Voice library support dashscope

api/tests/test_assistants.py

@@ -186,9 +186,11 @@ class TestAssistantAPI:
         sample_asr_model_data["vendor"] = "OpenAI Compatible"
         llm_resp = client.post("/api/llm", json=sample_llm_model_data)
         assert llm_resp.status_code == 200
+        llm_id = llm_resp.json()["id"]
 
         asr_resp = client.post("/api/asr", json=sample_asr_model_data)
         assert asr_resp.status_code == 200
+        asr_id = asr_resp.json()["id"]
 
         sample_voice_data["vendor"] = "OpenAI Compatible"
         sample_voice_data["base_url"] = "https://tts.example.com/v1/audio/speech"
@@ -198,8 +200,8 @@ class TestAssistantAPI:
         voice_id = voice_resp.json()["id"]
 
         sample_assistant_data.update({
-            "llmModelId": sample_llm_model_data["id"],
-            "asrModelId": sample_asr_model_data["id"],
+            "llmModelId": llm_id,
+            "asrModelId": asr_id,
             "voice": voice_id,
             "prompt": "runtime prompt",
             "opener": "runtime opener",
@@ -220,7 +222,8 @@ class TestAssistantAPI:
         assert metadata["services"]["llm"]["model"] == sample_llm_model_data["model_name"]
         assert metadata["services"]["asr"]["model"] == sample_asr_model_data["model_name"]
         assert metadata["services"]["asr"]["baseUrl"] == sample_asr_model_data["base_url"]
-        assert metadata["services"]["tts"]["voice"] == sample_voice_data["voice_key"]
+        expected_tts_voice = f"{sample_voice_data['model']}:{sample_voice_data['voice_key']}"
+        assert metadata["services"]["tts"]["voice"] == expected_tts_voice
         assert metadata["services"]["tts"]["baseUrl"] == sample_voice_data["base_url"]
 
     def test_get_engine_config_endpoint(self, client, sample_assistant_data):
@@ -252,6 +255,38 @@ class TestAssistantAPI:
         assert metadata["output"]["mode"] == "text"
         assert metadata["services"]["tts"]["enabled"] is False
 
+    def test_runtime_config_dashscope_voice_provider(self, client, sample_assistant_data):
+        """DashScope voices should map to dashscope tts provider in runtime metadata."""
+        voice_resp = client.post("/api/voices", json={
+            "name": "DashScope Cherry",
+            "vendor": "DashScope",
+            "gender": "Female",
+            "language": "zh",
+            "description": "dashscope voice",
+            "api_key": "dashscope-key",
+            "base_url": "wss://dashscope.aliyuncs.com/api-ws/v1/realtime",
+        })
+        assert voice_resp.status_code == 200
+        voice_payload = voice_resp.json()
+
+        sample_assistant_data.update({
+            "voice": voice_payload["id"],
+            "voiceOutputEnabled": True,
+        })
+        assistant_resp = client.post("/api/assistants", json=sample_assistant_data)
+        assert assistant_resp.status_code == 200
+        assistant_id = assistant_resp.json()["id"]
+
+        runtime_resp = client.get(f"/api/assistants/{assistant_id}/runtime-config")
+        assert runtime_resp.status_code == 200
+        metadata = runtime_resp.json()["sessionStartMetadata"]
+        tts = metadata["services"]["tts"]
+        assert tts["provider"] == "dashscope"
+        assert tts["voice"] == "Cherry"
+        assert tts["model"] == "qwen3-tts-flash-realtime"
+        assert tts["apiKey"] == "dashscope-key"
+        assert tts["baseUrl"] == "wss://dashscope.aliyuncs.com/api-ws/v1/realtime"
+
     def test_assistant_interrupt_and_generated_opener_flags(self, client, sample_assistant_data):
         sample_assistant_data.update({
             "firstTurnMode": "user_first",

api/tests/test_voices.py

@@ -171,8 +171,9 @@ class TestVoiceAPI:
             "voice_key": "FunAudioLLM/CosyVoice2-0.5B:anna"
         })
         assert create_resp.status_code == 200
+        voice_id = create_resp.json()["id"]
 
