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/runtime/multimodal/voice/voice.go

@@ -33,3 +33,31 @@ type TTS interface {
 	// honored.
 	TTS(ctx context.Context, text string) (Audio, error)
 }
+
+// VoiceCloner creates a custom voice (声音复刻) from a public reference audio URL.
+// A nil-cloner provider (no cloud rung configured) returns ErrNotConfigured.
+type VoiceCloner interface {
+	// CloneVoice creates a custom voice and returns its voice_id. referenceURL is
+	// a public audio URL; prefix is the voice-name prefix (≤10 alphanumeric chars).
+	CloneVoice(ctx context.Context, referenceURL, prefix string) (string, error)
+}
+
+// ctxKeyTTSInstruction is the context key for a per-request TTS instruction.
+// The TTS interface only carries (ctx, text), so an optional instruction is
+// threaded through ctx to reach the adapter without widening the interface.
+type ctxKeyTTSInstruction struct{}
+
+// WithTTSInstruction returns ctx carrying an optional per-request TTS instruction
+// (emotion/tone) that overrides the configured VOICE_TTS_INSTRUCTION for one call.
+func WithTTSInstruction(ctx context.Context, instruction string) context.Context {
+	return context.WithValue(ctx, ctxKeyTTSInstruction{}, instruction)
+}
+
+// TTSInstructionFromContext returns the per-request TTS instruction set by
+// WithTTSInstruction, or "" when none is carried.
+func TTSInstructionFromContext(ctx context.Context) string {
+	if v, ok := ctx.Value(ctxKeyTTSInstruction{}).(string); ok {
+		return v
+	}
+	return ""
+}