음성 복제

let (model, encoder) = try await Qwen3TTSModel.fromPretrainedWithEncoder()
let audio = model.synthesizeWithVoiceCloneICL(
    text: "Target text to synthesize.",
    referenceAudio: refSamples,
    referenceSampleRate: 24000,
    referenceText: "Exact transcript of reference audio.",
    language: "english",
    codecEncoder: encoder
)

# CosyVoice3 voice cloning (CAM++, CoreML Neural Engine)
.build/release/speech speak "Text in the cloned voice" \
    --engine cosyvoice --voice-sample reference.wav -o output.wav

# IndexTTS2 voice cloning (expanded MLX bundle)
.build/release/speech speak "Text in the cloned voice" \
    --engine indextts2 --voice-sample reference.wav \
    --indextts2-speaking-rate 1.35 \
    --indextts2-max-pause 0.05 \
    -o output.wav

# F5-TTS voice cloning (reference + transcript, MLX GPU)
.build/release/speech speak "Text in the cloned voice" \
    --engine f5 --voice-sample reference.wav \
    --f5-reference-text "Transcript of the reference clip." -o output.wav

# Higgs TTS 3 voice cloning (4B, expressive, MLX GPU)
.build/release/speech speak "Text in the cloned voice" \
    --engine higgs --voice-sample reference.wav \
    --higgs-ref-text "Transcript of the reference clip." -o output.wav

# Qwen3-TTS voice cloning (ECAPA-TDNN, MLX GPU)
.build/release/speech speak "Text in the cloned voice" \
    --voice-sample reference.wav -o output.wav

# CosyVoice3: multilingual voice cloning (9 languages)
.build/release/speech speak "Hello, this is my cloned voice." \
    --engine cosyvoice --voice-sample my_voice.wav -o cloned_hello.wav

# CosyVoice3: clone voice in a different language
.build/release/speech speak "Guten Tag, das ist meine geklonte Stimme." \
    --engine cosyvoice --voice-sample my_voice.wav --language german -o german.wav

# Qwen3-TTS: English voice cloning
.build/release/speech speak "The quick brown fox jumps over the lazy dog." \
    --voice-sample recording_15s.wav -o cloned_fox.wav

# IndexTTS2: local exported bundle
.build/release/speech speak "This voice was cloned locally." \
    --engine indextts2 --voice-sample my_voice.wav \
    --indextts2-speaking-rate 1.35 \
    --indextts2-max-pause 0.05 \
    --indextts2-bundle-dir /path/to/IndexTTS2-MLX-fp16 \
    -o indextts2.wav

# Two-speaker dialogue with voice cloning
.build/release/speech speak "[S1] Hello there! [S2] Hey, how are you?" \
    --engine cosyvoice --speakers s1=alice.wav,s2=bob.wav -o dialogue.wav

# Dialogue with emotion tags + voice cloning
.build/release/speech speak "[S1] (happy) Great news! [S2] (surprised) Really? Tell me more." \
    --engine cosyvoice --speakers s1=alice.wav,s2=bob.wav -o emotional_dialogue.wav

# Adjust silence between turns
.build/release/speech speak "[S1] First line. [S2] Second line." \
    --engine cosyvoice --speakers s1=a.wav,s2=b.wav --turn-gap 0.5 -o gapped.wav

import CosyVoiceTTS

// CosyVoice3 voice cloning
let model = try await CosyVoiceTTSModel.fromPretrained()
let speaker = try await CamPlusPlusSpeaker.fromPretrained()

// Extract 192-dim speaker embedding from reference audio
let embedding = try speaker.embed(audio: refSamples, sampleRate: 16000)

// Synthesize with cloned voice
let audio = model.synthesize(
    text: "Hello in a cloned voice!",
    speakerEmbedding: embedding
)

// With custom instruction + speaker embedding
let styledAudio = model.synthesize(
    text: "Hello!",
    instruction: "Speak happily and with excitement.",
    speakerEmbedding: embedding
)

// Multi-speaker dialogue
let segments = DialogueParser.parse("[S1] (happy) Hi! [S2] Hey there.")
let embeddings = ["S1": aliceEmbedding, "S2": bobEmbedding]
let dialogueAudio = DialogueSynthesizer.synthesize(
    segments: segments,
    speakerEmbeddings: embeddings,
    model: model,
    language: "english"
)

import Qwen3TTS

// Qwen3-TTS voice cloning
let model = try await Qwen3TTSModel.fromPretrained()
let audio = model.synthesizeWithVoiceClone(
    text: "Hello in a cloned voice!",
    referenceAudio: refSamples,
    referenceSampleRate: 24000
)

import IndexTTS2TTS

// IndexTTS2 zero-shot voice cloning
let model = try await IndexTTS2TTSModel.fromPretrained()
let audio = try await model.generate(
    text: "Hello in a cloned voice!",
    referenceAudio: URL(fileURLWithPath: "reference.wav"),
    synthesisOptions: try IndexTTS2SynthesisOptions(
        speakingRate: 1.35,
        maxInternalPauseDuration: 0.05)
)

let tts = try await Qwen3TTSModel.fromPretrained()

// First call: runs ECAPA-TDNN, caches the embedding
_ = tts.synthesizeWithVoiceClone(text: "Hello", referenceAudio: ref, ...)

// Subsequent calls with the same reference: cache hit
_ = tts.synthesizeWithVoiceClone(text: "How are you?", referenceAudio: ref, ...)

// Explicit eviction (rarely needed — LRU handles capacity)
tts.clearReferenceAudioCache()