live
MODEL IDalibaba:wan@2.7

Wan2.7

Alibaba
by

Wan2.7 is Alibaba's next-generation multimodal video model supporting text-to-video, image-to-video, reference-to-video, and video editing. It features multi-shot storytelling, subject-consistent multi-character generation, first-and-last-frame interpolation, video continuation, style transfer, instruction-based editing, and audio-conditioned generation with auto-dubbing. Output at 720p or 1080p, 30 FPS in multiple aspect ratios.

Wan2.7

text-to-video

Municipal Noir Limited Series Teaser$2.25~6m 58s
Try in Playground
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'alibaba:wan@2.7',
  positivePrompt: 'Create a finished 15-second cinematic title teaser for a prestige limited series called “THE MINUTES,” a municipal noir conspiracy drama centered on a city records archivist. Landscape 16:9. Photorealistic 35mm film texture, severe brutalist compositions, shallow focus, nicotine amber and oxidized green palette, deep blacks, restrained camera movement, ominous procedural realism.\n\n0–3 seconds: extreme macro shot of a dented metal microfilm reel beginning to rotate inside an old archive reader. Dust trembles in the projector beam. The camera creeps forward as tiny reversed council records flicker across the film. Synchronized audio: fluorescent electrical hum, reel mechanism engaging, dry film chatter.\n\n3–6 seconds: hard cut on a mechanical click to an overhead shot of gloved hands opening a water-damaged city council ledger on a scarred institutional desk. Several names are hidden beneath thick black redactions; damp paper fibers catch the amber task light. A rubber date stamp strikes the page once, precisely on the cut. Synchronized audio: paper drag, heavy stamp impact, low sub-bass pulse beginning beneath the room tone.\n\n6–9 seconds: match cut from the circular stamp to a corroded ceiling drain in an empty underground records corridor. A single drop falls toward the lens. Rows of olive filing cabinets recede symmetrically into darkness while fluorescent tubes switch off one by one from the far end toward camera. Slow backward dolly. Audio: isolated water drop, sequential ballast snaps, growing ventilation rumble.\n\n9–12 seconds: close tracking shot along drawer labels and evidence tags as an unseen force pulls one cabinet drawer open. Inside is a pristine cream envelope marked only with a small embossed city seal, no other readable text. The camera stops abruptly as the envelope edge enters a razor-thin shaft of light. Audio: metal drawer scrape, paper whisper, one distant gavel strike with a long architectural echo.\n\n12–15 seconds: cut to black for half a beat, then reveal the title “THE MINUTES” centered in large, sharply legible ivory condensed serif capitals, appearing as if pressed into black archival paper. A thin oxidized-green rule sits beneath the title. No subtitle, credits, logos, or additional words. Hold long enough to read. Audio resolves into a final projector click, the sub-bass cuts out, and only the fluorescent hum remains before sudden silence. Elegant editorial pacing, clean cuts motivated by sound, controlled suspense rather than horror.',
  negativePrompt: 'Fantasy imagery, futuristic technology, glossy sci-fi styling, action spectacle, visible faces, gore, comedy, blue-orange blockbuster grading, handheld shake, rapid montage, illegible title, misspelled words, extra captions, credits, logos, watermarks, interface elements, subtitles.',
  width: 1920,
  height: 1080,
  duration: 15,
  settings: {
    audio: true
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "alibaba:wan@2.7",
            "positivePrompt": "Create a finished 15-second cinematic title teaser for a prestige limited series called “THE MINUTES,” a municipal noir conspiracy drama centered on a city records archivist. Landscape 16:9. Photorealistic 35mm film texture, severe brutalist compositions, shallow focus, nicotine amber and oxidized green palette, deep blacks, restrained camera movement, ominous procedural realism.\n\n0–3 seconds: extreme macro shot of a dented metal microfilm reel beginning to rotate inside an old archive reader. Dust trembles in the projector beam. The camera creeps forward as tiny reversed council records flicker across the film. Synchronized audio: fluorescent electrical hum, reel mechanism engaging, dry film chatter.\n\n3–6 seconds: hard cut on a mechanical click to an overhead shot of gloved hands opening a water-damaged city council ledger on a scarred institutional desk. Several names are hidden beneath thick black redactions; damp paper fibers catch the amber task light. A rubber date stamp strikes the page once, precisely on the cut. Synchronized audio: paper drag, heavy stamp impact, low sub-bass pulse beginning beneath the room tone.\n\n6–9 seconds: match cut from the circular stamp to a corroded ceiling drain in an empty underground records corridor. A single drop falls toward the lens. Rows of olive filing cabinets recede symmetrically into darkness while fluorescent tubes switch off one by one from the far end toward camera. Slow backward dolly. Audio: isolated water drop, sequential ballast snaps, growing ventilation rumble.\n\n9–12 seconds: close tracking shot along drawer labels and evidence tags as an unseen force pulls one cabinet drawer open. Inside is a pristine cream envelope marked only with a small embossed city seal, no other readable text. The camera stops abruptly as the envelope edge enters a razor-thin shaft of light. Audio: metal drawer scrape, paper whisper, one distant gavel strike with a long architectural echo.\n\n12–15 seconds: cut to black for half a beat, then reveal the title “THE MINUTES” centered in large, sharply legible ivory condensed serif capitals, appearing as if pressed into black archival paper. A thin oxidized-green rule sits beneath the title. No subtitle, credits, logos, or additional words. Hold long enough to read. Audio resolves into a final projector click, the sub-bass cuts out, and only the fluorescent hum remains before sudden silence. Elegant editorial pacing, clean cuts motivated by sound, controlled suspense rather than horror.",
            "negativePrompt": "Fantasy imagery, futuristic technology, glossy sci-fi styling, action spectacle, visible faces, gore, comedy, blue-orange blockbuster grading, handheld shake, rapid montage, illegible title, misspelled words, extra captions, credits, logos, watermarks, interface elements, subtitles.",
            "width": 1920,
            "height": 1080,
            "duration": 15,
            "settings": {
                "audio": True
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "videoInference",
      "taskUUID": "5d33440c-55f7-4ac2-a7af-8820a5a7fa2b",
      "model": "alibaba:wan@2.7",
      "positivePrompt": "Create a finished 15-second cinematic title teaser for a prestige limited series called “THE MINUTES,” a municipal noir conspiracy drama centered on a city records archivist. Landscape 16:9. Photorealistic 35mm film texture, severe brutalist compositions, shallow focus, nicotine amber and oxidized green palette, deep blacks, restrained camera movement, ominous procedural realism.\n\n0–3 seconds: extreme macro shot of a dented metal microfilm reel beginning to rotate inside an old archive reader. Dust trembles in the projector beam. The camera creeps forward as tiny reversed council records flicker across the film. Synchronized audio: fluorescent electrical hum, reel mechanism engaging, dry film chatter.\n\n3–6 seconds: hard cut on a mechanical click to an overhead shot of gloved hands opening a water-damaged city council ledger on a scarred institutional desk. Several names are hidden beneath thick black redactions; damp paper fibers catch the amber task light. A rubber date stamp strikes the page once, precisely on the cut. Synchronized audio: paper drag, heavy stamp impact, low sub-bass pulse beginning beneath the room tone.\n\n6–9 seconds: match cut from the circular stamp to a corroded ceiling drain in an empty underground records corridor. A single drop falls toward the lens. Rows of olive filing cabinets recede symmetrically into darkness while fluorescent tubes switch off one by one from the far end toward camera. Slow backward dolly. Audio: isolated water drop, sequential ballast snaps, growing ventilation rumble.\n\n9–12 seconds: close tracking shot along drawer labels and evidence tags as an unseen force pulls one cabinet drawer open. Inside is a pristine cream envelope marked only with a small embossed city seal, no other readable text. The camera stops abruptly as the envelope edge enters a razor-thin shaft of light. Audio: metal drawer scrape, paper whisper, one distant gavel strike with a long architectural echo.\n\n12–15 seconds: cut to black for half a beat, then reveal the title “THE MINUTES” centered in large, sharply legible ivory condensed serif capitals, appearing as if pressed into black archival paper. A thin oxidized-green rule sits beneath the title. No subtitle, credits, logos, or additional words. Hold long enough to read. Audio resolves into a final projector click, the sub-bass cuts out, and only the fluorescent hum remains before sudden silence. Elegant editorial pacing, clean cuts motivated by sound, controlled suspense rather than horror.",
      "negativePrompt": "Fantasy imagery, futuristic technology, glossy sci-fi styling, action spectacle, visible faces, gore, comedy, blue-orange blockbuster grading, handheld shake, rapid montage, illegible title, misspelled words, extra captions, credits, logos, watermarks, interface elements, subtitles.",
      "width": 1920,
      "height": 1080,
      "duration": 15,
      "settings": {
        "audio": true
      }
    }
  ]'
runware run alibaba:wan@2.7 \
  positivePrompt="Create a finished 15-second cinematic title teaser for a prestige limited series called “THE MINUTES,” a municipal noir conspiracy drama centered on a city records archivist. Landscape 16:9. Photorealistic 35mm film texture, severe brutalist compositions, shallow focus, nicotine amber and oxidized green palette, deep blacks, restrained camera movement, ominous procedural realism.

