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/services/gateway/voice.go

@@ -19,8 +19,13 @@ import (
 type VoiceService interface {
 	// STT transcribes audio to text.
 	STT(ctx context.Context, audio voice.Audio) (string, error)
-	// TTS synthesizes audio from text.
+	// TTS synthesizes audio from text. A per-request emotion/tone instruction may
+	// be threaded through ctx (voice.WithTTSInstruction) to override the configured
+	// VOICE_TTS_INSTRUCTION for one call.
 	TTS(ctx context.Context, text string) (voice.Audio, error)
+	// CloneVoice creates a custom voice (声音复刻 create_voice) from a public
+	// reference audio URL and returns its voice_id.
+	CloneVoice(ctx context.Context, referenceURL, prefix string) (string, error)
 }
 
 // voiceInputRequest is the decoded payload of a voice_input frame. Audio is a