Speech Recognition

{
  "skill_name": "speech-recognition",
  "evals": [
    {
      "id": 0,
      "name": "speechanalyzer-live-transcription",
      "prompt": "I'm building an iOS 26 meeting recorder with live transcript text and word highlighting during playback. Sketch the SpeechAnalyzer implementation shape, including model setup, audio input, result handling, and cleanup.",
      "expected_output": "An iOS 26 SpeechAnalyzer plan that uses current SpeechTranscriber APIs, installs assets, converts live audio buffers, handles volatile/final results, and explicitly finishes the analyzer session.",
      "files": [],
      "assertions": [
        "Uses SpeechAnalyzer with SpeechTranscriber and a documented preset such as .timeIndexedProgressiveTranscription, not .offlineTranscription.",
        "Checks SpeechTranscriber.isAvailable and supportedLocale(equivalentTo:) before starting transcription.",
        "Installs or verifies model assets with AssetInventory.assetInstallationRequest(supporting:) before analysis.",
        "Converts AVAudioEngine microphone buffers to SpeechAnalyzer.bestAvailableAudioFormat(compatibleWith:) before yielding AnalyzerInput.",
        "Handles volatile results separately from finalized results so live text is replaced rather than duplicated.",
        "Explicitly finalizes or cancels the analyzer session after input ends."
      ]
    },
    {
      "id": 1,
      "name": "sfspeechrecognizer-live-review",
      "prompt": "Review this iOS live dictation plan: request only NSSpeechRecognitionUsageDescription, start AVAudioEngine immediately, use SFSpeechRecognizer forever in one recognition task, force requiresOnDeviceRecognition for every locale, and ignore availability changes. Give corrected guidance and focused Swift snippets.",
      "expected_output": "A correction-focused SFSpeechRecognizer review that covers speech and microphone authorization, live audio setup, availability changes, on-device checks, task cleanup, and recognition duration limits.",
      "files": [],
      "assertions": [
        "Requires both NSSpeechRecognitionUsageDescription and NSMicrophoneUsageDescription for live microphone transcription.",
        "Requests speech recognition authorization and microphone record permission before activating the audio session or starting AVAudioEngine.",
        "Uses SFSpeechRecognizerDelegate or availability handling for recognition service changes.",
        "Checks supportsOnDeviceRecognition before setting requiresOnDeviceRecognition and gives a fallback when unsupported.",
        "Accounts for SFSpeechRecognizer recognition duration/service limits instead of running one unbounded task.",
        "Stops AVAudioEngine, removes the input tap, ends audio, and cancels or clears the recognition task during cleanup."
      ]
    },
    {
      "id": 2,
      "name": "speech-boundary-routing",
      "prompt": "A notes feature records a spoken note, transcribes it, detects the text language and sentiment, translates a summary to Spanish, plays back the recording with captions, and optionally uses Apple Intelligence to summarize it. Which parts belong in the speech-recognition skill and which should be handed to sibling skills?",
      "expected_output": "A boundary-aware routing answer that keeps speech-to-text and microphone capture in Speech, and routes text analysis, translation, playback UI, and generative summarization to the correct sibling skills.",
      "files": [],
      "assertions": [
        "Keeps microphone capture, speech authorization, SpeechAnalyzer or SFSpeechRecognizer transcription, and transcript result handling in the speech-recognition scope.",
        "Routes language detection, sentiment, text embeddings, and translation to the natural-language skill after transcription exists.",
        "Routes playback UI, captions during media playback, or AVPlayer/AVKit concerns to the avkit skill.",
        "Routes Apple Intelligence or Foundation Models summarization to the apple-on-devic