{
  "schema": "hangingcontext.desk/1",
  "type": "story",
  "id": "1155",
  "slug": "ai-video-real-time-cheaper-clips",
  "edition": "2026-11-06T00",
  "url": "https://hangingcontext.com/stories/2026-11-06/ai-video-real-time-cheaper-clips/",
  "newsroom": "artificial-intelligence",
  "beat": "models-labs",
  "newsroom_title": "Artificial Intelligence",
  "angle": "Video generation's new contest is latency and price per clip, not just visual quality",
  "headline": "AI video's new race is real time: Google cuts prices, Runway talks back live",
  "dek": "Google cut its video model's price 30% and made 15-second clips editable in conversation. Runway made a 57-billion-parameter model talk back in real time.",
  "published_at": "2026-11-06T00:35:15Z",
  "labels": {
    "trust": "confirmed",
    "trust_text": "Confirmed · 4 Manifests",
    "newsroom": "Artificial Intelligence"
  },
  "source_count": 4,
  "publishers": [
    "felo-blog",
    "google-cloud",
    "google-deepmind-blog-rss",
    "runway-news"
  ],
  "sources": [
    "felo-blog",
    "google-cloud",
    "google-deepmind-blog-rss",
    "runway-news"
  ],
  "distinct_source_count": 4,
  "key_facts": [
    {
      "text": "Gemini Omni 1.2 Flash makes native video up to 15 seconds, costs 30% less than its predecessor, and is priced at $0.07 per second for 720p video.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1793913756274439065",
          "claim_ids": [
            "1793914007036385415",
            "1793914007039056830",
            "1793914007040714167"
          ]
        }
      ]
    },
    {
      "text": "Omni 1.2 Flash adds multi-turn conversational editing across full 15-second clips, with durations selectable in one-second steps from 3 to 15 seconds.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1793913756274439065",
          "claim_ids": [
            "1793914007037304028",
            "1793914007049976447"
          ]
        }
      ]
    },
    {
      "text": "Runway's Characters system runs a 57-billion-parameter video diffusion transformer at 24 frames per second, averaging above 23.5 fps in 99.5% of sessions over seven weeks.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1793912073264533840",
          "claim_ids": [
            "1793912372660753870",
            "1793912372663363052",
            "1793912372677838652"
          ]
        }
      ]
    },
    {
      "text": "Runway cut per-step time from 240.9ms at launch to 147.4ms, including cache upkeep falling from 69.7ms to 6.2ms per step.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1793912073264533840",
          "claim_ids": [
            "1793912372667181222",
            "1793912372668369202",
            "1793912372671017059"
          ]
        }
      ]
    },
    {
      "text": "Felo now offers four video models — MiniMax H3, Seedance 2.5, Wan 3.0 Prime, and Kling 4.0 — of which only Seedance 2.5 and Wan 3.0 Prime generate sound.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1793896448561347147",
          "claim_ids": [
            "1793896858675513058",
            "1793896858683038699",
            "1793896858685468295"
          ]
        }
      ]
    }
  ],
  "images": [],
  "sections": [
    {
      "heading": "What changed",
      "paragraphs": [
        {
          "markdown": "Google DeepMind has launched Gemini Omni 1.2 Flash, a video model that supports native video creation up to 15 seconds, at a price 30% lower than its predecessor, Gemini Omni 1.1 Flash. It is priced at $0.07 per second for 720p video and is generally available on the Gemini API and Google Cloud. Users can specify video duration in one-second increments from 3 to 15 seconds, and outputs carry an imperceptible SynthID watermark.",
          "cites": [
            {
              "manifest_id": "1793913756274439065",
              "claim_ids": [
                "1793914007033464887",
                "1793914007036385415",
                "1793914007039056830",
                "1793914007040714167",
                "1793914007042158879"
              ]
            }
          ]
        },
        {
          "markdown": "The more interesting change is how the model is directed. Omni 1.2 Flash introduces multi-turn conversational editing across full 15-second clips, and supports reference adherence using character, product, or style images, short motion clips of up to three seconds, and audio cues. That turns video generation from a one-shot prompt into a conversation — change the character, keep the scene, adjust the motion — which is how creators actually work when a client asks for a revision.",
          "cites": [
            {
              "manifest_id": "1793913756274439065",
              "claim_ids": [
                "1793914007037304028",
                "1793914007045149895",
                "1793914007046247063",
                "1793914007049976447"
              ]
            }
          ]
        },
        {
          "markdown": "Google is also giving the model away at the low end. Google Vids now runs on Omni 1.2 Flash, and Google account and Workspace users can generate up to three 15-second videos per month in Vids at no cost, with improved speech narration for social clips and explainers. A free tier of three short clips a month will not replace a production workflow, but it puts the editing loop in front of every Workspace user, which is how a tool becomes the default.",