-        preview_resp = client.post("/api/voices/anna/preview", json={"text": "你好"})
+        preview_resp = client.post(f"/api/voices/{voice_id}/preview", json={"text": "你好"})
         assert preview_resp.status_code == 200
         payload = preview_resp.json()
         assert payload["success"] is True
@@ -228,8 +229,103 @@ class TestVoiceAPI:
             "base_url": "https://api.siliconflow.cn/v1"
         })
         assert create_resp.status_code == 200
+        voice_id = create_resp.json()["id"]
 
-        preview_resp = client.post("/api/voices/anna2/preview", json={"text": "hello"})
+        preview_resp = client.post(f"/api/voices/{voice_id}/preview", json={"text": "hello"})
         assert preview_resp.status_code == 200
         assert captured_auth["value"] == "Bearer voice-key-123"
         assert captured_url["value"] == "https://api.siliconflow.cn/v1/audio/speech"
+
+    def test_create_voice_dashscope_defaults(self, client):
+        """Test creating DashScope voice applies model/voice defaults."""
+        create_resp = client.post("/api/voices", json={
+            "name": "DashScope Voice",
+            "vendor": "DashScope",
+            "gender": "Female",
+            "language": "zh",
+            "description": "dashscope",
+        })
+        assert create_resp.status_code == 200
+        payload = create_resp.json()
+        assert payload["vendor"] == "DashScope"
+        assert payload["model"] == "qwen3-tts-flash-realtime"
+        assert payload["voice_key"] == "Cherry"
+
+    def test_preview_voice_dashscope_success(self, client, monkeypatch):
+        """DashScope voice preview should return playable wav data url."""
+        from app.routers import voices as voice_router
+
+        captured = {
+            "api_key": "",
+            "model": "",
+            "url": "",
+            "session": {},
+            "text": "",
+        }
+
+        class DummyAudioFormat:
+            PCM_24000HZ_MONO_16BIT = "pcm24k16mono"
+
+        class DummyDashScopeModule:
+            api_key = ""
+
+        class DummyRealtime:
+            def __init__(self, *args, **kwargs):
+                captured["api_key"] = kwargs.get("api_key", "")
+                captured["model"] = kwargs.get("model", "")
+                captured["url"] = kwargs.get("url", "")
+                self.callback = kwargs["callback"]
+
+            def connect(self):
+                self.callback.on_open()
+
+            def update_session(self, **kwargs):
+                captured["session"] = kwargs
+
+            def append_text(self, text):
+                captured["text"] = text
+
+            def commit(self):
+                # 16-bit PCM mono samples
+                raw_pcm = b"\x00\x00\x01\x00\x02\x00\x03\x00"
+                self.callback.on_event({
+                    "type": "response.audio.delta",
+                    "delta": base64.b64encode(raw_pcm).decode("utf-8"),
+                })
+                self.callback.on_event({"type": "response.done"})
+
+            def finish(self):
+                return None
+
+            def close(self):
+                return None
+
+        monkeypatch.setattr(voice_router, "DASHSCOPE_SDK_AVAILABLE", True)
+        monkeypatch.setattr(voice_router, "AudioFormat", DummyAudioFormat)
+        monkeypatch.setattr(voice_router, "QwenTtsRealtime", DummyRealtime)
+        monkeypatch.setattr(voice_router, "dashscope", DummyDashScopeModule())
+
+        create_resp = client.post("/api/voices", json={
+            "name": "DashScope Voice",
+            "vendor": "DashScope",
+            "gender": "Female",
+            "language": "zh",
+            "description": "dashscope",
+            "api_key": "dashscope-key",
+            "base_url": "wss://dashscope.aliyuncs.com/api-ws/v1/realtime",
+        })
+        assert create_resp.status_code == 200
+        voice_id = create_resp.json()["id"]
+
+        preview_resp = client.post(f"/api/voices/{voice_id}/preview", json={"text": "你好"})
+        assert preview_resp.status_code == 200
+        payload = preview_resp.json()
+        assert payload["success"] is True
+        assert payload["audio_url"].startswith("data:audio/wav;base64,")
+        encoded = payload["audio_url"].split(",", 1)[1]
+        wav_bytes = base64.b64decode(encoded)
+        assert wav_bytes.startswith(b"RIFF")
+        assert captured["model"] == "qwen3-tts-flash-realtime"
+        assert captured["url"] == "wss://dashscope.aliyuncs.com/api-ws/v1/realtime"
+        assert captured["text"] == "你好"
+        assert captured["session"]["voice"] == "Cherry"