feat(voice): 百炼声音复刻create_voice + TTS instruction情绪驱动(主TTS-昔涟复刻音色)

internal/config/config.go

@@ -126,6 +126,15 @@ type VoiceConfig struct {
 	TTSVoiceID    string `env:"VOICE_TTS_VOICE_ID" default:"longxiaochun_v3"`
 	TTSFormat     string `env:"VOICE_TTS_FORMAT" default:"wav"`
 	TTSSampleRate int    `env:"VOICE_TTS_SAMPLE_RATE" default:"24000"`
+	// VoiceTTSInstruction is the emotion/tone instruction driving a cloned/designed
+	// TTS voice (e.g. "语气开朗俏皮，像女朋友撒娇"). cosyvoice v3 system voices (the
+	// long*_v3 family) require a fixed instruction format, so a free-form instruction
+	// is never sent for them — only for a cloned/designed voice (声音复刻).
+	VoiceTTSInstruction string `env:"VOICE_TTS_INSTRUCTION" default:""`
+	// VoiceClonePrefix is the name prefix used when creating a custom voice (声音复刻
+	// create_voice). It must be ≤10 alphanumeric chars; the empty value falls back
+	// to "cyrene". target_model stays TTSModel (must match the synthesis model).
+	VoiceClonePrefix string `env:"VOICE_CLONE_PREFIX" default:"cyrene"`
 }
 
 // BackgroundConfig holds the autonomous thinking settings. QuietStartHour and