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/chain.go

@@ -12,7 +12,8 @@ import (
 // provider is unavailable (nil direction) or fails. It implements STT and TTS so
 // it can be used anywhere a single provider is expected.
 type Chain struct {
-	steps []Provider
+	steps  []Provider
+	cloner VoiceCloner
 }
 
 // NewChain builds a degrading chain from the given providers in the order they
@@ -42,6 +43,16 @@ func (c *Chain) STT(ctx context.Context, audio Audio) (string, error) {
 	return "", fmt.Errorf("voice: %w: %v", ErrProviderFailed, lastErr)
 }
 
+// CloneVoice creates a custom voice via the cloud provider's voice-enrollment
+// endpoint (声音复刻 create_voice). A chain without a cloud rung returns
+// ErrNotConfigured. It is not a degradation step — the caller gets one result.
+func (c *Chain) CloneVoice(ctx context.Context, referenceURL, prefix string) (string, error) {
+	if c.cloner == nil {
+		return "", ErrNotConfigured
+	}
+	return c.cloner.CloneVoice(ctx, referenceURL, prefix)
+}
+
 // TTS walks the chain for synthesized audio.
 func (c *Chain) TTS(ctx context.Context, text string) (Audio, error) {
 	if len(c.steps) == 0 {
@@ -98,8 +109,10 @@ func New(cfg config.VoiceConfig, opts ...Option) *Chain {
 	}
 
 	steps := make([]Provider, 0, 5)
+	var cloner VoiceCloner
 	if voiceConfigured(cfg) {
 		steps = append(steps, CloudProvider(newDashboardSTT(cfg), newDashboardTTS(cfg)))
+		cloner = newDashboardCloner(cfg)
 	}
 	switch cfg.TTSProvider {
 	case "edge-tts", "edge":
@@ -108,7 +121,9 @@ func New(cfg config.VoiceConfig, opts ...Option) *Chain {
 		steps = append(steps, EspeakProvider(newEspeak()))
 	}
 	steps = append(steps, SilentProvider())
-	return NewChain(steps...)
+	chain := NewChain(steps...)
+	chain.cloner = cloner
+	return chain
 }
 
 // voiceConfigured reports whether any cloud voice credential or model is set, so