{
  "docId": "019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "docSlug": "8757f1b44ef7f176",
  "documentTitle": "2024 Air Street Capital The State of AI Report 2024",
  "authorId": "AirStreetCapital",
  "authorName": "Air Street Capital",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "vc_research",
  "sourceTypeLabel": "VC research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.777,
  "pageNumber": 136,
  "pageCount": 213,
  "prevPage": 135,
  "nextPage": 137,
  "slideType": "industry_trends",
  "function": "summarize",
  "density": "dense",
  "nDataPoints": 0,
  "notes": "Includes a social media testimonial from Andrej Karpathy and a screenshot of the Kyutai Moshi interface.",
  "elementsJson": [
    "headline_text",
    "paragraph",
    "screenshot"
  ],
  "metadataConfidence": 0.95,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-0856e1444fb9/136",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9#slide-136",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "The launch OpenAI's GPT-4o and Paris-based Kyutai's Moshi voice agents crosses the uncanny valley.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d1b-be427cd9b370",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.3,
        "w": 0.35,
        "x": 0.62,
        "y": 0.6
      },
      "kind": "image",
      "text": "Kyutai Moshi interface",
      "attrs": null,
      "subkind": "screenshot",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "b962c65c-d2c1-4526-947f-efac2f7773f6",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.25,
        "w": 0.5,
        "x": 0.02,
        "y": 0.65
      },
      "kind": "image",
      "text": "Andrej Karpathy tweet about Deep Dive podcast",
      "attrs": null,
      "subkind": "screenshot",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "ced02cff-608a-4f7b-830c-30841390baae",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.4,
        "w": 0.96,
        "x": 0.02,
        "y": 0.22
      },
      "kind": "paragraph",
      "text": "For more than a decade, Alexa and Siri have delivered royally underwhelming consumer voice agent experiences. The launch OpenAI's GPT-4o and Paris-based Kyutai's Moshi voice agents crosses the uncanny valley. Both systems think and speak at the same time to ensure maximum flow between the speaker/agent. OpenAI showed how two phones running GPT-4o could hold a compelling voice conversation with one another. Moshi's inference speed was impressive and borderline too fast, producing occasionally jarring interruptions to the human speaker if they paused too long. Google's Notebook LM's ability to generate conversational podcasts based on research is also winning fans. More recently, Hugging Face implemented a speech-to-speech pipeline with voice activity detection, TTS, an LLM and text-to-speech.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "5dab371b-21ae-4c0a-8115-e163aab08b3f",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "quote",
      "text": "Deep Dive is now my favorite podcast. The more I listen the more I feel like I'm becoming friends with the hosts and I think this is the first time I've actually viscerally liked an AI. - Andrej Karpathy",
      "attrs": null,
      "subkind": null,
      "toolName": "Authority citation",
      "toolSlug": "authority-citation",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d1b-c1c53b8d725c",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.5,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "The next (uncanny) frontier: speech-to-speech?",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "78aec2e4-7a5f-4c43-9215-809d67cf9e9f",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 153,
      "from": 9,
      "beatId": "019dd95a-0682-776c-8e35-5f2398b8d1d0",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Exec summary + Research + Industry sections inventory the year",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 174,
      "from": 86,
      "beatId": "019dd95a-0682-776c-8e35-73133c63a096",
      "arcName": "Voyage and Return",
      "arcSlug": "voyage-return",
      "beatName": "Discoveries",
      "beatSlug": "voyage-return-discoveries",
      "evidence": "Industry + Politics findings on NVIDIA, regulation, geopolitics",
      "position": 3,
      "confidence": 55,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 136,
      "from": 131,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3e-5814a3b51188",
      "evidence": "ElevenLabs $1.1B, GenAI app growth, speech-recognition, GPT-4o/Moshi voice",
      "position": 15,
      "objective": "Document the rise of speech and audio interfaces",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 70,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}