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

2026-09-08 06:48:15 +08:00
1 parent 73dabb9dde
commit 03d7050e1e
@@ -0,0 +1,239 @@
+package voice
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+
+	"git.yeij.top/AskaEth/Cyrene_v2/internal/config"
+)
+
+// TestDashscopeCloner_Ok asserts the create_voice request body shape
+// (model/action/target_model/prefix/url) and the voice_id parsing.
+func TestDashscopeCloner_Ok(t *testing.T) {
+	t.Parallel()
+	var gotBody map[string]any
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if !strings.HasSuffix(r.URL.Path, "/customization") {
+			t.Errorf("path = %q, want .../customization", r.URL.Path)
+		}
+		if r.Header.Get("Authorization") != "Bearer sk" {
+			t.Errorf("auth = %q, want Bearer sk", r.Header.Get("Authorization"))
+		}
+		if sse := r.Header.Get("X-DashScope-SSE"); sse != "" {
+			t.Errorf("sse = %q, want empty", sse)
+		}
+		if err := json.NewDecoder(r.Body).Decode(&gotBody); err != nil {
+			t.Fatalf("decode: %v", err)
+		}
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"output":{"voice_id":"cosyvoice-v3-flash-cyrene-abc123"}}`))
+	}))
+	defer srv.Close()
+
+	cloner := NewDashscopeCloner(config.VoiceConfig{DashscopeBaseURL: srv.URL, DashscopeAPIKey: "sk"})
+	voiceID, err := cloner.CloneVoice(context.Background(), "https://example.com/ref.wav", "cyrene")
+	if err != nil {
+		t.Fatalf("CloneVoice error: %v", err)
+	}
+	if voiceID != "cosyvoice-v3-flash-cyrene-abc123" {
+		t.Errorf("voice_id = %q, want cosyvoice-v3-flash-cyrene-abc123", voiceID)
+	}
+	if gotBody["model"] != "voice-enrollment" {
+		t.Errorf("model = %v, want voice-enrollment", gotBody["model"])
+	}
+	input := gotBody["input"].(map[string]any)
+	if input["action"] != "create_voice" {
+		t.Errorf("action = %v, want create_voice", input["action"])
+	}
+	if input["target_model"] != "cosyvoice-v3-flash" {
+		t.Errorf("target_model = %v, want cosyvoice-v3-flash", input["target_model"])
+	}
+	if input["prefix"] != "cyrene" {
+		t.Errorf("prefix = %v, want cyrene", input["prefix"])
+	}
+	if input["url"] != "https://example.com/ref.wav" {
+		t.Errorf("url = %v, want the reference url", input["url"])
+	}
+}
+
+// TestDashscopeCloner_DefaultPrefix asserts the empty prefix falls back to the
+// configured VOICE_CLONE_PREFIX default ("cyrene").
+func TestDashscopeCloner_DefaultPrefix(t *testing.T) {
+	t.Parallel()
+	var gotBody map[string]any
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if err := json.NewDecoder(r.Body).Decode(&gotBody); err != nil {
+			t.Fatalf("decode: %v", err)
+		}
+		_, _ = w.Write([]byte(`{"output":{"voice_id":"v1"}}`))
+	}))
+	defer srv.Close()
+
+	cloner := NewDashscopeCloner(config.VoiceConfig{DashscopeBaseURL: srv.URL, DashscopeAPIKey: "sk", VoiceClonePrefix: "cyrene"})
+	if _, err := cloner.CloneVoice(context.Background(), "https://example.com/ref.wav", ""); err != nil {
+		t.Fatalf("CloneVoice error: %v", err)
+	}
+	if p := gotBody["input"].(map[string]any)["prefix"]; p != "cyrene" {
+		t.Errorf("prefix = %v, want default cyrene", p)
+	}
+}
+
+// TestDashscopeCloner_TargetModelOverride asserts target_model tracks the config
+// TTSModel (must match the synthesis model).
+func TestDashscopeCloner_TargetModelOverride(t *testing.T) {
+	t.Parallel()
+	var gotBody map[string]any
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if err := json.NewDecoder(r.Body).Decode(&gotBody); err != nil {
+			t.Fatalf("decode: %v", err)
+		}
+		_, _ = w.Write([]byte(`{"output":{"voice_id":"v1"}}`))
+	}))
+	defer srv.Close()
+
+	cloner := NewDashscopeCloner(config.VoiceConfig{DashscopeBaseURL: srv.URL, DashscopeAPIKey: "sk", TTSModel: "cosyvoice-v3.5-plus"})
+	if _, err := cloner.CloneVoice(context.Background(), "https://example.com/ref.wav", "x"); err != nil {
+		t.Fatalf("CloneVoice error: %v", err)
+	}
+	if tm := gotBody["input"].(map[string]any)["target_model"]; tm != "cosyvoice-v3.5-plus" {
+		t.Errorf("target_model = %v, want cosyvoice-v3.5-plus", tm)
+	}
+}
+
+// TestDashscopeCloner_NotConfigured asserts a missing API key degrades.
+func TestDashscopeCloner_NotConfigured(t *testing.T) {
+	t.Parallel()
+	cloner := NewDashscopeCloner(config.VoiceConfig{})
+	if _, err := cloner.CloneVoice(context.Background(), "https://example.com/ref.wav", "x"); err != ErrNotConfigured {
+		t.Fatalf("err = %v, want ErrNotConfigured", err)
+	}
+}
+
+// TestDashscopeCloner_EmptyURL asserts an empty reference URL is rejected.