0–3 seconds: extreme macro shot of a dented metal microfilm reel beginning to rotate inside an old archive reader. Dust trembles in the projector beam. The camera creeps forward as tiny reversed council records flicker across the film. Synchronized audio: fluorescent electrical hum, reel mechanism engaging, dry film chatter.

3–6 seconds: hard cut on a mechanical click to an overhead shot of gloved hands opening a water-damaged city council ledger on a scarred institutional desk. Several names are hidden beneath thick black redactions; damp paper fibers catch the amber task light. A rubber date stamp strikes the page once, precisely on the cut. Synchronized audio: paper drag, heavy stamp impact, low sub-bass pulse beginning beneath the room tone.

6–9 seconds: match cut from the circular stamp to a corroded ceiling drain in an empty underground records corridor. A single drop falls toward the lens. Rows of olive filing cabinets recede symmetrically into darkness while fluorescent tubes switch off one by one from the far end toward camera. Slow backward dolly. Audio: isolated water drop, sequential ballast snaps, growing ventilation rumble.

9–12 seconds: close tracking shot along drawer labels and evidence tags as an unseen force pulls one cabinet drawer open. Inside is a pristine cream envelope marked only with a small embossed city seal, no other readable text. The camera stops abruptly as the envelope edge enters a razor-thin shaft of light. Audio: metal drawer scrape, paper whisper, one distant gavel strike with a long architectural echo.

