wx44wx/AI-VideoAssistant
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Voice library support dashscope

Browse Source
This commit is contained in:
Xin Wang
2026-02-26 03:54:52 +08:00
parent b193f91432
commit f77f7c7531
11 changed files with 684 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
api/tests/test_assistants.py
View File

@@ -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",