Kokoro TTS

swift run fluidaudio tts "Welcome to FluidAudio text to speech" \
  --output ~/Desktop/demo.wav \
  --voice af_heart

import FluidAudioTTS

let manager = TtSManager()
try await manager.initialize()

let audioData = try await manager.synthesize(text: "Hello from FluidAudio!")
try audioData.write(to: URL(fileURLWithPath: "/tmp/demo.wav"))

let detailed = try await manager.synthesizeDetailed(
    text: "FluidAudio can report chunk splits for you.",
    variantPreference: .fifteenSecond
)

for chunk in detailed.chunks {
    print("Chunk #\(chunk.index) -> variant: \(chunk.variant), tokens: \(chunk.tokenCount)")
    print("  text: \(chunk.text)")
}

text → espeak G2P → IPA phonemes → Kokoro model → audio
         ↑                ↑
   custom lexicon    SSML <phoneme>
   overrides here    overrides here

dependencies: [
    .package(url: "https://github.com/FluidInference/FluidAudio.git", from: "0.7.7"),
],
targets: [
    .target(
        name: "YourTarget",
        dependencies: [
            .product(name: "FluidAudioWithTTS", package: "FluidAudio")
        ]
    )
]

import FluidAudio       // Core (ASR, diarization, VAD)
import FluidAudioTTS    // TTS features