+func TestDashscopeCloner_EmptyURL(t *testing.T) {
+	t.Parallel()
+	cloner := NewDashscopeCloner(config.VoiceConfig{DashscopeBaseURL: "http://x", DashscopeAPIKey: "sk"})
+	if _, err := cloner.CloneVoice(context.Background(), "   ", "x"); !errors.Is(err, ErrProviderFailed) {
+		t.Fatalf("err = %v, want ErrProviderFailed", err)
+	}
+}
+
+// TestDashscopeCloner_BadPrefix asserts a non-alphanumeric or >10-char prefix is
+// rejected before any request is sent.
+func TestDashscopeCloner_BadPrefix(t *testing.T) {
+	t.Parallel()
+	cloner := NewDashscopeCloner(config.VoiceConfig{DashscopeBaseURL: "http://x", DashscopeAPIKey: "sk"})
+	for _, prefix := range []string{"invalid-prefix!", "this-prefix-is-way-too-long"} {
+		if _, err := cloner.CloneVoice(context.Background(), "https://example.com/ref.wav", prefix); !errors.Is(err, ErrProviderFailed) {
+			t.Errorf("prefix %q: err = %v, want ErrProviderFailed", prefix, err)
+		}
+	}
+}
+
+// TestDashscopeCloner_ModelError asserts a top-level message in an HTTP 200
+// response is surfaced as an error (no voice_id).
+func TestDashscopeCloner_ModelError(t *testing.T) {
+	t.Parallel()
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"message":"invalid reference url"}`))
+	}))
+	defer srv.Close()
+
+	cloner := NewDashscopeCloner(config.VoiceConfig{DashscopeBaseURL: srv.URL, DashscopeAPIKey: "sk"})
+	if _, err := cloner.CloneVoice(context.Background(), "https://example.com/ref.wav", "x"); !errors.Is(err, ErrProviderFailed) {
+		t.Fatalf("err = %v, want ErrProviderFailed", err)
+	}
+}
+
+// TestDashscopeTTS_Instruction_ClonedVoice asserts a cloned voice carries the
+// configured instruction in the request input.
+func TestDashscopeTTS_Instruction_ClonedVoice(t *testing.T) {
+	t.Parallel()
+	var gotBody map[string]any
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if err := json.NewDecoder(r.Body).Decode(&gotBody); err != nil {
+			t.Fatalf("decode: %v", err)
+		}
+		_, _ = w.Write([]byte(`{"output":{"audio":{"data":"eA=="}}}`))
+	}))
+	defer srv.Close()
+
+	tts := NewDashscopeTTS(config.VoiceConfig{
+		DashscopeBaseURL:    srv.URL,
+		DashscopeAPIKey:     "sk",
+		TTSVoiceID:          "cosyvoice-v3-flash-cyrene-abc123",
+		VoiceTTSInstruction: "语气开朗俏皮",
+	})
+	if _, err := tts.TTS(context.Background(), "你好"); err != nil {
+		t.Fatalf("TTS error: %v", err)
+	}
+	if gotBody["model"] != "cosyvoice-v3-flash" {
+		t.Errorf("model = %v, want cosyvoice-v3-flash", gotBody["model"])
+	}
+	input := gotBody["input"].(map[string]any)
+	if input["instruction"] != "语气开朗俏皮" {
+		t.Errorf("instruction = %v, want the configured instruction", input["instruction"])
+	}
+}
+
+// TestDashscopeTTS_NoInstruction_SystemVoice asserts a system voice (longxiaochun_v3)
+// never receives a free-form instruction even when one is configured.
+func TestDashscopeTTS_NoInstruction_SystemVoice(t *testing.T) {
+	t.Parallel()
+	var gotBody map[string]any
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if err := json.NewDecoder(r.Body).Decode(&gotBody); err != nil {
+			t.Fatalf("decode: %v", err)
+		}
+		_, _ = w.Write([]byte(`{"output":{"audio":{"data":"eA=="}}}`))
+	}))
+	defer srv.Close()
+
+	tts := NewDashscopeTTS(config.VoiceConfig{
+		DashscopeBaseURL:    srv.URL,
+		DashscopeAPIKey:     "sk",
+		TTSVoiceID:          "longxiaochun_v3",
+		VoiceTTSInstruction: "语气开朗俏皮",
+	})
+	if _, err := tts.TTS(context.Background(), "你好"); err != nil {
+		t.Fatalf("TTS error: %v", err)
+	}
+	input := gotBody["input"].(map[string]any)
+	if _, ok := input["instruction"]; ok {
+		t.Errorf("instruction present for system voice, want omitted: %v", input)
+	}
+}
+
+// TestDashscopeTTS_Instruction_ContextOverride asserts a per-request ctx
+// instruction wins over the configured one for a cloned voice.
+func TestDashscopeTTS_Instruction_ContextOverride(t *testing.T) {
+	t.Parallel()
+	var gotBody map[string]any
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if err := json.NewDecoder(r.Body).Decode(&gotBody); err != nil {
+			t.Fatalf("decode: %v", err)
+		}
+		_, _ = w.Write([]byte(`{"output":{"audio":{"data":"eA=="}}}`))
+	}))
+	defer srv.Close()
+
+	tts := NewDashscopeTTS(config.VoiceConfig{
+		DashscopeBaseURL:    srv.URL,
+		DashscopeAPIKey:     "sk",
+		TTSVoiceID:          "cosyvoice-v3-flash-cyrene-abc123",
+		VoiceTTSInstruction: "语气温柔",
+	})
+	ctx := WithTTSInstruction(context.Background(), "语气开朗俏皮")
+	if _, err := tts.TTS(ctx, "你好"); err != nil {
+		t.Fatalf("TTS error: %v", err)
+	}
+	if instr := gotBody["input"].(map[string]any)["instruction"]; instr != "语气开朗俏皮" {
+		t.Errorf("instruction = %v, want the ctx override", instr)
+	}
+}