diff --git a/backend/internal/ai/tts/openai_test.go b/backend/internal/ai/tts/openai_test.go
new file mode 100644
index 0000000..3f5e609
--- /dev/null
+++ b/backend/internal/ai/tts/openai_test.go
@@ -0,0 +1,300 @@
+package tts
+
+import (
+	"context"
+	"fmt"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"go.uber.org/zap"
+)
+
+// mockTTSServer 创建模拟 OpenAI TTS API 的 HTTP 服务器。
+func mockTTSServer(t *testing.T, handler http.HandlerFunc) *httptest.Server {
+	t.Helper()
+	return httptest.NewServer(handler)
+}
+
+// sendSentences 向 channel 发送句子并关闭。
+func sendSentences(sentences ...string) <-chan string {
+	ch := make(chan string, len(sentences))
+	for _, s := range sentences {
+		ch <- s
+	}
+	close(ch)
+	return ch
+}
+
+func TestOpenAIService_SynthesizeStream_Success(t *testing.T) {
+	var callCount int32
+	srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
+		atomic.AddInt32(&callCount, 1)
+
+		if r.Method != http.MethodPost {
+			t.Errorf("method = %s, want POST", r.Method)
+		}
+		if !strings.Contains(r.URL.Path, "/audio/speech") {
+			t.Errorf("path = %s, should contain /audio/speech", r.URL.Path)
+		}
+		auth := r.Header.Get("Authorization")
+		if auth != "Bearer test-key" {
+			t.Errorf("Authorization = %q, want %q", auth, "Bearer test-key")
+		}
+
+		// 验证请求体
+		body, _ := io.ReadAll(r.Body)
+		if !strings.Contains(string(body), "tts-1") {
+			t.Errorf("request body should contain model tts-1")
+		}
+
+		// 返回假 MP3 数据
+		w.Header().Set("Content-Type", "audio/mpeg")
+		fmt.Fprintf(w, "fake-mp3-data")
+	})
+	defer srv.Close()
+
+	svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
+
+	textStream := sendSentences("你好", "世界", "！")
+
+	ch, err := svc.SynthesizeStream(context.Background(), textStream, Options{
+		Voice: "alloy", Speed: 1.0, OutputFmt: "mp3", SampleRate: 24000,
+	})
+	if err != nil {
+		t.Fatalf("SynthesizeStream() error: %v", err)
+	}
+
+	var chunks []Chunk
+	for c := range ch {
+		chunks = append(chunks, c)
+	}
+
+	// 应该有 3 个音频 chunk + 1 个 IsLast 标记
+	if len(chunks) != 4 {
+		t.Fatalf("got %d chunks, want 4", len(chunks))
+	}
+
+	// 验证前 3 个有音频数据
+	for i := 0; i < 3; i++ {
+		if string(chunks[i].Audio) != "fake-mp3-data" {
+			t.Errorf("chunk[%d].Audio = %q, want %q", i, string(chunks[i].Audio), "fake-mp3-data")
+		}
+		if chunks[i].IsLast {
+			t.Errorf("chunk[%d].IsLast should be false", i)
+		}
+	}
+
+	// 验证最后一个是 IsLast
+	if !chunks[3].IsLast {
+		t.Error("last chunk should be IsLast")
+	}
+	if chunks[3].Audio != nil {
+		t.Error("last chunk Audio should be nil")
+	}
+
+	// 验证调用了 3 次 API（3 个句子）
+	if atomic.LoadInt32(&callCount) != 3 {
+		t.Errorf("API called %d times, want 3", callCount)
+	}
+}
+
+func TestOpenAIService_SynthesizeStream_APIError(t *testing.T) {
+	srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(http.StatusInternalServerError)
+		fmt.Fprintf(w, "internal error")
+	})
+	defer srv.Close()
+
+	svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
+
+	textStream := sendSentences("你好")
+
+	ch, err := svc.SynthesizeStream(context.Background(), textStream, Options{})
+	if err != nil {
+		t.Fatalf("SynthesizeStream() error: %v", err)
+	}
+
+	// 应该只有一个 IsLast chunk（音频被跳过）
+	var chunks []Chunk
+	for c := range ch {
+		chunks = append(chunks, c)
+	}
+
+	if len(chunks) != 1 {
+		t.Fatalf("got %d chunks, want 1 (IsLast only)", len(chunks))
+	}
+	if !chunks[0].IsLast {
+		t.Error("chunk should be IsLast")
+	}
+}
+
+func TestOpenAIService_SynthesizeStream_Timeout(t *testing.T) {
+	srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
+		time.Sleep(3 * time.Second)
+		w.Header().Set("Content-Type", "audio/mpeg")
+		fmt.Fprintf(w, "late-mp3")
+	})
+	defer srv.Close()
+
+	// 1 秒超时
+	svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 1, zap.NewNop().Sugar())
+
