Make speech streaming default to SSE (#4679)

Signed-off-by: syd520zy <529477025@qq.com>
This commit is contained in:
faceless void authored and GitHub committed 2026-06-30 02:17:24 +00:00
1 parent c45ac74d43
commit 11f6a0b72e
39 files changed
+146 -58

No files matched your search

@@ -104,6 +104,7 @@ def test_voice_clone_zh_002(omni_server, openai_client) -> None:
"model": omni_server.model,
"input": get_prompt("zh"),
"stream": True,
"stream_format": "audio",
"response_format": "wav",
"ref_audio": REF_AUDIO_URL,
"ref_text": REF_TEXT,
@@ -97,6 +97,7 @@ def test_voice_clone_zh_async_chunk(omni_server, openai_client) -> None:
"model": omni_server.model,
"input": "今天天气真不错,适合出去散散步。",
"stream": True,
"stream_format": "audio",
"response_format": "wav",
"ref_audio": REF_AUDIO_URL,
"ref_text": REF_TEXT,
@@ -98,6 +98,7 @@ class TestHiggsAudioV2OnlineHappyPath:
"model": omni_server.model,
"input": "Streaming the quick brown fox over the lazy dog.",
"stream": True,
"stream_format": "audio",
"response_format": "pcm",
"timeout": DEFAULT_SPEECH_TIMEOUT_S,
"min_audio_bytes": _MIN_AUDIO_BYTES,
@@ -270,6 +271,7 @@ class TestHiggsAudioV2OnlineVoiceClone:
"ref_audio": _REF_AUDIO_URL,
"ref_text": _REF_TEXT,
"stream": True,
"stream_format": "audio",
"response_format": "pcm",
"timeout": DEFAULT_SPEECH_TIMEOUT_S,
"min_audio_bytes": _MIN_AUDIO_BYTES,
@@ -135,6 +135,7 @@ class TestHiggsAudioV3OnlineHappyPath:
"model": omni_server.model,
"input": "The quick brown fox jumps over the lazy dog.",
"stream": True,
"stream_format": "audio",
"response_format": "pcm",
"timeout": DEFAULT_SPEECH_TIMEOUT_S,
"min_hnr_db": 0.0,
@@ -160,6 +161,7 @@ class TestHiggsAudioV3OnlineHappyPath:
"model": omni_server.model,
"input": "She sells seashells by the seashore.",
"stream": True,
"stream_format": "audio",
"response_format": "pcm",
"timeout": DEFAULT_SPEECH_TIMEOUT_S,
"min_hnr_db": -2.0,
@@ -75,6 +75,7 @@ def test_streaming(omni_server, openai_client) -> None:
"model": omni_server.model,
"input": "Hello, this is a voice cloning demo.",
"stream": True,
"stream_format": "audio",
"response_format": "pcm",
"ref_audio": REF_AUDIO_URL,
"min_audio_bytes": 1024,
@@ -90,6 +90,7 @@ def test_text_to_audio_streaming_001(omni_server, openai_client) -> None:
"input": get_prompt("zh_short"),
"voice": "灵小甄",
"stream": True,
"stream_format": "audio",
"response_format": "wav",
"timeout": 300.0,
}
@@ -137,6 +137,7 @@ def test_text_to_audio_002_streaming(omni_server, openai_client, ref_audio_data_
"model": omni_server.model,
"input": get_prompt(),
"stream": True,
"stream_format": "audio",
"response_format": "pcm",
"ref_audio": ref_audio_data_url,
"min_hnr_db": -5.0,
@@ -129,6 +129,7 @@ def test_text_to_audio_002(omni_server, openai_client, ref_audio_data_url) -> No
"model": omni_server.model,
"input": get_prompt(),
"stream": True,
"stream_format": "audio",
"response_format": "pcm",
"ref_audio": ref_audio_data_url,
"min_hnr_db": -5.0,
@@ -100,6 +100,7 @@ def test_text_to_audio_002(omni_server, openai_client) -> None:
"model": omni_server.model,
"input": get_prompt(),
"stream": True,
"stream_format": "audio",
"timeout": DEFAULT_AUDIO_SPEECH_TIMEOUT_S,
"response_format": "wav",
"task_type": "Base",
@@ -80,6 +80,7 @@ def test_voice_clone_streaming_001(omni_server, openai_client) -> None:
"model": omni_server.model,
"input": get_prompt(),
"stream": True,
"stream_format": "audio",
"response_format": "wav",
"task_type": "Base",
"voice": "clone",
@@ -95,6 +95,7 @@ def test_text_to_audio_002(omni_server, openai_client) -> None:
"model": omni_server.model,
"input": get_prompt(),
"stream": True,
"stream_format": "audio",
"response_format": "wav",
"task_type": "CustomVoice",
"voice": "vivian",
@@ -75,6 +75,7 @@ def test_voice_001(omni_server, openai_client) -> None:
"model": omni_server.model,