12–15 seconds: cut to black for half a beat, then reveal the title “THE MINUTES” centered in large, sharply legible ivory condensed serif capitals, appearing as if pressed into black archival paper. A thin oxidized-green rule sits beneath the title. No subtitle, credits, logos, or additional words. Hold long enough to read. Audio resolves into a final projector click, the sub-bass cuts out, and only the fluorescent hum remains before sudden silence. Elegant editorial pacing, clean cuts motivated by sound, controlled suspense rather than horror." \
  negativePrompt="Fantasy imagery, futuristic technology, glossy sci-fi styling, action spectacle, visible faces, gore, comedy, blue-orange blockbuster grading, handheld shake, rapid montage, illegible title, misspelled words, extra captions, credits, logos, watermarks, interface elements, subtitles." \
  width=1920 \
  height=1080 \
  duration=15 \
  settings.audio=true
{
  "taskType": "videoInference",
  "taskUUID": "5d33440c-55f7-4ac2-a7af-8820a5a7fa2b",
  "model": "alibaba:wan@2.7",
  "positivePrompt": "Create a finished 15-second cinematic title teaser for a prestige limited series called “THE MINUTES,” a municipal noir conspiracy drama centered on a city records archivist. Landscape 16:9. Photorealistic 35mm film texture, severe brutalist compositions, shallow focus, nicotine amber and oxidized green palette, deep blacks, restrained camera movement, ominous procedural realism.\n\n0–3 seconds: extreme macro shot of a dented metal microfilm reel beginning to rotate inside an old archive reader. Dust trembles in the projector beam. The camera creeps forward as tiny reversed council records flicker across the film. Synchronized audio: fluorescent electrical hum, reel mechanism engaging, dry film chatter.\n\n3–6 seconds: hard cut on a mechanical click to an overhead shot of gloved hands opening a water-damaged city council ledger on a scarred institutional desk. Several names are hidden beneath thick black redactions; damp paper fibers catch the amber task light. A rubber date stamp strikes the page once, precisely on the cut. Synchronized audio: paper drag, heavy stamp impact, low sub-bass pulse beginning beneath the room tone.\n\n6–9 seconds: match cut from the circular stamp to a corroded ceiling drain in an empty underground records corridor. A single drop falls toward the lens. Rows of olive filing cabinets recede symmetrically into darkness while fluorescent tubes switch off one by one from the far end toward camera. Slow backward dolly. Audio: isolated water drop, sequential ballast snaps, growing ventilation rumble.\n\n9–12 seconds: close tracking shot along drawer labels and evidence tags as an unseen force pulls one cabinet drawer open. Inside is a pristine cream envelope marked only with a small embossed city seal, no other readable text. The camera stops abruptly as the envelope edge enters a razor-thin shaft of light. Audio: metal drawer scrape, paper whisper, one distant gavel strike with a long architectural echo.\n\n12–15 seconds: cut to black for half a beat, then reveal the title “THE MINUTES” centered in large, sharply legible ivory condensed serif capitals, appearing as if pressed into black archival paper. A thin oxidized-green rule sits beneath the title. No subtitle, credits, logos, or additional words. Hold long enough to read. Audio resolves into a final projector click, the sub-bass cuts out, and only the fluorescent hum remains before sudden silence. Elegant editorial pacing, clean cuts motivated by sound, controlled suspense rather than horror.",
  "negativePrompt": "Fantasy imagery, futuristic technology, glossy sci-fi styling, action spectacle, visible faces, gore, comedy, blue-orange blockbuster grading, handheld shake, rapid montage, illegible title, misspelled words, extra captions, credits, logos, watermarks, interface elements, subtitles.",
  "width": 1920,
  "height": 1080,
  "duration": 15,
  "settings": {
    "audio": true
  }
}
Response
{
  "taskType": "videoInference",
  "taskUUID": "5d33440c-55f7-4ac2-a7af-8820a5a7fa2b",
  "videoUUID": "3a71d990-d28f-46ca-8015-f4d9e6f058bd",
  "videoURL": "https://vm.runware.ai/video/os/a10dlim3/ws/5/vi/3a71d990-d28f-46ca-8015-f4d9e6f058bd.mp4",
  "seed": 809954976,
  "cost": 2.2534
}

first-frame

Urban Beekeeping Suit Showcase Reel$0.756~51s
Try in Playground
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'alibaba:wan@2.7',
  positivePrompt: 'Continue directly from the supplied first frame as a polished five-second vertical fashion showcase, preserving the same model, facial appearance, ivory beekeeping suit, copper-mesh hood, gloves, honey extractor, vermilion studio, lighting, and centered composition. The model makes a slow controlled quarter-turn while sliding one gloved hand along the reinforced cuff, revealing the suit\'s articulated sleeve, utility pocket, and tailored side profile. A gentle studio fan creates subtle movement in the fabric without disturbing the hood. The camera performs a smooth, restrained push-in with a slight clockwise arc, ending on a confident three-quarter pose as amber light travels cleanly across the copper mesh and brushed steel. Crisp editorial workwear cinematography, realistic textile physics, premium material detail, bold cream-vermilion-amber palette, stable anatomy, no text, no logo.',
  negativePrompt: 'Wardrobe changes, altered suit details, extra people, bees, distorted hands, broken mesh, warped extractor, flicker, jitter, sudden cuts, excessive camera shake, text, logos, watermarks',
  resolution: '1080p',
  duration: 5,
  settings: {
    audio: true
  },
  inputs: {
    frameImages: [
      {
        image: 'https://assets.runware.ai/assets/inputs/a9f85cad-c7a3-4472-9269-1b3c49ed4e3e.jpg',
        frame: 'first'
      }
    ]
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "alibaba:wan@2.7",