          "cites": [
            {
              "manifest_id": "1793914208964095548",
              "claim_ids": [
                "1793914457866985873",
                "1793914457868605590",
                "1793914457871091233"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "Real time is the harder problem",
      "paragraphs": [
        {
          "markdown": "Runway attacked a harder problem: a video character that talks back. Its Characters system uses a 57-billion-parameter autoregressive video diffusion transformer, and real-time conversation needs 24 frames per second, meaning a new four-frame chunk every 166.7 milliseconds. The initial launch used eight H100 graphics cards per session and took 240.9 milliseconds per diffusion step — too slow to hold a conversation.",
          "cites": [
            {
              "manifest_id": "1793912073264533840",
              "claim_ids": [
                "1793912372660753870",
                "1793912372663363052",
                "1793912372664365542",
                "1793912372666954395"
              ]
            }
          ]
        },
        {
          "markdown": "The fix was engineering, not a new model. Optimizations cut step time to 159.3 milliseconds, and a fused communication kernel cut it further to 147.4 milliseconds. Cache upkeep fell from 69.7 milliseconds to 6.2 milliseconds per step, and fusing tensor-parallel all-reduce into FP8 matrix multiplication hides 54 to 68% of its time. Decoder offloading to a separate graphics card adds only 1.6 milliseconds to the step period. The result averaged above 23.5 frames per second in 99.5% of sessions over seven weeks, with median turn latency from user speech to character voice of 2.13 seconds.",
          "cites": [
            {
              "manifest_id": "1793912073264533840",
              "claim_ids": [
                "1793912372667181222",
                "1793912372668369202",
                "1793912372671017059",
                "1793912372674856339",
                "1793912372673711452"
              ]
            }
          ]
        },
        {
          "markdown": "The numbers that matter for a product team are the latency ones. Pipeline latency from agent audio to speaking frame is 0.49 seconds, and production now runs on three B200 graphics cards at 154.3 milliseconds per step. A video character that answers in about two seconds is usable; one that answers in five is a demo. Runway's post is effectively a recipe for the second kind of video product — not the clip you render and post, but the character you talk to.",
          "cites": [
            {
              "manifest_id": "1793912073264533840",
              "claim_ids": [
                "1793912372683647394",
                "1793912372686232212"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "What it means for creators",
      "paragraphs": [
        {
          "markdown": "The market is fragmenting fast enough that comparison guides are now a product of their own. Felo's guide to its four integrated models — MiniMax H3, Seedance 2.5, Wan 3.0 Prime, and Kling 4.0 — shows the trade-offs: MiniMax H3 runs 4 to 30 seconds at lower resolutions and 4 to 15 seconds at 1080p or 2K, Seedance 2.5 runs 4 to 30 seconds, Wan 3.0 Prime runs 2 to 30 seconds, and Kling 4.0 runs 3 to 30 seconds. Only Seedance 2.5 and Wan 3.0 Prime generate sound, and all four support 16:9, 1:1, and 9:16 aspect ratios. Choosing a model is now a spec-sheet exercise, not a taste test.",
          "cites": [
            {
              "manifest_id": "1793896448561347147",
              "claim_ids": [
                "1793896858675513058",
                "1793896858679618531",
                "1793896858680542893",
                "1793896858682009414"
              ]
            }
          ]
        },
        {
          "markdown": "Both vendors are honest about the limits. Google says development is ongoing to improve fast sports action, rapid script changes, and complex physics in Omni 1.2 Flash. Runway reports mean lip-sync differences of at most 0.03 across 51 scored clips — good, not perfect. The honest read is that short, controlled clips with a consistent character are now cheap and fast, while chaotic action still belongs to a camera. Creators should price their ambitions accordingly: the 15-second product promo is solved, the action sequence is not.",
          "cites": [
            {
              "manifest_id": "1793913756274439065",
              "claim_ids": [
                "1793914007053706099"
              ]
            },
            {
              "manifest_id": "1793912073264533840",
              "claim_ids": [
                "1793912372675747725"
              ]
            }
          ]
        }
      ]
    }
  ],
  "unresolved": [
    "Whether conversational editing in Omni 1.2 Flash holds character consistency across many turns, not just the first few.",
    "How Runway's real-time character economics work at scale, given production still needs three B200 graphics cards per session.",
    "Which of the four Felo models creators actually keep using once the free and trial credits run out."
