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_test.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"encoding/base64"
 	"net/http"
+	"strings"
 	"testing"
 
 	"git.yeij.top/AskaEth/Cyrene_v2/internal/auth"
@@ -21,6 +22,13 @@ type audioStubVoice struct {
 	gotText   string
 	sttCalled bool
 	ttsCalled bool
+
+	cloneVoiceID string
+	cloneErr     error
+	cloneCalled  bool
+	gotCloneURL  string
+	gotClonePfx  string
+	gotInstr     string
 }
 
 func (s *audioStubVoice) STT(ctx context.Context, audio voice.Audio) (string, error) {
@@ -32,9 +40,17 @@ func (s *audioStubVoice) STT(ctx context.Context, audio voice.Audio) (string, er
 func (s *audioStubVoice) TTS(ctx context.Context, text string) (voice.Audio, error) {
 	s.ttsCalled = true
 	s.gotText = text
+	s.gotInstr = voice.TTSInstructionFromContext(ctx)
 	return s.ttsAudio, s.ttsErr
 }
 
+func (s *audioStubVoice) CloneVoice(ctx context.Context, referenceURL, prefix string) (string, error) {
+	s.cloneCalled = true
+	s.gotCloneURL = referenceURL
+	s.gotClonePfx = prefix
+	return s.cloneVoiceID, s.cloneErr
+}
+
 func TestHandleTranscribe(t *testing.T) {
 	env := newEnv(t, nil, false)
 	sv := &audioStubVoice{sttText: "你好世界"}
@@ -122,3 +138,97 @@ func TestHandleSpeech_EmptyText(t *testing.T) {
 		t.Fatalf("status = %d, want 400 (body=%s)", resp.StatusCode, body)
 	}
 }
+
+func TestHandleSpeech_InstructionPassthrough(t *testing.T) {
+	env := newEnv(t, nil, false)
+	sv := &audioStubVoice{ttsAudio: voice.Audio{Format: "wav", Data: []byte("audio-bytes")}}
+	env.srv.SetVoice(sv)
+
+	token := env.token(t, auth.RoleOwner)
+	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/speech", map[string]any{
+		"text":        "你好，我是昔涟",
+		"instruction": "语气开朗俏皮，像女朋友撒娇",
+	}, token)
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("status = %d, body = %s", resp.StatusCode, body)
+	}
+	if !sv.ttsCalled {
+		t.Fatal("TTS not called")
+	}
+	if sv.gotText != "你好，我是昔涟" {
+		t.Errorf("TTS text = %q, want 你好，我是昔涟", sv.gotText)
+	}
+	if sv.gotInstr != "语气开朗俏皮，像女朋友撒娇" {
+		t.Errorf("instruction threaded = %q, want the per-request instruction", sv.gotInstr)
+	}
+}
+
+func TestHandleSpeech_NoInstruction(t *testing.T) {
+	env := newEnv(t, nil, false)
+	sv := &audioStubVoice{ttsAudio: voice.Audio{Format: "wav", Data: []byte("audio-bytes")}}
+	env.srv.SetVoice(sv)
+
+	token := env.token(t, auth.RoleOwner)
+	resp, _ := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/speech", map[string]any{
+		"text": "你好",
+	}, token)
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("status = %d, want 200", resp.StatusCode)
+	}
+	if sv.gotInstr != "" {
+		t.Errorf("instruction = %q, want empty when not supplied", sv.gotInstr)
+	}
+}
+
+func TestHandleVoiceClone(t *testing.T) {
+	env := newEnv(t, nil, false)
+	sv := &audioStubVoice{cloneVoiceID: "cosyvoice-v3-flash-cyrene-abc123"}
+	env.srv.SetVoice(sv)
+
+	token := env.token(t, auth.RoleOwner)
+	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/voice-clone", map[string]any{
+		"url":    "https://example.com/ref.wav",
+		"prefix": "xilian",
+	}, token)
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("status = %d, body = %s", resp.StatusCode, body)
+	}
+	if !sv.cloneCalled {
+		t.Fatal("CloneVoice not called")
+	}
+	if sv.gotCloneURL != "https://example.com/ref.wav" || sv.gotClonePfx != "xilian" {
+		t.Errorf("clone url/prefix = %q / %q, want the request values", sv.gotCloneURL, sv.gotClonePfx)
+	}
+	env2 := decodeBody(t, body)
+	if got := string(env2["data"]); got == "" {
+		t.Errorf("data envelope empty: %s", body)
+	}
+	if !strings.Contains(string(env2["data"]), "cosyvoice-v3-flash-cyrene-abc123") {
+		t.Errorf("voiceId missing: %s", body)
+	}
+}
+
+func TestHandleVoiceClone_AuthRequired(t *testing.T) {
+	env := newEnv(t, nil, false)
+	env.srv.SetVoice(&audioStubVoice{})
+
+	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/voice-clone", map[string]any{
+		"url": "https://example.com/ref.wav",
+	}, "")
+	if resp.StatusCode != http.StatusUnauthorized {
+		t.Fatalf("status = %d, want 401 (body=%s)", resp.StatusCode, body)
+	}
+}
+
+func TestHandleVoiceClone_EmptyURL(t *testing.T) {
+	env := newEnv(t, nil, false)
+	env.srv.SetVoice(&audioStubVoice{})
+
+	token := env.token(t, auth.RoleOwner)
+	resp, body := doReq(t, http.MethodPost, env.ts.URL+"/api/v1/audio/voice-clone", map[string]any{
+		"url": "  ",
+	}, token)
+	if resp.StatusCode != http.StatusBadRequest {
+		t.Fatalf("status = %d, want 400 (body=%s)", resp.StatusCode, body)
+	}
+}