            "positivePrompt": "Continue directly from the supplied first frame as a polished five-second vertical fashion showcase, preserving the same model, facial appearance, ivory beekeeping suit, copper-mesh hood, gloves, honey extractor, vermilion studio, lighting, and centered composition. The model makes a slow controlled quarter-turn while sliding one gloved hand along the reinforced cuff, revealing the suit's articulated sleeve, utility pocket, and tailored side profile. A gentle studio fan creates subtle movement in the fabric without disturbing the hood. The camera performs a smooth, restrained push-in with a slight clockwise arc, ending on a confident three-quarter pose as amber light travels cleanly across the copper mesh and brushed steel. Crisp editorial workwear cinematography, realistic textile physics, premium material detail, bold cream-vermilion-amber palette, stable anatomy, no text, no logo.",
            "negativePrompt": "Wardrobe changes, altered suit details, extra people, bees, distorted hands, broken mesh, warped extractor, flicker, jitter, sudden cuts, excessive camera shake, text, logos, watermarks",
            "resolution": "1080p",
            "duration": 5,
            "settings": {
                "audio": True
            },
            "inputs": {
                "frameImages": [
                    {
                        "image": "https://assets.runware.ai/assets/inputs/a9f85cad-c7a3-4472-9269-1b3c49ed4e3e.jpg",
                        "frame": "first"
                    }
                ]
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "videoInference",
      "taskUUID": "5b15003c-1045-4b7f-bc77-008301536db9",
      "model": "alibaba:wan@2.7",
      "positivePrompt": "Continue directly from the supplied first frame as a polished five-second vertical fashion showcase, preserving the same model, facial appearance, ivory beekeeping suit, copper-mesh hood, gloves, honey extractor, vermilion studio, lighting, and centered composition. The model makes a slow controlled quarter-turn while sliding one gloved hand along the reinforced cuff, revealing the suit's articulated sleeve, utility pocket, and tailored side profile. A gentle studio fan creates subtle movement in the fabric without disturbing the hood. The camera performs a smooth, restrained push-in with a slight clockwise arc, ending on a confident three-quarter pose as amber light travels cleanly across the copper mesh and brushed steel. Crisp editorial workwear cinematography, realistic textile physics, premium material detail, bold cream-vermilion-amber palette, stable anatomy, no text, no logo.",
      "negativePrompt": "Wardrobe changes, altered suit details, extra people, bees, distorted hands, broken mesh, warped extractor, flicker, jitter, sudden cuts, excessive camera shake, text, logos, watermarks",
      "resolution": "1080p",
      "duration": 5,
      "settings": {
        "audio": true
      },
      "inputs": {
        "frameImages": [
          {
            "image": "https://assets.runware.ai/assets/inputs/a9f85cad-c7a3-4472-9269-1b3c49ed4e3e.jpg",
            "frame": "first"
          }
        ]
      }
    }
  ]'
runware run alibaba:wan@2.7 \
  positivePrompt="Continue directly from the supplied first frame as a polished five-second vertical fashion showcase, preserving the same model, facial appearance, ivory beekeeping suit, copper-mesh hood, gloves, honey extractor, vermilion studio, lighting, and centered composition. The model makes a slow controlled quarter-turn while sliding one gloved hand along the reinforced cuff, revealing the suit's articulated sleeve, utility pocket, and tailored side profile. A gentle studio fan creates subtle movement in the fabric without disturbing the hood. The camera performs a smooth, restrained push-in with a slight clockwise arc, ending on a confident three-quarter pose as amber light travels cleanly across the copper mesh and brushed steel. Crisp editorial workwear cinematography, realistic textile physics, premium material detail, bold cream-vermilion-amber palette, stable anatomy, no text, no logo." \
  negativePrompt="Wardrobe changes, altered suit details, extra people, bees, distorted hands, broken mesh, warped extractor, flicker, jitter, sudden cuts, excessive camera shake, text, logos, watermarks" \
  resolution=1080p \
  duration=5 \
  settings.audio=true \
  inputs.frameImages.0.image=https://assets.runware.ai/assets/inputs/a9f85cad-c7a3-4472-9269-1b3c49ed4e3e.jpg \
  inputs.frameImages.0.frame=first
{
  "taskType": "videoInference",
  "taskUUID": "5b15003c-1045-4b7f-bc77-008301536db9",
  "model": "alibaba:wan@2.7",
  "positivePrompt": "Continue directly from the supplied first frame as a polished five-second vertical fashion showcase, preserving the same model, facial appearance, ivory beekeeping suit, copper-mesh hood, gloves, honey extractor, vermilion studio, lighting, and centered composition. The model makes a slow controlled quarter-turn while sliding one gloved hand along the reinforced cuff, revealing the suit's articulated sleeve, utility pocket, and tailored side profile. A gentle studio fan creates subtle movement in the fabric without disturbing the hood. The camera performs a smooth, restrained push-in with a slight clockwise arc, ending on a confident three-quarter pose as amber light travels cleanly across the copper mesh and brushed steel. Crisp editorial workwear cinematography, realistic textile physics, premium material detail, bold cream-vermilion-amber palette, stable anatomy, no text, no logo.",
  "negativePrompt": "Wardrobe changes, altered suit details, extra people, bees, distorted hands, broken mesh, warped extractor, flicker, jitter, sudden cuts, excessive camera shake, text, logos, watermarks",
  "resolution": "1080p",
  "duration": 5,
  "settings": {
    "audio": true
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/a9f85cad-c7a3-4472-9269-1b3c49ed4e3e.jpg",
        "frame": "first"
      }
    ]
  }
}
Response
{
  "taskType": "videoInference",
  "taskUUID": "5b15003c-1045-4b7f-bc77-008301536db9",
  "videoUUID": "e2dd202f-7d59-4d7c-a993-7b2d46994bce",
  "videoURL": "https://vm.runware.ai/video/os/a02d21/ws/5/vi/e2dd202f-7d59-4d7c-a993-7b2d46994bce.mp4",
  "seed": 771411886,
  "cost": 0.7557
}

