feat: add Cloudflare AI TTS engine (aura-2-en) with voice grouping in UI

backend/internal/backend/handlers.go

@@ -44,6 +44,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/libnovel/backend/internal/cfai"
 	"github.com/libnovel/backend/internal/domain"
 	"github.com/libnovel/backend/internal/kokoro"
 	"github.com/libnovel/backend/internal/meili"
@@ -774,7 +775,13 @@ func (s *Server) handleAudioStream(w http.ResponseWriter, r *http.Request) {
 	// Open the TTS stream (WAV or MP3 depending on format param).
 	var audioStream io.ReadCloser
 	if format == "wav" {
-		if pockettts.IsPocketTTSVoice(voice) {
+		if cfai.IsCFAIVoice(voice) {
+			if s.deps.CFAI == nil {
+				jsonError(w, http.StatusServiceUnavailable, "cloudflare AI TTS not configured")
+				return
+			}
+			audioStream, err = s.deps.CFAI.StreamAudioWAV(r.Context(), text, voice)
+		} else if pockettts.IsPocketTTSVoice(voice) {
 			if s.deps.PocketTTS == nil {
 				jsonError(w, http.StatusServiceUnavailable, "pocket-tts not configured")
 				return
@@ -788,7 +795,13 @@ func (s *Server) handleAudioStream(w http.ResponseWriter, r *http.Request) {
 			audioStream, err = s.deps.Kokoro.StreamAudioWAV(r.Context(), text, voice)
 		}
 	} else {
-		if pockettts.IsPocketTTSVoice(voice) {
+		if cfai.IsCFAIVoice(voice) {
+			if s.deps.CFAI == nil {
+				jsonError(w, http.StatusServiceUnavailable, "cloudflare AI TTS not configured")
+				return
+			}
+			audioStream, err = s.deps.CFAI.StreamAudioMP3(r.Context(), text, voice)
+		} else if pockettts.IsPocketTTSVoice(voice) {
 			if s.deps.PocketTTS == nil {
 				jsonError(w, http.StatusServiceUnavailable, "pocket-tts not configured")
 				return
@@ -1343,6 +1356,9 @@ func (s *Server) handlePresignVoiceSample(w http.ResponseWriter, r *http.Request
 	}
 
 	key := kokoro.VoiceSampleKey(voice)
+	if cfai.IsCFAIVoice(voice) {
+		key = cfai.VoiceSampleKey(voice)
+	}
 
 	// Generate sample on demand when it is not in MinIO yet.
 	if !s.deps.AudioStore.AudioExists(r.Context(), key) {
@@ -1352,7 +1368,13 @@ func (s *Server) handlePresignVoiceSample(w http.ResponseWriter, r *http.Request
 			mp3 []byte
 			err error
 		)
-		if pockettts.IsPocketTTSVoice(voice) {
+		if cfai.IsCFAIVoice(voice) {
+			if s.deps.CFAI == nil {
+				jsonError(w, http.StatusServiceUnavailable, "cloudflare AI TTS not configured")
+				return
+			}
+			mp3, err = s.deps.CFAI.GenerateAudio(r.Context(), voiceSampleText, voice)
+		} else if pockettts.IsPocketTTSVoice(voice) {
 			if s.deps.PocketTTS == nil {
 				jsonError(w, http.StatusServiceUnavailable, "pocket-tts not configured")
 				return

backend/internal/backend/server.go

@@ -30,6 +30,7 @@ import (
 
 	sentryhttp "github.com/getsentry/sentry-go/http"
 	"github.com/libnovel/backend/internal/bookstore"
+	"github.com/libnovel/backend/internal/cfai"
 	"github.com/libnovel/backend/internal/domain"
 	"github.com/libnovel/backend/internal/kokoro"
 	"github.com/libnovel/backend/internal/meili"
@@ -69,6 +70,9 @@ type Dependencies struct {
 	// PocketTTS is the pocket-tts client (used for voice list only in the backend;
 	// audio generation is done by the runner).
 	PocketTTS pockettts.Client
+	// CFAI is the Cloudflare Workers AI TTS client (used for voice sample
+	// generation and audio-stream live TTS; audio task generation is done by the runner).
+	CFAI cfai.Client
 	// Log is the structured logger.
 	Log *slog.Logger
 }
@@ -338,6 +342,23 @@ func (s *Server) voices(ctx context.Context) []domain.Voice {
 		}
 	}
 
+	// ── Cloudflare AI voices ──────────────────────────────────────────────────
+	if s.deps.CFAI != nil {
+		for _, speaker := range cfai.Speakers() {
+			gender := "m"
+			if cfai.IsFemale(speaker) {
+				gender = "f"
+			}
+			result = append(result, domain.Voice{
+				ID:     cfai.VoiceID(speaker),
+				Engine: "cfai",
+				Lang:   "en",
+				Gender: gender,
+			})
+		}
+		s.deps.Log.Info("backend: loaded CF AI voices", "count", len(cfai.Speakers()))
+	}
+
 	s.voiceMu.Lock()
 	s.cachedVoices = result
 	s.voiceMu.Unlock()