feat(voice): 百炼声音复刻create_voice + TTS instruction情绪驱动(主TTS-昔涟复刻音色)

internal/services/gateway/audio.go

@@ -7,6 +7,7 @@ import (
 	"strings"
 
 	apperr "git.yeij.top/AskaEth/Cyrene_v2/internal/errors"
+	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/multimodal/voice"
 )
 
 // maxAudioRequestBytes caps the JSON body a /api/v1/audio/* request may carry so
@@ -23,11 +24,14 @@ type transcribeRequest struct {
 
 // speechRequest is the POST /api/v1/audio/speech body. Voice/format are accepted
 // for forward compatibility; synthesis currently follows the server's
-// VOICE_TTS_VOICE_ID / VOICE_TTS_FORMAT config.
+// VOICE_TTS_VOICE_ID / VOICE_TTS_FORMAT config. Instruction is an optional
+// per-request emotion/tone override for a cloned voice (声音复刻); a system voice
+// (longxiaochun_v3) ignores it and never receives a free-form instruction.
 type speechRequest struct {
-	Text   string `json:"text"`
-	Voice  string `json:"voice,omitempty"`
-	Format string `json:"format,omitempty"`
+	Text        string `json:"text"`
+	Voice       string `json:"voice,omitempty"`
+	Format      string `json:"format,omitempty"`
+	Instruction string `json:"instruction,omitempty"`
 }
 
 // handleTranscribe runs STT on the uploaded audio and returns the recognized
@@ -88,7 +92,11 @@ func (s *Server) handleSpeech(w http.ResponseWriter, r *http.Request) {
 		writeError(w, apperr.Wrap(apperr.ErrInternal, "voice_unavailable", "voice service is not configured"))
 		return
 	}
-	audi, err := s.voice.TTS(r.Context(), req.Text)
+	ctx := r.Context()
+	if req.Instruction != "" {
+		ctx = voice.WithTTSInstruction(ctx, req.Instruction)
+	}
+	audi, err := s.voice.TTS(ctx, req.Text)
 	if err != nil {
 		s.auditClaims(r, "audio.speech", "error")
 		s.log.Warn("voice speech", "err", err)
@@ -107,6 +115,48 @@ func (s *Server) handleSpeech(w http.ResponseWriter, r *http.Request) {
 	_, _ = w.Write(audi.Data)
 }
 
+// voiceCloneRequest is the POST /api/v1/audio/voice-clone body. URL is the public
+// reference audio URL; prefix is the optional voice-name prefix (≤10 alnum chars).
+// Neither is logged, and the URL is not persisted (owner + audit only, red line).
+type voiceCloneRequest struct {
+	URL    string `json:"url"`
+	Prefix string `json:"prefix,omitempty"`
+}
+
+// handleVoiceClone creates a custom TTS voice from a public reference audio URL
+// via the Bailian voice-enrollment API (声音复刻 create_voice) and returns the new
+// voice_id. Owner-only + audited; the reference URL is never written to the audit
+// trail or the log (red line).
+func (s *Server) handleVoiceClone(w http.ResponseWriter, r *http.Request) {
+	r.Body = http.MaxBytesReader(w, r.Body, maxAudioRequestBytes)
+	var req voiceCloneRequest
+	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
+		s.auditClaims(r, "audio.voice-clone", "error")
+		writeError(w, apperr.Wrap(apperr.ErrBadRequest, "bad_request", "invalid request body"))
+		return
+	}
+	if strings.TrimSpace(req.URL) == "" {
+		s.auditClaims(r, "audio.voice-clone", "error")
+		writeError(w, apperr.Wrap(apperr.ErrBadRequest, "bad_request", "url is required"))
+		return
+	}
+	if s.voice == nil {
+		s.auditClaims(r, "audio.voice-clone", "error")
+		writeError(w, apperr.Wrap(apperr.ErrInternal, "voice_unavailable", "voice service is not configured"))
+		return
+	}
+	voiceID, err := s.voice.CloneVoice(r.Context(), req.URL, req.Prefix)
+	if err != nil {
+		s.auditClaims(r, "audio.voice-clone", "error")
+		// Do not log the cause: a provider error body may echo the reference URL.
+		s.log.Warn("voice clone failed")
+		writeError(w, apperr.Wrap(apperr.ErrInternal, "voice_clone_failed", "voice clone failed"))
+		return
+	}
+	s.auditClaims(r, "audio.voice-clone", "ok")
+	writeJSON(w, http.StatusOK, map[string]any{"voiceId": voiceID})
+}
+
 // audioMime maps an audio format to its Content-Type for the speech response.
 func audioMime(format string) string {
 	switch strings.ToLower(format) {