(*gin.Context, *relaycommon.RelayInfo, *dto.GeminiChatRequest) (any, error) {
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertClaudeRequest(c *gin.Context, info *relaycommon.RelayInfo, req *dto.ClaudeRequest) (any, error) {
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	if info.RelayMode != constant.RelayModeAudioSpeech {
+		return nil, errors.New("unsupported audio relay mode")
+	}
+
+	voiceID := request.Voice
+	speed := request.Speed
+	outputFormat := request.ResponseFormat
+
+	minimaxRequest := MiniMaxTTSRequest{
+		Model: info.OriginModelName,
+		Text:  request.Input,
+		VoiceSetting: VoiceSetting{
+			VoiceID: voiceID,
+			Speed:   speed,
+		},
+		AudioSetting: &AudioSetting{
+			Format: outputFormat,
+		},
+		OutputFormat: outputFormat,
+	}
+
+	// 同步扩展字段的厂商自定义metadata
+	if len(request.Metadata) > 0 {
+		if err := json.Unmarshal(request.Metadata, &minimaxRequest); err != nil {
+			return nil, fmt.Errorf("error unmarshalling metadata to minimax request: %w", err)
+		}
+	}
+
+	jsonData, err := json.Marshal(minimaxRequest)
+	if err != nil {
+		return nil, fmt.Errorf("error marshalling minimax request: %w", err)
+	}
+	if outputFormat != "hex" {
+		outputFormat = "url"
+	}
+
+	c.Set("response_format", outputFormat)
+
+	// Debug: log the request structure
+	// fmt.Printf("MiniMax TTS Request: %s\n", string(jsonData))
+
+	return bytes.NewReader(jsonData), nil
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return GetRequestURL(info)
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return request, nil
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
+	if info.RelayMode == constant.RelayModeAudioSpeech {
+		return handleTTSResponse(c, resp, info)
+	}
+
+	adaptor := openai.Adaptor{}
+	return adaptor.DoResponse(c, resp, info)
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/minimax/constants.go

@@ -8,6 +8,12 @@ var ModelList = []string{
 	"abab6-chat",
 	"abab5.5-chat",
 	"abab5.5s-chat",
+	"speech-2.5-hd-preview",
+	"speech-2.5-turbo-preview",
+	"speech-02-hd",
+	"speech-02-turbo",
+	"speech-01-hd",
+	"speech-01-turbo",
 }
 
 var ChannelName = "minimax"

relay/channel/minimax/relay-minimax.go

@@ -3,9 +3,23 @@ package minimax
 import (
 	"fmt"
 
+	channelconstant "github.com/QuantumNous/new-api/constant"
 	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/QuantumNous/new-api/relay/constant"
 )
 
 func GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	return fmt.Sprintf("%s/v1/text/chatcompletion_v2", info.ChannelBaseUrl), nil
+	baseUrl := info.ChannelBaseUrl
+	if baseUrl == "" {
+		baseUrl = channelconstant.ChannelBaseURLs[channelconstant.ChannelTypeMiniMax]
+	}
+
+	switch info.RelayMode {
+	case constant.RelayModeChatCompletions:
+		return fmt.Sprintf("%s/v1/text/chatcompletion_v2", baseUrl), nil
+	case constant.RelayModeAudioSpeech:
+		return fmt.Sprintf("%s/v1/t2a_v2", baseUrl), nil
+	default:
+		return "", fmt.Errorf("unsupported relay mode: %d", info.RelayMode)
+	}
 }

