Fix "Add online serving to Stable Audio Diffusion and introduce v1/audio/generate endpoint" (#1794)

Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
This commit is contained in:
authored and GitHub committed 2026-04-28 18:06:57 +00:00
1 parent b50fe1d8b1
commit 4c2bea782e
13 files changed
+1788 -7

No files matched your search

@@ -197,6 +197,7 @@ class OmniOpenAIServingSpeech(OpenAIServing, AudioMixin):
return instance
def __init__(self, *args, **kwargs):
self.model_name = kwargs.pop("model_name", None)
super().__init__(*args, **kwargs)
# Initialize uploaded speakers storage (ephemeral — cleared on restart)
speech_voice_samples_dir = os.environ.get("SPEECH_VOICE_SAMPLES", "/tmp/voice_samples")