"input": get_prompt(),
"stream": True,
"stream_format": "audio",
"response_format": "wav",
"task_type": "CustomVoice",
"voice": "uncle_fu",
@@ -89,6 +89,7 @@ def test_text_to_audio_002(omni_server, openai_client) -> None:
"model": omni_server.model,
"input": get_prompt(),
"stream": True,
"stream_format": "audio",
"timeout": DEFAULT_AUDIO_SPEECH_TIMEOUT_S,
"response_format": "wav",
"voice": "default",
@@ -62,6 +62,7 @@ def test_voice_clone_streaming_001(omni_server, openai_client) -> None:
"model": omni_server.model,
"input": get_prompt(),
"stream": True,
"stream_format": "audio",
"timeout": DEFAULT_AUDIO_SPEECH_TIMEOUT_S,
"response_format": "wav",
"voice": "default",
@@ -56,6 +56,7 @@ def test_speech_english_streaming(omni_server, openai_client) -> None:
"voice": "casual_female",
"language": "English",
"stream": True,
"stream_format": "audio",
"response_format": "pcm",
"timeout": 120.0,
"min_audio_bytes": _MIN_AUDIO_BYTES_BASIC,
@@ -141,6 +141,7 @@ class TestSpeakerEmbeddingBase:
"x_vector_only_mode": True,
"response_format": "pcm",
"stream": True,
"stream_format": "audio",
"max_new_tokens": MAX_NEW_TOKENS,
}
with httpx.Client(timeout=120.0) as client:
@@ -1849,17 +1849,22 @@ class TestStreamingProtocolValidation:
OpenAICreateSpeechRequest(input="Hello", stream_format="audio", response_format="pcm", speed=2.0)
def test_stream_valid(self):
"""stream=True + response_format in ('pcm', 'wav') + speed=1.0 is accepted."""
"""stream=True + response_format in ('pcm', 'wav') + speed=1.0 is accepted as SSE."""
req = OpenAICreateSpeechRequest(input="Hello", stream=True, response_format="pcm")
assert req.stream is True
assert req.is_sse_stream() is True
assert req.is_raw_audio_stream() is False
req = OpenAICreateSpeechRequest(input="Hello", stream=True, response_format="wav")
assert req.stream is True
assert req.is_sse_stream() is True
assert req.is_raw_audio_stream() is False
def test_stream_format_audio_is_valid(self):
req = OpenAICreateSpeechRequest(input="Hello", stream_format="audio", response_format="pcm")
assert req.stream_format == "audio"
assert req.is_raw_audio_stream() is True
assert req.is_sse_stream() is False
def test_sse_stream_format_is_valid(self):
"""stream_format='sse' is accepted for /audio/speech."""
@@ -1867,6 +1872,7 @@ class TestStreamingProtocolValidation:
assert req.stream_format == "sse"
assert req.is_sse_stream() is True
assert req.is_raw_audio_stream() is False
class TestStreamingResponse:
@@ -1939,13 +1945,24 @@ class TestStreamingResponse:
app.add_api_route("/v1/audio/speech", speech_server.create_speech, methods=["POST"], response_model=None)
return app
@staticmethod
def _assert_sse_audio_response(response, response_format: str = "pcm"):
assert response.status_code == 200
assert "text/event-stream" in response.headers["content-type"]
body = response.text
assert "event: speech.audio.delta" in body
assert "event: speech.audio.done" in body
data_line = next(line for line in body.splitlines() if line.startswith("data: "))
payload = json.loads(data_line.removeprefix("data: "))
assert payload["type"] == "speech.audio.delta"
assert payload["response_format"] == response_format
assert base64.b64decode(payload["audio"])
def test_streaming(self, streaming_app):
"""stream=True must return audio/pcm with non-empty body."""
"""stream=True defaults to OpenAI speech.audio.* SSE events."""
client = TestClient(streaming_app)
response = client.post("/v1/audio/speech", json={"input": "Hello", "stream": True, "response_format": "pcm"})
assert response.status_code == 200
assert "audio/pcm" in response.headers["content-type"]
assert len(response.content) > 0
self._assert_sse_audio_response(response)
def test_stream_format_audio_streaming(self, streaming_app):
"""stream_format=audio without stream=True returns raw audio/pcm chunks."""