+	textStream := sendSentences("很长的句子")
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	ch, err := svc.SynthesizeStream(ctx, textStream, Options{})
+	if err != nil {
+		t.Fatalf("SynthesizeStream() error: %v", err)
+	}
+
+	var chunks []Chunk
+	for c := range ch {
+		chunks = append(chunks, c)
+	}
+
+	// 超时后音频被跳过，只有 IsLast
+	if len(chunks) != 1 {
+		t.Fatalf("got %d chunks, want 1", len(chunks))
+	}
+	if !chunks[0].IsLast {
+		t.Error("chunk should be IsLast")
+	}
+}
+
+func TestOpenAIService_SynthesizeStream_EmptyText(t *testing.T) {
+	var callCount int32
+	srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
+		atomic.AddInt32(&callCount, 1)
+		w.Header().Set("Content-Type", "audio/mpeg")
+		fmt.Fprintf(w, "mp3")
+	})
+	defer srv.Close()
+
+	svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
+
+	// 空句子应该被跳过
+	textStream := sendSentences("", "你好", "")
+
+	ch, err := svc.SynthesizeStream(context.Background(), textStream, Options{})
+	if err != nil {
+		t.Fatalf("SynthesizeStream() error: %v", err)
+	}
+
+	var chunks []Chunk
+	for c := range ch {
+		chunks = append(chunks, c)
+	}
+
+	// 只有 "你好" 应该被合成
+	if atomic.LoadInt32(&callCount) != 1 {
+		t.Errorf("API called %d times, want 1", callCount)
+	}
+
+	// 1 个音频 + 1 个 IsLast
+	if len(chunks) != 2 {
+		t.Fatalf("got %d chunks, want 2", len(chunks))
+	}
+}
+
+func TestOpenAIService_SynthesizeStream_ContextCancelled(t *testing.T) {
+	srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "audio/mpeg")
+		fmt.Fprintf(w, "mp3")
+	})
+	defer srv.Close()
+
+	svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
+
+	// 发送多个句子，但在第一个后取消
+	textStream := make(chan string, 3)
+	textStream <- "第一句"
+	textStream <- "第二句"
+	textStream <- "第三句"
+	close(textStream)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	// 立即取消
+	cancel()
+
+	ch, err := svc.SynthesizeStream(ctx, textStream, Options{})
+	if err != nil {
+		t.Fatalf("SynthesizeStream() error: %v", err)
+	}
+
+	// 消费 channel，应该很快结束
+	var count int
+	for range ch {
+		count++
+	}
+	// 可能收到 0 个或 1 个 chunk，取决于时序
+	t.Logf("received %d chunks after context cancel", count)
+}
+
+func TestOpenAIService_SynthesizeStream_PartialFailure(t *testing.T) {
+	var callCount int32
+	srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
+		n := atomic.AddInt32(&callCount, 1)
+		if n == 2 {
+			// 第二个句子失败
+			w.WriteHeader(http.StatusInternalServerError)
+			fmt.Fprintf(w, "error")
+			return
+		}
+		w.Header().Set("Content-Type", "audio/mpeg")
+		fmt.Fprintf(w, "mp3-%d", n)
+	})
+	defer srv.Close()
+
+	svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
+
+	textStream := sendSentences("第一句", "第二句", "第三句")
+
+	ch, err := svc.SynthesizeStream(context.Background(), textStream, Options{})
+	if err != nil {
+		t.Fatalf("SynthesizeStream() error: %v", err)
+	}
+
+	var chunks []Chunk
+	for c := range ch {
+		chunks = append(chunks, c)
+	}
+
+	// 2 个成功音频 + 1 个 IsLast（第二句被跳过）
+	if len(chunks) != 3 {
+		t.Fatalf("got %d chunks, want 3", len(chunks))
+	}
+	if !chunks[len(chunks)-1].IsLast {
+		t.Error("last chunk should be IsLast")
+	}
+}
+
+func TestOpenAIService_SynthesizeStream_CustomVoice(t *testing.T) {
+	srv := mockTTSServer(t, func(w http.ResponseWriter, r *http.Request) {
+		body, _ := io.ReadAll(r.Body)
+		if !strings.Contains(string(body), "nova") {
+			t.Errorf("request body should contain voice 'nova', got: %s", string(body))
+		}
+		w.Header().Set("Content-Type", "audio/mpeg")
+		fmt.Fprintf(w, "mp3")
+	})
+	defer srv.Close()
+
+	svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
+
+	textStream := sendSentences("你好")
+
+	ch, err := svc.SynthesizeStream(context.Background(), textStream, Options{Voice: "nova"})
+	if err != nil {
+		t.Fatalf("SynthesizeStream() error: %v", err)
+	}
+
+	for range ch {
+	}
+}