[Bugfix] Use upstream MediaConnector for ref_audio resolution (#1661)

Signed-off-by: linyueqian <linyueqian@outlook.com>
This commit is contained in:
Yueqian Lin authored and GitHub committed 2026-03-09 01:38:26 +00:00
1 parent 0e432e524c
commit a9f694b08a
5 files changed
+41 -68

No files matched your search

@@ -11,7 +11,7 @@ Qwen3 TTS provides multiple task variants for speech generation:
- **CustomVoice**: Generate speech with a known speaker identity (speaker ID) and optional instruction.
- **VoiceDesign**: Generate speech from text plus a descriptive instruction that designs a new voice.
- **Base**: Voice cloning using a reference audio + reference transcript, with optional mode selection.
- **Base**: Voice cloning using a reference audio + reference transcript, with optional mode selection. The `ref_audio` field accepts a local file path, HTTP URL, or base64 data URL.
## Setup
Please refer to the [stage configuration documentation](https://docs.vllm.ai/projects/vllm-omni/en/latest/configuration/stage_configs/) to configure memory allocation appropriately for your hardware setup.