mirror of
https://github.com/jie65535/JChatGPT.git
synced 2026-06-23 00:49:31 +08:00
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>