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 <noreply@anthropic.com>
This commit is contained in:
2026-05-22 15:57:15 +08:00
parent 39b49bb302
commit 92acbb2310
3 changed files with 14 additions and 5 deletions

View File

@@ -95,8 +95,8 @@ dashScopeApiKey: ''
imageModel: 'qwen-image-2.0'
# 是否在生成图片右下角添加 Qwen-Image 水印
imageWatermark: false
# 百炼平台TTS模型
ttsModel: 'qwen-tts'
# 百炼平台TTS模型qwen3-tts-instruct-flash 支持 instructions 指令控制语气
ttsModel: 'qwen3-tts-instruct-flash'
# Jina API Key
jinaApiKey: ''
# SearXNG 搜索引擎地址,如 http://127.0.0.1:8080/search 必须启用允许json格式返回