first-last-frame

Night Shift Lyric Video Segment$0.708~1m 6s
Try in Playground
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'alibaba:wan@2.7',
  positivePrompt: 'Create a finished seven-second lyric-video segment as one continuous overhead stop-motion shot, interpolating naturally between the supplied locked first and last frames. Begin with the exact phrase “WHEN THE CITY CLOCKS OUT” resting across the packing table. After a brief hold, the narrow conveyor rollers turn, a time clock arm stamps down on the beat, and thermal labels feed rapidly across the surface. The original paper letters peel up one by one, slide, rotate and fold with believable handmade frame-by-frame motion. Timecards shuffle into rhythmic rows while safety-orange scraps pulse outward like graphic sound waves. The moving pieces progressively reassemble into the exact final phrase “WE COME ALIVE”, completing the transformation cleanly before a confident final hold. Preserve the same tabletop, objects, palette and handcrafted risograph texture throughout: warm cream paper, charcoal typography, cobalt shadows, safety orange, coarse halftone ink, visible fibers and subtle print misregistration. Keep all motion purposeful and rhythmically accelerating, with stable overhead framing and only a very slight camera push-in. The typography must remain bold, centered and legible; introduce no additional text. Energetic, defiant night-shift mood, polished enough for an official post-punk lyric video.',
  negativePrompt: 'Misspelled lyrics, extra words, logos, branding, glossy CGI, photorealistic hands, camera cuts, side angles, illegible typography, warped letters, flickering background, duplicated objects, random symbols, neon cyberpunk lighting, excessive motion blur.',
  resolution: '720p',
  duration: 7,
  settings: {
    audio: true
  },
  inputs: {
    frameImages: [
      {
        image: 'https://assets.runware.ai/assets/inputs/3af384e9-a73b-42bf-a0e4-7d2da3771c1a.jpg',
        frame: 'first'
      },
      {
        image: 'https://assets.runware.ai/assets/inputs/b5c4c99f-dd58-45ac-8345-919737036b63.jpg',
        frame: 'last'
      }
    ]
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "alibaba:wan@2.7",
            "positivePrompt": "Create a finished seven-second lyric-video segment as one continuous overhead stop-motion shot, interpolating naturally between the supplied locked first and last frames. Begin with the exact phrase “WHEN THE CITY CLOCKS OUT” resting across the packing table. After a brief hold, the narrow conveyor rollers turn, a time clock arm stamps down on the beat, and thermal labels feed rapidly across the surface. The original paper letters peel up one by one, slide, rotate and fold with believable handmade frame-by-frame motion. Timecards shuffle into rhythmic rows while safety-orange scraps pulse outward like graphic sound waves. The moving pieces progressively reassemble into the exact final phrase “WE COME ALIVE”, completing the transformation cleanly before a confident final hold. Preserve the same tabletop, objects, palette and handcrafted risograph texture throughout: warm cream paper, charcoal typography, cobalt shadows, safety orange, coarse halftone ink, visible fibers and subtle print misregistration. Keep all motion purposeful and rhythmically accelerating, with stable overhead framing and only a very slight camera push-in. The typography must remain bold, centered and legible; introduce no additional text. Energetic, defiant night-shift mood, polished enough for an official post-punk lyric video.",
            "negativePrompt": "Misspelled lyrics, extra words, logos, branding, glossy CGI, photorealistic hands, camera cuts, side angles, illegible typography, warped letters, flickering background, duplicated objects, random symbols, neon cyberpunk lighting, excessive motion blur.",
            "resolution": "720p",
            "duration": 7,
            "settings": {
                "audio": True
            },
            "inputs": {
                "frameImages": [
                    {
                        "image": "https://assets.runware.ai/assets/inputs/3af384e9-a73b-42bf-a0e4-7d2da3771c1a.jpg",
                        "frame": "first"
                    },
                    {
                        "image": "https://assets.runware.ai/assets/inputs/b5c4c99f-dd58-45ac-8345-919737036b63.jpg",
                        "frame": "last"
                    }
                ]
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "videoInference",
      "taskUUID": "fc8da50c-9131-4b3f-9880-bb202c5acc2f",
      "model": "alibaba:wan@2.7",
      "positivePrompt": "Create a finished seven-second lyric-video segment as one continuous overhead stop-motion shot, interpolating naturally between the supplied locked first and last frames. Begin with the exact phrase “WHEN THE CITY CLOCKS OUT” resting across the packing table. After a brief hold, the narrow conveyor rollers turn, a time clock arm stamps down on the beat, and thermal labels feed rapidly across the surface. The original paper letters peel up one by one, slide, rotate and fold with believable handmade frame-by-frame motion. Timecards shuffle into rhythmic rows while safety-orange scraps pulse outward like graphic sound waves. The moving pieces progressively reassemble into the exact final phrase “WE COME ALIVE”, completing the transformation cleanly before a confident final hold. Preserve the same tabletop, objects, palette and handcrafted risograph texture throughout: warm cream paper, charcoal typography, cobalt shadows, safety orange, coarse halftone ink, visible fibers and subtle print misregistration. Keep all motion purposeful and rhythmically accelerating, with stable overhead framing and only a very slight camera push-in. The typography must remain bold, centered and legible; introduce no additional text. Energetic, defiant night-shift mood, polished enough for an official post-punk lyric video.",
      "negativePrompt": "Misspelled lyrics, extra words, logos, branding, glossy CGI, photorealistic hands, camera cuts, side angles, illegible typography, warped letters, flickering background, duplicated objects, random symbols, neon cyberpunk lighting, excessive motion blur.",
      "resolution": "720p",
      "duration": 7,
      "settings": {
        "audio": true
      },
      "inputs": {
        "frameImages": [
          {
            "image": "https://assets.runware.ai/assets/inputs/3af384e9-a73b-42bf-a0e4-7d2da3771c1a.jpg",
            "frame": "first"
          },
          {
            "image": "https://assets.runware.ai/assets/inputs/b5c4c99f-dd58-45ac-8345-919737036b63.jpg",
            "frame": "last"
          }
        ]
      }
    }
  ]'
runware run alibaba:wan@2.7 \
  positivePrompt="Create a finished seven-second lyric-video segment as one continuous overhead stop-motion shot, interpolating naturally between the supplied locked first and last frames. Begin with the exact phrase “WHEN THE CITY CLOCKS OUT” resting across the packing table. After a brief hold, the narrow conveyor rollers turn, a time clock arm stamps down on the beat, and thermal labels feed rapidly across the surface. The original paper letters peel up one by one, slide, rotate and fold with believable handmade frame-by-frame motion. Timecards shuffle into rhythmic rows while safety-orange scraps pulse outward like graphic sound waves. The moving pieces progressively reassemble into the exact final phrase “WE COME ALIVE”, completing the transformation cleanly before a confident final hold. Preserve the same tabletop, objects, palette and handcrafted risograph texture throughout: warm cream paper, charcoal typography, cobalt shadows, safety orange, coarse halftone ink, visible fibers and subtle print misregistration. Keep all motion purposeful and rhythmically accelerating, with stable overhead framing and only a very slight camera push-in. The typography must remain bold, centered and legible; introduce no additional text. Energetic, defiant night-shift mood, polished enough for an official post-punk lyric video." \
  negativePrompt="Misspelled lyrics, extra words, logos, branding, glossy CGI, photorealistic hands, camera cuts, side angles, illegible typography, warped letters, flickering background, duplicated objects, random symbols, neon cyberpunk lighting, excessive motion blur." \
  resolution=720p \
  duration=7 \
  settings.audio=true \
  inputs.frameImages.0.image=https://assets.runware.ai/assets/inputs/3af384e9-a73b-42bf-a0e4-7d2da3771c1a.jpg \
  inputs.frameImages.0.frame=first \
  inputs.frameImages.1.image=https://assets.runware.ai/assets/inputs/b5c4c99f-dd58-45ac-8345-919737036b63.jpg \
  inputs.frameImages.1.frame=last
{
  "taskType": "videoInference",
  "taskUUID": "fc8da50c-9131-4b3f-9880-bb202c5acc2f",
  "model": "alibaba:wan@2.7",
  "positivePrompt": "Create a finished seven-second lyric-video segment as one continuous overhead stop-motion shot, interpolating naturally between the supplied locked first and last frames. Begin with the exact phrase “WHEN THE CITY CLOCKS OUT” resting across the packing table. After a brief hold, the narrow conveyor rollers turn, a time clock arm stamps down on the beat, and thermal labels feed rapidly across the surface. The original paper letters peel up one by one, slide, rotate and fold with believable handmade frame-by-frame motion. Timecards shuffle into rhythmic rows while safety-orange scraps pulse outward like graphic sound waves. The moving pieces progressively reassemble into the exact final phrase “WE COME ALIVE”, completing the transformation cleanly before a confident final hold. Preserve the same tabletop, objects, palette and handcrafted risograph texture throughout: warm cream paper, charcoal typography, cobalt shadows, safety orange, coarse halftone ink, visible fibers and subtle print misregistration. Keep all motion purposeful and rhythmically accelerating, with stable overhead framing and only a very slight camera push-in. The typography must remain bold, centered and legible; introduce no additional text. Energetic, defiant night-shift mood, polished enough for an official post-punk lyric video.",
  "negativePrompt": "Misspelled lyrics, extra words, logos, branding, glossy CGI, photorealistic hands, camera cuts, side angles, illegible typography, warped letters, flickering background, duplicated objects, random symbols, neon cyberpunk lighting, excessive motion blur.",
  "resolution": "720p",
  "duration": 7,
  "settings": {
    "audio": true
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/3af384e9-a73b-42bf-a0e4-7d2da3771c1a.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/b5c4c99f-dd58-45ac-8345-919737036b63.jpg",
        "frame": "last"
      }
    ]
  }
}
Response
{
  "taskType": "videoInference",
  "taskUUID": "fc8da50c-9131-4b3f-9880-bb202c5acc2f",
  "videoUUID": "272aa676-8dd2-4f7a-982d-505df990684c",
  "videoURL": "https://vm.runware.ai/video/os/a04d20/ws/5/vi/272aa676-8dd2-4f7a-982d-505df990684c.mp4",
  "seed": 509797366,
  "cost": 0.7082
}

