Quickstart

dependencies: [
    .package(url: "https://github.com/FluidInference/FluidAudio.git", from: "0.7.9"),
],

import FluidAudio

Task {
    let models = try await AsrModels.downloadAndLoad(version: .v3)
    let asrManager = AsrManager(config: .default)
    try await asrManager.initialize(models: models)

    let audioURL = URL(fileURLWithPath: "/path/to/audio.wav")
    let result = try await asrManager.transcribe(audioURL, source: .system)
    print("Transcription: \(result.text)")
}

import FluidAudio

Task {
    let models = try await DiarizerModels.downloadIfNeeded()
    let diarizer = DiarizerManager()
    diarizer.initialize(models: models)

    let samples = try AudioConverter().resampleAudioFile(
        URL(fileURLWithPath: "meeting.wav")
    )
    let result = try diarizer.performCompleteDiarization(samples)

    for segment in result.segments {
        print("Speaker \(segment.speakerId): \(segment.startTimeSeconds)s - \(segment.endTimeSeconds)s")
    }
}

import FluidAudio

Task {
    let manager = try await VadManager(
        config: VadConfig(defaultThreshold: 0.75)
    )

    let samples = try AudioConverter().resampleAudioFile(
        URL(fileURLWithPath: "audio.wav")
    )

    var segmentation = VadSegmentationConfig.default
    segmentation.minSpeechDuration = 0.25

    let segments = try await manager.segmentSpeech(samples, config: segmentation)
    for segment in segments {
        print(String(format: "Speech %.2f–%.2fs", segment.startTime, segment.endTime))
    }
}

import FluidAudioTTS

Task {
    let manager = TtSManager()
    try await manager.initialize()
    let audio = try await manager.synthesize(text: "Hello from FluidAudio!")
    try audio.write(to: URL(fileURLWithPath: "/tmp/demo.wav"))
}

# Transcribe
swift run fluidaudio transcribe audio.wav

# Diarize
swift run fluidaudio process meeting.wav --mode offline --threshold 0.6

# TTS
swift run fluidaudio tts "Hello from FluidAudio" --output out.wav