API và giao thức

┌─────────────────────────────────────────────────────────┐
│                    AudioCommon                          │
│                                                         │
│  AudioChunk          SpeechGenerationModel (TTS)        │
│  AlignedWord         SpeechRecognitionModel (STT)       │
│  SpeechSegment       ForcedAlignmentModel               │
│                      SpeechToSpeechModel                │
│                      VoiceActivityDetectionModel (VAD)   │
│                      SpeakerEmbeddingModel              │
│                      SpeakerDiarizationModel            │
│                      SpeakerExtractionCapable           │
└─────────────────────────────────────────────────────────┘

public protocol SpeechRecognitionModel: AnyObject {
    var inputSampleRate: Int { get }
    func transcribe(audio: [Float], sampleRate: Int, language: String?) -> String
    func transcribeWithLanguage(audio: [Float], sampleRate: Int, language: String?) -> TranscriptionResult
}

public protocol SpeechGenerationModel: AnyObject {
    var sampleRate: Int { get }
    func generate(text: String, language: String?) async throws -> [Float]
    func generateStream(text: String, language: String?) -> AsyncThrowingStream<AudioChunk, Error>  // has default impl
}

public protocol ForcedAlignmentModel: AnyObject {
    func align(audio: [Float], text: String, sampleRate: Int, language: String?) -> [AlignedWord]
}

public protocol SpeechToSpeechModel: AnyObject {
    var sampleRate: Int { get }
    func respond(userAudio: [Float]) -> [Float]
    func respondStream(userAudio: [Float]) -> AsyncThrowingStream<AudioChunk, Error>
}

public protocol VoiceActivityDetectionModel: AnyObject {
    var inputSampleRate: Int { get }
    func detectSpeech(audio: [Float], sampleRate: Int) -> [SpeechSegment]
}

public protocol SpeakerEmbeddingModel: AnyObject {
    var inputSampleRate: Int { get }
    var embeddingDimension: Int { get }
    func embed(audio: [Float], sampleRate: Int) -> [Float]
}

public protocol SpeakerDiarizationModel: AnyObject {
    var inputSampleRate: Int { get }
    func diarize(audio: [Float], sampleRate: Int) -> [DiarizedSegment]
}

public protocol SpeakerExtractionCapable: SpeakerDiarizationModel {
    func extractSpeaker(audio: [Float], sampleRate: Int, targetEmbedding: [Float]) -> [SpeechSegment]
}

public struct AudioChunk {
    public let samples: [Float]   // PCM samples
    public let sampleRate: Int    // Sample rate (e.g. 24000)
}

public struct SpeechSegment {
    public let startTime: Float   // Start time in seconds
    public let endTime: Float     // End time in seconds
}

public struct AlignedWord {
    public let text: String       // The word
    public let startTime: Float   // Start time in seconds
    public let endTime: Float     // End time in seconds
}

public struct DiarizedSegment {
    public let startTime: Float   // Start time in seconds
    public let endTime: Float     // End time in seconds
    public let speakerId: Int     // Speaker identifier (0-based)
}

public struct DialogueSegment: Sendable, Equatable {
    public let speaker: String?   // Speaker identifier ("S1", "S2"), nil for untagged
    public let emotion: String?   // Emotion tag ("happy", "whispers"), nil if none
    public let text: String       // Cleaned text to synthesize
}

public enum DialogueParser {
    static func parse(_ text: String) -> [DialogueSegment]
    static func emotionToInstruction(_ emotion: String) -> String
}

public enum DialogueSynthesizer {
    static func synthesize(
        segments: [DialogueSegment],
        speakerEmbeddings: [String: [Float]],
        model: CosyVoiceTTSModel,
        language: String,
        config: DialogueSynthesisConfig,
        verbose: Bool
    ) -> [Float]
}