reference-to-video

Natural Indigo Workshop B-Roll$1.00~6m 40s
Try in Playground
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'alibaba:wan@2.7',
  positivePrompt: 'Create a new 10-second multi-shot landscape b-roll sequence for an editorial documentary about low-impact textile production. Preserve the technician\'s recognizable face, silver bob, amber safety glasses and rust-red apron from the reference image, along with the authentic hand movements, restrained handheld camera language, workshop materials and muted indigo-rust-cream grade established by the reference video. This must be a newly staged sequence, not a frame-by-frame recreation of either reference. Shot 1: a slow lateral medium-wide move past hanging undyed linen reveals the artisan lifting a circular bamboo resist frame from beside an open indigo fermentation vat; blue vapor and soft window light add depth. Shot 2: tactile macro close-up of her blue-stained gloves pressing folded linen beneath the glossy dye surface, with natural ripples, bubbles and pigment clinging to the fabric. Shot 3: waist-level three-quarter view as she raises the saturated cloth and unfolds it once over a wooden draining rack; the textile shifts from green-blue toward rich indigo as it meets the air, droplets falling back into the vat. Maintain subject identity, wardrobe continuity, believable workshop geography and physically accurate liquid and fabric motion across all shots. Premium documentary stock-footage finish, observational rather than promotional, gentle film grain, soft highlights, crisp material detail, calm methodical mood. Compose every shot for 1088x832 landscape with useful negative space and clean editorial framing. No captions, signage, logos, watermarks or direct address to camera.',
  width: 1088,
  height: 832,
  duration: 10,
  settings: {
    shotType: 'multi',
    promptExtend: true,
    audio: true
  },
  inputs: {
    referenceImages: [
      'https://assets.runware.ai/assets/inputs/9455b0dc-3c94-4ada-87b9-269757491f43.jpg'
    ],
    referenceVideos: [
      'https://assets.runware.ai/assets/inputs/e513b5ed-d59c-4684-9540-6c759462fa3e.mp4'
    ]
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "alibaba:wan@2.7",
            "positivePrompt": "Create a new 10-second multi-shot landscape b-roll sequence for an editorial documentary about low-impact textile production. Preserve the technician's recognizable face, silver bob, amber safety glasses and rust-red apron from the reference image, along with the authentic hand movements, restrained handheld camera language, workshop materials and muted indigo-rust-cream grade established by the reference video. This must be a newly staged sequence, not a frame-by-frame recreation of either reference. Shot 1: a slow lateral medium-wide move past hanging undyed linen reveals the artisan lifting a circular bamboo resist frame from beside an open indigo fermentation vat; blue vapor and soft window light add depth. Shot 2: tactile macro close-up of her blue-stained gloves pressing folded linen beneath the glossy dye surface, with natural ripples, bubbles and pigment clinging to the fabric. Shot 3: waist-level three-quarter view as she raises the saturated cloth and unfolds it once over a wooden draining rack; the textile shifts from green-blue toward rich indigo as it meets the air, droplets falling back into the vat. Maintain subject identity, wardrobe continuity, believable workshop geography and physically accurate liquid and fabric motion across all shots. Premium documentary stock-footage finish, observational rather than promotional, gentle film grain, soft highlights, crisp material detail, calm methodical mood. Compose every shot for 1088x832 landscape with useful negative space and clean editorial framing. No captions, signage, logos, watermarks or direct address to camera.",
            "width": 1088,
            "height": 832,
            "duration": 10,
            "settings": {
                "shotType": "multi",
                "promptExtend": True,
                "audio": True
            },
            "inputs": {
                "referenceImages": [
                    "https://assets.runware.ai/assets/inputs/9455b0dc-3c94-4ada-87b9-269757491f43.jpg"
                ],
                "referenceVideos": [
                    "https://assets.runware.ai/assets/inputs/e513b5ed-d59c-4684-9540-6c759462fa3e.mp4"
                ]
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "videoInference",
      "taskUUID": "05765e76-50bb-4985-8650-e5b3eb782bac",
      "model": "alibaba:wan@2.7",
      "positivePrompt": "Create a new 10-second multi-shot landscape b-roll sequence for an editorial documentary about low-impact textile production. Preserve the technician's recognizable face, silver bob, amber safety glasses and rust-red apron from the reference image, along with the authentic hand movements, restrained handheld camera language, workshop materials and muted indigo-rust-cream grade established by the reference video. This must be a newly staged sequence, not a frame-by-frame recreation of either reference. Shot 1: a slow lateral medium-wide move past hanging undyed linen reveals the artisan lifting a circular bamboo resist frame from beside an open indigo fermentation vat; blue vapor and soft window light add depth. Shot 2: tactile macro close-up of her blue-stained gloves pressing folded linen beneath the glossy dye surface, with natural ripples, bubbles and pigment clinging to the fabric. Shot 3: waist-level three-quarter view as she raises the saturated cloth and unfolds it once over a wooden draining rack; the textile shifts from green-blue toward rich indigo as it meets the air, droplets falling back into the vat. Maintain subject identity, wardrobe continuity, believable workshop geography and physically accurate liquid and fabric motion across all shots. Premium documentary stock-footage finish, observational rather than promotional, gentle film grain, soft highlights, crisp material detail, calm methodical mood. Compose every shot for 1088x832 landscape with useful negative space and clean editorial framing. No captions, signage, logos, watermarks or direct address to camera.",
      "width": 1088,
      "height": 832,
      "duration": 10,
      "settings": {
        "shotType": "multi",
        "promptExtend": true,
        "audio": true
      },
      "inputs": {
        "referenceImages": [
          "https://assets.runware.ai/assets/inputs/9455b0dc-3c94-4ada-87b9-269757491f43.jpg"
        ],
        "referenceVideos": [
          "https://assets.runware.ai/assets/inputs/e513b5ed-d59c-4684-9540-6c759462fa3e.mp4"
        ]
      }
    }
  ]'
runware run alibaba:wan@2.7 \
  positivePrompt="Create a new 10-second multi-shot landscape b-roll sequence for an editorial documentary about low-impact textile production. Preserve the technician's recognizable face, silver bob, amber safety glasses and rust-red apron from the reference image, along with the authentic hand movements, restrained handheld camera language, workshop materials and muted indigo-rust-cream grade established by the reference video. This must be a newly staged sequence, not a frame-by-frame recreation of either reference. Shot 1: a slow lateral medium-wide move past hanging undyed linen reveals the artisan lifting a circular bamboo resist frame from beside an open indigo fermentation vat; blue vapor and soft window light add depth. Shot 2: tactile macro close-up of her blue-stained gloves pressing folded linen beneath the glossy dye surface, with natural ripples, bubbles and pigment clinging to the fabric. Shot 3: waist-level three-quarter view as she raises the saturated cloth and unfolds it once over a wooden draining rack; the textile shifts from green-blue toward rich indigo as it meets the air, droplets falling back into the vat. Maintain subject identity, wardrobe continuity, believable workshop geography and physically accurate liquid and fabric motion across all shots. Premium documentary stock-footage finish, observational rather than promotional, gentle film grain, soft highlights, crisp material detail, calm methodical mood. Compose every shot for 1088x832 landscape with useful negative space and clean editorial framing. No captions, signage, logos, watermarks or direct address to camera." \
  width=1088 \
  height=832 \
  duration=10 \
  settings.shotType=multi \
  settings.promptExtend=true \
  settings.audio=true \
  inputs.referenceImages.0=https://assets.runware.ai/assets/inputs/9455b0dc-3c94-4ada-87b9-269757491f43.jpg \
  inputs.referenceVideos.0=https://assets.runware.ai/assets/inputs/e513b5ed-d59c-4684-9540-6c759462fa3e.mp4
{
  "taskType": "videoInference",
  "taskUUID": "05765e76-50bb-4985-8650-e5b3eb782bac",
  "model": "alibaba:wan@2.7",
  "positivePrompt": "Create a new 10-second multi-shot landscape b-roll sequence for an editorial documentary about low-impact textile production. Preserve the technician's recognizable face, silver bob, amber safety glasses and rust-red apron from the reference image, along with the authentic hand movements, restrained handheld camera language, workshop materials and muted indigo-rust-cream grade established by the reference video. This must be a newly staged sequence, not a frame-by-frame recreation of either reference. Shot 1: a slow lateral medium-wide move past hanging undyed linen reveals the artisan lifting a circular bamboo resist frame from beside an open indigo fermentation vat; blue vapor and soft window light add depth. Shot 2: tactile macro close-up of her blue-stained gloves pressing folded linen beneath the glossy dye surface, with natural ripples, bubbles and pigment clinging to the fabric. Shot 3: waist-level three-quarter view as she raises the saturated cloth and unfolds it once over a wooden draining rack; the textile shifts from green-blue toward rich indigo as it meets the air, droplets falling back into the vat. Maintain subject identity, wardrobe continuity, believable workshop geography and physically accurate liquid and fabric motion across all shots. Premium documentary stock-footage finish, observational rather than promotional, gentle film grain, soft highlights, crisp material detail, calm methodical mood. Compose every shot for 1088x832 landscape with useful negative space and clean editorial framing. No captions, signage, logos, watermarks or direct address to camera.",
  "width": 1088,
  "height": 832,
  "duration": 10,
  "settings": {
    "shotType": "multi",
    "promptExtend": true,
    "audio": true
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/9455b0dc-3c94-4ada-87b9-269757491f43.jpg"
    ],
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/e513b5ed-d59c-4684-9540-6c759462fa3e.mp4"
    ]
  }
}
Response
{
  "taskType": "videoInference",
  "taskUUID": "05765e76-50bb-4985-8650-e5b3eb782bac",
  "videoUUID": "ced815f6-4483-4423-bd4a-ab20adafa60f",
  "videoURL": "https://vm.runware.ai/video/os/a05d22/ws/5/vi/ced815f6-4483-4423-bd4a-ab20adafa60f.mp4",
  "seed": 154632082,
  "cost": 1.0031
}

