We’re trying to do speech to text on Apple Watch. How do we do that?

On iOS we're using SFSpeechRecognizer from Speech:

private let speechRecognizer = SFSpeechRecognizer(locale: Locale(identifier: "en-US"))
private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?
private var recognitionTask: SFSpeechRecognitionTask?
private let audioEngine = AVAudioEngine()

...this type of thing, but these services are not available on Apple Watch. We figure there has to be a way to do this since the watch has such limited input methods, and voice is an obvious way to be getting info from our user. Can we capture audio on the watch and use the iOS companion app to do the processing? Something else?

We're also doing text to speech, and aren't sure the best approach on Apple Watch for this either.

Thanks! -Ian