diff --git a/dto/audio.go b/dto/audio.go
index e3569172..e0d4f9d0 100644
--- a/dto/audio.go
+++ b/dto/audio.go
@@ -18,6 +18,16 @@ type AudioRequest struct {
 	Speed          *float64        `json:"speed,omitempty"`
 	StreamFormat   string          `json:"stream_format,omitempty"`
 	Metadata       json.RawMessage `json:"metadata,omitempty"`
+	// vllm-omini
+	TaskType                json.RawMessage `json:"task_type,omitempty"`
+	Language                json.RawMessage `json:"language,omitempty"`
+	RefAudio                json.RawMessage `json:"ref_audio,omitempty"`
+	RefText                 json.RawMessage `json:"ref_text,omitempty"`
+	XVectorOnlyMode         json.RawMessage `json:"x_vector_only_mode,omitempty"`
+	MaxNewTokens            json.RawMessage `json:"max_new_tokens,omitempty"`
+	InitialCodecChunkFrames json.RawMessage `json:"initial_codec_chunk_frames,omitempty"`
+	// TODO：ensure that the logic remains correct after the stream is started.
+	//Stream                  json.RawMessage `json:"stream,omitempty"`
 }
 
 func (r *AudioRequest) GetTokenCountMeta() *types.TokenCountMeta {
diff --git a/relay/channel/openai/adaptor.go b/relay/channel/openai/adaptor.go
index 29a8f349..2b7f71d6 100644
--- a/relay/channel/openai/adaptor.go
+++ b/relay/channel/openai/adaptor.go
@@ -369,7 +369,7 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
 	a.ResponseFormat = request.ResponseFormat
 	if info.RelayMode == relayconstant.RelayModeAudioSpeech {
-		jsonData, err := json.Marshal(request)
+		jsonData, err := common.Marshal(request)
 		if err != nil {
 			return nil, fmt.Errorf("error marshalling object: %w", err)
 		}