audio-driven

Ice Core Archive Safety Presenter$0.803~3m 7s
Try in Playground
import { createClient } from '@runware/sdk'

const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()

const [result] = await client.run({
  model: 'alibaba:wan@2.7',
  positivePrompt: 'A polished vertical talking-head safety presenter clip for a polar research institute. In one continuous medium close-up, a female ice-core archive manager in her early forties faces the camera inside a real subzero storage aisle. She wears a vivid safety-orange insulated jacket over navy cold-room workwear, with frost-softened steel shelving and translucent cylindrical ice-core sleeves receding behind her in cool cyan light. Her lip movements synchronize precisely with the supplied speech. She speaks with calm authority and natural facial movement. On the words “label and seal,” she lifts one gloved hand and points toward the sealed end of an ice-core sleeve beside her. At “Any frost inside,” her expression becomes briefly concerned and she indicates a faint frosted patch without blocking her face. On “stop,” she makes a small, clear open-palm halt gesture, then returns to steady eye contact for the final instruction. Restrained documentary realism, clean institutional training-film art direction, soft frontal key light, subtle cold vapor in the background, realistic skin and fabric texture, shallow depth of field, stable camera, centered portrait composition with comfortable headroom. No cuts, no captions, no logos, no visible writing, no interface elements.',
  width: 720,
  height: 1280,
  duration: 8,
  inputs: {
    audio: 'https://assets.runware.ai/assets/inputs/52984900-6239-4cb5-8c16-30a7932d223c.mp3'
  }
})
import asyncio
import os