relay/channel/minimax/tts.go

@@ -0,0 +1,194 @@
+package minimax
+
+import (
+	"encoding/hex"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+
+	"github.com/QuantumNous/new-api/dto"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/QuantumNous/new-api/types"
+	"github.com/gin-gonic/gin"
+)
+
+type MiniMaxTTSRequest struct {
+	Model             string             `json:"model"`
+	Text              string             `json:"text"`
+	Stream            bool               `json:"stream,omitempty"`
+	StreamOptions     *StreamOptions     `json:"stream_options,omitempty"`
+	VoiceSetting      VoiceSetting       `json:"voice_setting"`
+	PronunciationDict *PronunciationDict `json:"pronunciation_dict,omitempty"`
+	AudioSetting      *AudioSetting      `json:"audio_setting,omitempty"`
+	TimbreWeights     []TimbreWeight     `json:"timbre_weights,omitempty"`
+	LanguageBoost     string             `json:"language_boost,omitempty"`
+	VoiceModify       *VoiceModify       `json:"voice_modify,omitempty"`
+	SubtitleEnable    bool               `json:"subtitle_enable,omitempty"`
+	OutputFormat      string             `json:"output_format,omitempty"`
+	AigcWatermark     bool               `json:"aigc_watermark,omitempty"`
+}
+
+type StreamOptions struct {
+	ExcludeAggregatedAudio bool `json:"exclude_aggregated_audio,omitempty"`
+}
+
+type VoiceSetting struct {
+	VoiceID           string  `json:"voice_id"`
+	Speed             float64 `json:"speed,omitempty"`
+	Vol               float64 `json:"vol,omitempty"`
+	Pitch             int     `json:"pitch,omitempty"`
+	Emotion           string  `json:"emotion,omitempty"`
+	TextNormalization bool    `json:"text_normalization,omitempty"`
+	LatexRead         bool    `json:"latex_read,omitempty"`
+}
+
+type PronunciationDict struct {
+	Tone []string `json:"tone,omitempty"`
+}
+
+type AudioSetting struct {
+	SampleRate int    `json:"sample_rate,omitempty"`
+	Bitrate    int    `json:"bitrate,omitempty"`
+	Format     string `json:"format,omitempty"`
+	Channel    int    `json:"channel,omitempty"`
+	ForceCbr   bool   `json:"force_cbr,omitempty"`
+}
+
+type TimbreWeight struct {
+	VoiceID string `json:"voice_id"`
+	Weight  int    `json:"weight"`
+}
+
+type VoiceModify struct {
+	Pitch        int    `json:"pitch,omitempty"`
+	Intensity    int    `json:"intensity,omitempty"`
+	Timbre       int    `json:"timbre,omitempty"`
+	SoundEffects string `json:"sound_effects,omitempty"`
+}
+
+type MiniMaxTTSResponse struct {
+	Data      MiniMaxTTSData   `json:"data"`
+	ExtraInfo MiniMaxExtraInfo `json:"extra_info"`
+	TraceID   string           `json:"trace_id"`
+	BaseResp  MiniMaxBaseResp  `json:"base_resp"`
+}
+
+type MiniMaxTTSData struct {
+	Audio  string `json:"audio"`
+	Status int    `json:"status"`
+}
+
+type MiniMaxExtraInfo struct {
+	UsageCharacters int64 `json:"usage_characters"`
+}
+
+type MiniMaxBaseResp struct {
+	StatusCode int64  `json:"status_code"`
+	StatusMsg  string `json:"status_msg"`
+}
+
+func getContentTypeByFormat(format string) string {
+	contentTypeMap := map[string]string{
+		"mp3":  "audio/mpeg",
+		"wav":  "audio/wav",
+		"flac": "audio/flac",
+		"aac":  "audio/aac",
+		"pcm":  "audio/pcm",
+	}
+	if ct, ok := contentTypeMap[format]; ok {
+		return ct
+	}
+	return "audio/mpeg" // default to mp3
+}
+
+func handleTTSResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
+	body, readErr := io.ReadAll(resp.Body)
+	if readErr != nil {
+		return nil, types.NewErrorWithStatusCode(
+			fmt.Errorf("failed to read minimax response: %w", readErr),
+			types.ErrorCodeReadResponseBodyFailed,
+			http.StatusInternalServerError,
+		)
+	}
+	defer resp.Body.Close()
+
+	// Parse response
+	var minimaxResp MiniMaxTTSResponse
+	if unmarshalErr := json.Unmarshal(body, &minimaxResp); unmarshalErr != nil {
+		return nil, types.NewErrorWithStatusCode(
+			fmt.Errorf("failed to unmarshal minimax TTS response: %w", unmarshalErr),
+			types.ErrorCodeBadResponseBody,
+			http.StatusInternalServerError,
+		)
+	}
+
+	// Check base_resp status code
+	if minimaxResp.BaseResp.StatusCode != 0 {
+		return nil, types.NewErrorWithStatusCode(
+			fmt.Errorf("minimax TTS error: %d - %s", minimaxResp.BaseResp.StatusCode, minimaxResp.BaseResp.StatusMsg),
+			types.ErrorCodeBadResponse,
+			http.StatusBadRequest,
+		)
+	}
+
+	// Check if we have audio data
+	if minimaxResp.Data.Audio == "" {
+		return nil, types.NewErrorWithStatusCode(
+			fmt.Errorf("no audio data in minimax TTS response"),
+			types.ErrorCodeBadResponse,
+			http.StatusBadRequest,
+		)
+	}
+
+	if strings.HasPrefix(minimaxResp.Data.Audio, "http") {
+		c.Redirect(http.StatusFound, minimaxResp.Data.Audio)
+	} else {
+		// Handle hex-encoded audio data
+		audioData, decodeErr := hex.DecodeString(minimaxResp.Data.Audio)
+		if decodeErr != nil {
+			return nil, types.NewErrorWithStatusCode(
+				fmt.Errorf("failed to decode hex audio data: %w", decodeErr),
+				types.ErrorCodeBadResponse,
+				http.StatusInternalServerError,
+			)
+		}
+
+		// Determine content type - default to mp3
+		contentType := "audio/mpeg"
+
+		c.Data(http.StatusOK, contentType, audioData)
+	}
+
+	usage = &dto.Usage{
+		PromptTokens:     info.PromptTokens,
+		CompletionTokens: 0,
+		TotalTokens:      int(minimaxResp.ExtraInfo.UsageCharacters),
+	}
+
+	return usage, nil
+}
+
+func handleChatCompletionResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
+	body, readErr := io.ReadAll(resp.Body)
+	if readErr != nil {
+		return nil, types.NewErrorWithStatusCode(
+			errors.New("failed to read minimax response"),
+			types.ErrorCodeReadResponseBodyFailed,
+			http.StatusInternalServerError,
+		)
+	}
+	defer resp.Body.Close()
+
+	// Set response headers
+	for key, values := range resp.Header {
+		for _, value := range values {
+			c.Header(key, value)
+		}
+	}
+
+	c.Data(resp.StatusCode, "application/json", body)
+	return nil, nil
+}