fix: Qwen3 TTS Model default voice parameters not support longxiaochun

[Binx98]

What this PR does / why we need it?

当前 qwen3 默认 TSS 默认参数根本就无法满足 qwen3-tts-flash 模型，所以添加模型时候一定会报错。
百炼文档里的 qwen3-tts-flash 示例音色是 Cherry，不是当前 v2 分支代码默认的 longxiaochun
对应问题issue： #6236

Summary of your change

追加一套 tss 音频模型初始化参数，为了适配 tss-flash 模型场景，已经自测通过。

Please indicate you've done the following:

• [✅] Made sure tests are passing and test coverage is added if needed.
• [✅] Made sure commit message follow the rule of Conventional Commits specification.
• [✅] Considered the docs impact and opened a new docs issue or PR with docs changes if needed.