[文本转语音TTS不支持mimo-v2.5-tts-voicedesign]

[Lagxio]

What happened / 发生了什么

模型提供商中填写新模型mimo-v2.5-tts-voicedesign的时候，已经按照mimo官方文档中提示进行操作留空音色，但是还是会报错HTTP 400, response: {"error":{"code":"400","message":"Param Incorrect","param":"audio.voice is not supported for voice design model","type":""}}
我猜测和参数有关，此模型的参数和mimo-v2.5-tts参数不同

Reproduce / 如何复现？

AstrBot version, deployment method (e.g., Windows Docker Desktop deployment), provider used, and messaging platform used. / AstrBot 版本、部署方式（如 Windows Docker Desktop 部署）、使用的提供商、使用的消息平台适配器

AstrBot 版本v4.24.2
linux docker部署
提供商为mimotts
消息适配器为LLBot

OS

Linux

Logs / 报错日志

MiMo TTS API request failed: HTTP 400, response: {"error":{"code":"400","message":"Param Incorrect","param":"audio.voice is not supported for voice design model","type":""}}

Are you willing to submit a PR? / 你愿意提交 PR 吗？

• Yes!

Code of Conduct

• I have read and agree to abide by the project's Code of Conduct。

[dosubot]

Hi @Lagxio! I'm Dosu and I’m helping the AstrBot team.

确认了这个问题。根源在 astrbot/core/provider/sources/mimo_tts_api_source.py 的 _build_payload() 方法中 [1]，audio.voice 参数是始终被包含在请求体中的：

return {
    "model": self.model_name,
    "messages": messages,
    "audio": {
        "format": self.audio_format,
        "voice": self.voice,  # 始终包含
    },
}

即使用户留空音色配置，代码也会回退到默认值 "mimo_default" [2]，导致 voice 参数永远不会被省略。而 mimo-v2.5-tts-voicedesign 模型不支持 audio.voice 参数，因此报 400 错误。

修复方向：在 _build_payload() 中增加条件判断，当模型为 voice design 类型或 voice 配置为空时，不在 audio 对象中包含 voice 字段。例如：

audio_params = {"format": self.audio_format}
if self.voice and "voicedesign" not in self.model_name:
    audio_params["voice"] = self.voice
return {
    "model": self.model_name,
    "messages": messages,
    "audio": audio_params,
}

既然你愿意提交 PR，可以参考上述思路进行修改。

To reply, just mention @dosu.

---

Docs are dead. Just use Dosu.