@@ -1967,25 +1984,26 @@ class TestStreamingResponse:
json={"input": "Hello", "stream_format": "sse", "response_format": "pcm"},
)
assert response.status_code == 200
assert "text/event-stream" in response.headers["content-type"]
body = response.text
assert "event: speech.audio.delta" in body
assert "event: speech.audio.done" in body
data_line = next(line for line in body.splitlines() if line.startswith("data: "))
payload = json.loads(data_line.removeprefix("data: "))
assert payload["type"] == "speech.audio.delta"
assert payload["response_format"] == "pcm"
assert base64.b64decode(payload["audio"])
self._assert_sse_audio_response(response)
def test_stream_true_prefers_raw_audio_over_sse(self, streaming_app):
"""stream=True keeps the existing raw audio stream behavior even with stream_format=sse."""
def test_stream_true_with_stream_format_sse_uses_sse(self, streaming_app):
"""stream=True and stream_format=sse both select SSE streaming."""
client = TestClient(streaming_app)
response = client.post(
"/v1/audio/speech",
json={"input": "Hello", "stream": True, "stream_format": "sse", "response_format": "pcm"},
)
self._assert_sse_audio_response(response)
def test_stream_format_audio_with_stream_true_opts_into_raw_audio(self, streaming_app):
"""stream_format=audio remains an explicit raw audio opt-in."""
client = TestClient(streaming_app)
response = client.post(
"/v1/audio/speech",
json={"input": "Hello", "stream": True, "stream_format": "audio", "response_format": "pcm"},
)
assert response.status_code == 200
assert "audio/pcm" in response.headers["content-type"]
assert "text/event-stream" not in response.headers["content-type"]
@@ -3021,7 +3039,10 @@ class TestWAVStreaming:
def test_wav_streaming_success(self, wav_streaming_app):
"""Test WAV format streaming returns correct content type and includes WAV header."""
client = TestClient(wav_streaming_app)
response = client.post("/v1/audio/speech", json={"input": "Hello", "stream": True, "response_format": "wav"})
response = client.post(
"/v1/audio/speech",
json={"input": "Hello", "stream": True, "stream_format": "audio", "response_format": "wav"},
)
assert response.status_code == 200
assert "audio/wav" in response.headers["content-type"]
@@ -3040,7 +3061,10 @@ class TestWAVStreaming:
unsupported_formats = ["mp3"]
for fmt in unsupported_formats:
response = client.post("/v1/audio/speech", json={"input": "Hello", "stream": True, "response_format": fmt})
response = client.post(
"/v1/audio/speech",
json={"input": "Hello", "stream": True, "stream_format": "audio", "response_format": fmt},
)
assert response.status_code == 422
@@ -3336,6 +3360,23 @@ class TestTTSAsyncOffloading:
mock_coerce.assert_called_once_with(qwen3_tts_server.engine_client.default_sampling_params_list, True)
def test_prepare_speech_generation_treats_stream_true_as_streaming(self, qwen3_tts_server, mocker: MockerFixture):
"""stream=True should request delta-style multimodal outputs for SSE streaming."""
qwen3_tts_server._validate_tts_request = mocker.MagicMock(return_value=None)
qwen3_tts_server._build_tts_params = mocker.MagicMock(
return_value={"text": ["hello"], "task_type": ["CustomVoice"], "speaker": ["Vivian"]}
)
qwen3_tts_server._estimate_prompt_len_async = mocker.AsyncMock(return_value=512)
mock_coerce = mocker.patch(
"vllm_omni.entrypoints.openai.serving_speech.coerce_param_message_types",
return_value=qwen3_tts_server.engine_client.default_sampling_params_list,
)
request = OpenAICreateSpeechRequest(input="hello", stream=True, response_format="pcm")
asyncio.run(qwen3_tts_server._prepare_speech_generation(request))
mock_coerce.assert_called_once_with(qwen3_tts_server.engine_client.default_sampling_params_list, True)
def test_prepare_speech_generation_treats_audio_as_streaming(self, qwen3_tts_server, mocker: MockerFixture):
"""stream_format=audio should request delta-style multimodal outputs."""
qwen3_tts_server._validate_tts_request = mocker.MagicMock(return_value=None)
+1
View File
@@ -1770,6 +1770,7 @@ class OpenAIClientHandler:
"seed",
"instructions",
"speed",
"stream_format",
):
if key in request_config:
extra_body[key] = request_config[key]