Upgrade TTS to qwen3-tts-instruct-flash with instruction control

Adds an optional instructions parameter to sendVoiceMessage so the model
can describe tone, pace and emotion in natural language. Defaults the
TTS model to qwen3-tts-instruct-flash; Chelsie voice is unchanged.

Co-Authored-By: Claude Opus 4.7 <[email protected]>
This commit is contained in:
2026-05-22 15:57:15 +08:00
co-authored by Claude Opus 4.7
parent 39b49bb302
commit 92acbb2310
3 changed files with 14 additions and 5 deletions
+2 -2
View File
@@ -56,8 +56,8 @@ object PluginConfig : AutoSavePluginConfig("Config") {
@ValueDescription("是否在生成的图片右下角添加 Qwen-Image 水印")
val imageWatermark: Boolean by value(false)
@ValueDescription("百炼平台TTS模型")
val ttsModel: String by value("qwen-tts")
@ValueDescription("百炼平台TTS模型。qwen3-tts-instruct-flash 支持 instructions 指令控制;纯发音可用 qwen3-tts-flash 或 qwen-tts")
val ttsModel: String by value("qwen3-tts-instruct-flash")
@ValueDescription("Jina API Key")
val jinaApiKey by value("")