public struct DialogueSynthesisConfig: Sendable {
    public var turnGapSeconds: Float      // Default: 0.2
    public var crossfadeSeconds: Float    // Default: 0.0
    public var defaultInstruction: String // Default: "You are a helpful assistant."
    public var maxTokensPerSegment: Int   // Default: 500
}

public protocol PipelineLLM: AnyObject {
    func chat(messages: [(role: MessageRole, content: String)],
              onToken: @escaping (String, Bool) -> Void)
    func cancel()
}

let audio = AudioIO()
try audio.startMicrophone(targetSampleRate: 16000) { samples in
    pipeline.pushAudio(samples)
}
audio.player.scheduleChunk(ttsOutput)
audio.stopMicrophone()

public struct SentencePieceModel: Sendable {
    public struct Piece: Sendable, Equatable {
        public let text: String
        public let score: Float
        public let type: Int32
        public var pieceType: PieceType? { get }
        public var isControlOrUnknown: Bool { get }
    }
    public enum PieceType: Int32 {
        case normal = 1, unknown = 2, control = 3,
             userDefined = 4, unused = 5, byte = 6
    }
    public let pieces: [Piece]
    public var count: Int { get }
    public subscript(_ id: Int) -> Piece? { get }
    public init(contentsOf url: URL) throws
    public init(modelPath: String) throws
    public init(data: Data) throws
}

public enum SDPA {
    // Flat [B, T, H*D] input: project/reshape happens inside
    public static func multiHead(
        q: MLXArray, k: MLXArray, v: MLXArray,
        numHeads: Int, headDim: Int, scale: Float,
        mask: MLXArray? = nil
    ) -> MLXArray

    // GQA / MQA variant with separate query and KV head counts
    public static func multiHead(
        q: MLXArray, k: MLXArray, v: MLXArray,
        numQueryHeads: Int, numKVHeads: Int, headDim: Int, scale: Float,
        mask: MLXArray? = nil
    ) -> MLXArray

    // Already-shaped [B, H, T, D] (RoPE / KV cache paths)
    public static func attendAndMerge(
        qHeads: MLXArray, kHeads: MLXArray, vHeads: MLXArray,
        scale: Float,
        mask: MLXArray? = nil
    ) -> MLXArray

    // Same, with ScaledDotProductAttentionMaskMode enum (newer API)
    public static func attendAndMerge(
        qHeads: MLXArray, kHeads: MLXArray, vHeads: MLXArray,
        scale: Float,
        mask: MLXFast.ScaledDotProductAttentionMaskMode
    ) -> MLXArray

    // Low-level head merge: [B, H, T, D] → [B, T, H*D]
    public static func mergeHeads(_ attn: MLXArray) -> MLXArray
}

swift build -c release
.build/release/speech-server --port 8080

# Tải sẵn mọi mô hình khi khởi động
.build/release/speech-server --port 8080 --preload

# Chuyển một tệp thành văn bản
curl -X POST http://localhost:8080/transcribe \
  --data-binary @recording.wav \
  -H "Content-Type: audio/wav"

# Tổng hợp giọng nói
curl -X POST http://localhost:8080/speak \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello world", "engine": "cosyvoice"}' \
  -o output.wav

# Vòng giọng nói tới giọng nói đầy đủ
curl -X POST http://localhost:8080/respond \
  --data-binary @question.wav \
  -o response.wav

const ws = new WebSocket('ws://localhost:8080/v1/realtime');

// ASR: push audio, request transcription
ws.send(JSON.stringify({ type: 'input_audio_buffer.append', audio: base64PCM16 }));
ws.send(JSON.stringify({ type: 'input_audio_buffer.commit' }));
// → conversation.item.input_audio_transcription.completed

// TTS: request synthesis and stream audio deltas
ws.send(JSON.stringify({
  type: 'response.create',
  response: { modalities: ['audio', 'text'], instructions: 'Hello world' }
}));
// → response.audio.delta (repeated), response.audio.done, response.done