GenAI Speech Recognition API

implementation("com.google.mlkit:genai-speech-recognition:1.0.0-alpha1")

// 1. Create a SpeechRecognizer with desired options.
val options: SpeechRecognizerOptions =
    speechRecognizerOptions {
        locale = Locale.US
        preferredMode = SpeechRecognizerOptions.Mode.MODE_ADVANCED
    }
val speechRecognizer: SpeechRecognizer = SpeechRecognition.getClient(options)

// 2. Check if the recognition model is available or needs downloading.
launch {
    val status: Int = speechRecognizer.checkStatus()
    if (status == FeatureStatus.DOWNLOADABLE) {
        // 3. If needed, download the model and monitor progress.
        speechRecognizer.download.collect { downloadStatus ->
            when (downloadStatus) {
                is DownloadStatus.DownloadCompleted -> {
                    // Model is ready, start recognition.
                    startMyRecognition(speechRecognizer)
                }
                is DownloadStatus.DownloadFailed -> {
                    // Handle download failure (e.g., inform the user).
                }
                is DownloadStatus.DownloadProgress -> {
                    // Handle download progress (e.g., update a progress bar).
                }
            }
        }
    } else if (status == FeatureStatus.AVAILABLE) {
        // Model is already ready, start recognition immediately.
        startMyRecognition(speechRecognizer)
    } else {
        // Handle other statuses (e.g., DOWNLOADING, UNAVAILABLE).
    }
}

// 4. Define your recognition logic using a suspend function.
suspend fun startMyRecognition(recognizer: SpeechRecognizer) {
    // Create a request (e.g., specifying audio source).
    val request: SpeechRecognizerRequest
        = speechRecognizerRequest { audioSource = AudioSource.fromMic() }
    // Start recognition and process the continuous stream of responses.
    recognizer.startRecognition(request).collect {
        // Process the SpeechRecognitionResponse data here.
    }
}

// 5. Stop recognition and clean up resources when the session is complete.
launch {
    recognizer.stopRecognition()
    recognizer.close()
}

suspend fun recognizeFromFile(recognizer: SpeechRecognizer, audioFile: File) {
    val audioSource = AudioSource.fromFile(audioFile)
    val request = speechRecognizerRequest { this.audioSource = audioSource }
    try {
        recognizer.startRecognition(request).collect { response ->
            when (response) {
                is SpeechRecognizerResponse.FinalTextResponse -> {
                    // Process the transcription of the whole file.
                }
                is SpeechRecognizerResponse.ErrorResponse -> {
                    // Handle the error, for example an unsupported audio format.
                }
                else -> {}
            }
        }
    } finally {
        audioSource.close()
    }
}

suspend fun recognizeWithWordTiming(recognizer: SpeechRecognizer) {
    val request = speechRecognizerRequest {
        audioSource = AudioSource.fromMic()
        recognitionOptions { enableWordTiming = true }
    }
    recognizer.startRecognition(request).collect { response ->
        if (response is SpeechRecognizerResponse.FinalTextResponse) {
            for (wordTiming in response.wordTimings) {
                val word: String = wordTiming.text
                val timestamp: Long = wordTiming.timestampMs
            }
        }
    }
}