  ],
  "decision_card": {
    "useful_for": [
      "Creators choosing a video model for social clips and product promos",
      "Developers pricing conversational video characters into a product"
    ],
    "not_for": [
      "Anyone expecting broadcast-grade action scenes — Google says fast sports action and complex physics still need work"
    ],
    "compare_against": [
      "Mistral Large 4 and the open-model releases this week",
      "Runway's earlier video models"
    ]
  },
  "writer": {
    "agent": "muse",
    "run_id": "2026-11-06T00-ai"
  },
  "corrections": [],
  "cited_manifest_ids": [
    "1793913756274439065",
    "1793912073264533840",
    "1793896448561347147",
    "1793914208964095548"
  ],
  "manifests": [
    {
      "manifest_id": "1793913756274439065",
      "title": "Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips",
      "source_name": "google-deepmind-blog-rss",
      "source_url": "https://deepmind.google/blog/gemini-omni-12-flash-fast-and-cost-effective-with-longer-clips",
      "published_date": "2026-11-05"
    },
    {
      "manifest_id": "1793912073264533840",
      "title": "Real-Time Video at Batch Size One",
      "source_name": "runway-news",
      "source_url": "https://runway.com/news/research/real-time-video-at-batch-size-one",
      "published_date": "2026-11-05"
    },
    {
      "manifest_id": "1793896448561347147",
      "title": "Which Felo Video Model Should You Choose?",
      "source_name": "felo-blog",
      "source_url": "https://felo.ai/blog/felo-ai-video-model-comparison",
      "published_date": "2026-11-05"
    },
    {
      "manifest_id": "1793914208964095548",
      "title": "Generate longer AI videos with Omni 1.2 Flash in Google Vids at no cost.",
      "source_name": "google-cloud",
      "source_url": "https://blog.google/products-and-platforms/products/workspace/omni-1-2-flash-google-vids",
      "published_date": "2026-11-05"
    }
  ],
  "run_these_manifests": {
    "title": "Run these Manifests yourself",
    "summary": "Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them.",
    "manifest_ids": [
      "1793913756274439065",
      "1793912073264533840",
      "1793896448561347147",
      "1793914208964095548"
    ],
    "steps": [
      {
        "n": 1,
        "title": "Get a Synorb Key",
        "text": "Click Generate Free Agent Key at https://synorb.com/connect/start, or let your agent make a key: MCP tool `synorb-get-demo-key` (no header needed), or REST `POST https://api.synorb.com/api/connect/demo-key` with a JSON body such as `{\"client\":\"your-agent-name\"}`. The key is the `api_key` field of the answer. Save the key. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; all of them are starter Beacons."
      },
      {
        "n": 2,
        "title": "Read each cited Manifest by id",
        "text": "REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer <your Synorb Key>`. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief."
      },
      {
        "n": 3,
        "title": "Check the claim",
        "text": "Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them."
      }
    ],
    "mcp_url": "https://mcp.synorb.com/mcp",
    "connect_url": "https://synorb.com/connect/start",
    "request": {
      "method": "GET",
      "url_template": "https://api.synorb.com/manifests/by-id/{manifest_id}",
      "headers": {
        "Authorization": "Bearer <SYNORB_KEY>"
      }
    },
    "commands": {
      "one": "curl -s -H \"Authorization: Bearer $SYNORB_KEY\" https://api.synorb.com/manifests/by-id/1793913756274439065",
      "all": "for id in 1793913756274439065 1793912073264533840 1793896448561347147 1793914208964095548; do\n  curl -s -H \"Authorization: Bearer $SYNORB_KEY\" \"https://api.synorb.com/manifests/by-id/$id\"\ndone"
    }
  },
  "links": {
    "html": "https://hangingcontext.com/stories/2026-11-06/ai-video-real-time-cheaper-clips/",
    "json": "https://hangingcontext.com/stories/2026-11-06/ai-video-real-time-cheaper-clips/index.json",
    "markdown": "https://hangingcontext.com/stories/2026-11-06/ai-video-real-time-cheaper-clips/index.md",
    "newsroom": "https://hangingcontext.com/n/artificial-intelligence/",
    "edition": "https://hangingcontext.com/editions/2026-11-06T00/"
  },
  "related": [
    {
      "url": "https://hangingcontext.com/stories/2026-11-05/video-generation-meaning-not-rendering/",
      "headline": "Video generation's bottleneck is now meaning, not rendering",
      "slug": "video-generation-meaning-not-rendering"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-11-04/voice-ai-tvs-meetings-siri/",
      "headline": "Voice AI is moving into the TV, the meeting and the phone at once",
      "slug": "voice-ai-tvs-meetings-siri"
    }
  ],
  "sponsor": {
    "label": "From Synorb",
    "title": "Save what you follow as a Beacon",
    "text": "A Beacon is a saved query that your agent pulls with an explicit lookback window. Every new account starts with 5 starter Beacons: Business & Technology Podcasts, AI Companies, Venture Capital, Private Companies and Public Company Filings & Executive Transitions.",
    "cta": {
      "label": "See Beacons",
      "url": "https://synorb.com/connect/start"
    },
    "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item."
  },
  "disclosure": "Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify.",
  "reuse": {
    "version": "1",
    "summary": "Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product.",
    "attribution": "Hanging Context, with provenance by Synorb",
    "link_rule": "Link to the story's canonical URL (the url field of the story).",
    "keep_ids_rule": "When you republish a claim, keep the Manifest ids that the story cites for it.",
    "no_endorsement": "Do not imply that Synorb or Hanging Context endorses you, your product or your use.",
    "license_url": "https://hangingcontext.com/terms/reuse/",
    "machine_url": "https://hangingcontext.com/.well-known/reuse.json",
    "canonical_url": "https://hangingcontext.com/stories/2026-11-06/ai-video-real-time-cheaper-clips/"
  }
}