from runware import Runware


async def main():
    async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
        results = await client.run({
            "model": "alibaba:wan@2.7",
            "positivePrompt": "A polished vertical talking-head safety presenter clip for a polar research institute. In one continuous medium close-up, a female ice-core archive manager in her early forties faces the camera inside a real subzero storage aisle. She wears a vivid safety-orange insulated jacket over navy cold-room workwear, with frost-softened steel shelving and translucent cylindrical ice-core sleeves receding behind her in cool cyan light. Her lip movements synchronize precisely with the supplied speech. She speaks with calm authority and natural facial movement. On the words “label and seal,” she lifts one gloved hand and points toward the sealed end of an ice-core sleeve beside her. At “Any frost inside,” her expression becomes briefly concerned and she indicates a faint frosted patch without blocking her face. On “stop,” she makes a small, clear open-palm halt gesture, then returns to steady eye contact for the final instruction. Restrained documentary realism, clean institutional training-film art direction, soft frontal key light, subtle cold vapor in the background, realistic skin and fabric texture, shallow depth of field, stable camera, centered portrait composition with comfortable headroom. No cuts, no captions, no logos, no visible writing, no interface elements.",
            "width": 720,
            "height": 1280,
            "duration": 8,
            "inputs": {
                "audio": "https://assets.runware.ai/assets/inputs/52984900-6239-4cb5-8c16-30a7932d223c.mp3"
            }
        })


asyncio.run(main())
curl https://api.runware.ai/v1 \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '[
    {
      "taskType": "videoInference",
      "taskUUID": "6ebf3f37-11a5-4031-ac0f-765b58e4ab4f",
      "model": "alibaba:wan@2.7",
      "positivePrompt": "A polished vertical talking-head safety presenter clip for a polar research institute. In one continuous medium close-up, a female ice-core archive manager in her early forties faces the camera inside a real subzero storage aisle. She wears a vivid safety-orange insulated jacket over navy cold-room workwear, with frost-softened steel shelving and translucent cylindrical ice-core sleeves receding behind her in cool cyan light. Her lip movements synchronize precisely with the supplied speech. She speaks with calm authority and natural facial movement. On the words “label and seal,” she lifts one gloved hand and points toward the sealed end of an ice-core sleeve beside her. At “Any frost inside,” her expression becomes briefly concerned and she indicates a faint frosted patch without blocking her face. On “stop,” she makes a small, clear open-palm halt gesture, then returns to steady eye contact for the final instruction. Restrained documentary realism, clean institutional training-film art direction, soft frontal key light, subtle cold vapor in the background, realistic skin and fabric texture, shallow depth of field, stable camera, centered portrait composition with comfortable headroom. No cuts, no captions, no logos, no visible writing, no interface elements.",
      "width": 720,
      "height": 1280,
      "duration": 8,
      "inputs": {
        "audio": "https://assets.runware.ai/assets/inputs/52984900-6239-4cb5-8c16-30a7932d223c.mp3"
      }
    }
  ]'
runware run alibaba:wan@2.7 \
  positivePrompt="A polished vertical talking-head safety presenter clip for a polar research institute. In one continuous medium close-up, a female ice-core archive manager in her early forties faces the camera inside a real subzero storage aisle. She wears a vivid safety-orange insulated jacket over navy cold-room workwear, with frost-softened steel shelving and translucent cylindrical ice-core sleeves receding behind her in cool cyan light. Her lip movements synchronize precisely with the supplied speech. She speaks with calm authority and natural facial movement. On the words “label and seal,” she lifts one gloved hand and points toward the sealed end of an ice-core sleeve beside her. At “Any frost inside,” her expression becomes briefly concerned and she indicates a faint frosted patch without blocking her face. On “stop,” she makes a small, clear open-palm halt gesture, then returns to steady eye contact for the final instruction. Restrained documentary realism, clean institutional training-film art direction, soft frontal key light, subtle cold vapor in the background, realistic skin and fabric texture, shallow depth of field, stable camera, centered portrait composition with comfortable headroom. No cuts, no captions, no logos, no visible writing, no interface elements." \
  width=720 \
  height=1280 \
  duration=8 \
  inputs.audio=https://assets.runware.ai/assets/inputs/52984900-6239-4cb5-8c16-30a7932d223c.mp3
{
  "taskType": "videoInference",
  "taskUUID": "6ebf3f37-11a5-4031-ac0f-765b58e4ab4f",
  "model": "alibaba:wan@2.7",
  "positivePrompt": "A polished vertical talking-head safety presenter clip for a polar research institute. In one continuous medium close-up, a female ice-core archive manager in her early forties faces the camera inside a real subzero storage aisle. She wears a vivid safety-orange insulated jacket over navy cold-room workwear, with frost-softened steel shelving and translucent cylindrical ice-core sleeves receding behind her in cool cyan light. Her lip movements synchronize precisely with the supplied speech. She speaks with calm authority and natural facial movement. On the words “label and seal,” she lifts one gloved hand and points toward the sealed end of an ice-core sleeve beside her. At “Any frost inside,” her expression becomes briefly concerned and she indicates a faint frosted patch without blocking her face. On “stop,” she makes a small, clear open-palm halt gesture, then returns to steady eye contact for the final instruction. Restrained documentary realism, clean institutional training-film art direction, soft frontal key light, subtle cold vapor in the background, realistic skin and fabric texture, shallow depth of field, stable camera, centered portrait composition with comfortable headroom. No cuts, no captions, no logos, no visible writing, no interface elements.",
  "width": 720,
  "height": 1280,
  "duration": 8,
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/52984900-6239-4cb5-8c16-30a7932d223c.mp3"
  }
}
Response
{
  "taskType": "videoInference",
  "taskUUID": "6ebf3f37-11a5-4031-ac0f-765b58e4ab4f",
  "videoUUID": "46ca71e0-ab62-4972-9d40-2a70036f6aa3",
  "videoURL": "https://vm.runware.ai/video/os/a02d21/ws/5/vi/46ca71e0-ab62-4972-9d40-2a70036f6aa3.mp4",
  "seed": 1001780382,
  "cost": 0.8034
}