[Feat]Support voice clone for omnivoice in online serving & add seed parameter for reproducible (#3668)

Signed-off-by: sphinxkkkbc <binchengkang8@gmail.com>
Co-authored-by: sphinxkkkbc <binchengkang8@gmail.com>
This commit is contained in:
boatmanandsphinxkkkbc authored and GitHub committed 2026-05-29 07:42:08 +00:00
1 parent c69ed4037d
commit 4d9262a6eb
9 files changed
+158 -22

No files matched your search

@@ -74,6 +74,41 @@ class TestOmniVoiceTTS:
openai_client.send_audio_speech_request(request_config)
@pytest.mark.parametrize("omni_server", TEST_PARAMS, indirect=True)
class TestOmniVoiceSeed:
"""E2E tests for OmniVoice Seed Params."""
@hardware_test(res={"cuda": "L4"}, num_cards=1)
def test_speech_auto_voice_seed_deterministic(self, omni_server, openai_client) -> None:
cfg = {
"model": omni_server.model,
"input": get_prompt("text"),
"response_format": "wav",
"seed": 42,
"min_audio_bytes": _DEFAULT_MIN_AUDIO_BYTES,
}
r1 = openai_client.send_audio_speech_request(cfg)[0]
r2 = openai_client.send_audio_speech_request(cfg)[0]
assert r1.audio_bytes == r2.audio_bytes
@hardware_test(res={"cuda": "L4"}, num_cards=1)
def test_speech_auto_voice_seed_non_deterministic(self, omni_server, openai_client) -> None:
cfg = {
"model": omni_server.model,
"input": get_prompt("text"),
"response_format": "wav",
"min_audio_bytes": _DEFAULT_MIN_AUDIO_BYTES,
}
cfg1 = {**cfg, "seed": 42}
cfg2 = {**cfg, "seed": 43}
r1 = openai_client.send_audio_speech_request(cfg1)[0]
r2 = openai_client.send_audio_speech_request(cfg2)[0]
assert r1.audio_bytes != r2.audio_bytes
@pytest.mark.skipif(not _HAS_VOICE_CLONE, reason="Voice cloning requires transformers>=5.3.0")
@pytest.mark.parametrize("omni_server", TEST_PARAMS, indirect=True)
class TestOmniVoiceVoiceCloning:
+1 -1
View File
@@ -1671,7 +1671,7 @@ class OpenAIClientHandler:
# Qwen3-TTS custom fields, forwarded via extra_body.
extra_body: dict[str, Any] = {}
# Keep this list aligned with vllm_omni.entrypoints.openai.protocol.audio params.
for key in ("task_type", "ref_text", "ref_audio", "language", "max_new_tokens"):
for key in ("task_type", "ref_text", "ref_audio", "language", "max_new_tokens", "seed"):
if key in request_config:
extra_body[key] = request_config[key]