FAQ

brew install whisperkit-cli

let config = WhisperKitConfig(
    model: "large-v3",
    modelRepo: "username/your-model-repo"
)
let pipe = try await WhisperKit(config)

var options = DecodingOptions()
options.wordTimestamps = true

let result = try await pipe.transcribe(
    audioPath: "audio.wav",
    decodeOptions: options
)

// Access timestamps
for segment in result.segments {
    for word in segment.words {
        print("\(word.word): \(word.start) - \(word.end)")
    }
}

var options = DecodingOptions()
options.language = "es" // Spanish

let result = try await pipe.transcribe(
    audioPath: "audio.wav",
    decodeOptions: options
)

let pipe = try await WhisperKit()

// Start streaming
try await pipe.startRecording()

// Receive callbacks with transcription updates
pipe.onTranscriptionUpdate = { result in
    print(result.text)
}

// Stop when done
try await pipe.stopRecording()

var options = DecodingOptions()
options.task = .translate

let result = try await pipe.transcribe(
    audioPath: "spanish_audio.wav",
    decodeOptions: options
)
// Result is in English

let tts = try await TTSKit(TTSKitConfig(model: .qwen3TTS_1_7b))

var options = GenerationOptions()
options.instruction = "Speak slowly and warmly, like a storyteller."

let result = try await tts.generate(
    text: "Once upon a time...",
    options: options
)

try await tts.play(text: "This starts playing immediately.")

BUILD_ALL=1 swift run whisperkit-cli serve

from openai import OpenAI

client = OpenAI(base_url="http://localhost:50060/v1")

result = client.audio.transcriptions.create(
    file=open("audio.wav", "rb"),
    model="tiny"
)
print(result.text)

with client.audio.transcriptions.create(
    file=open("audio.wav", "rb"),
    model="tiny",
    stream=True
) as stream:
    for chunk in stream:
        print(chunk.text, end="", flush=True)