https://seedaudio2.app/_next/static/chunks/app/how-to-use-seed-aud…?dpl=dpl_6a5T6C5JwuqCby9rjTKzsTef94CP

1(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[7536],{2673:(e,s,a)=>{Promise.resolve().then(a.bind(a,7997))},4498:()=>{},7997:(e,s,a)=>{"use strict";a.r(s),a.d(s,{default:()=>l});var n=a(5155),i=a(2115),t=a(5078),o=a(6717);a(4498);let r=[{title:"Cinematic dialogue in a rain alley",tag:"Dialogue + ambience + final event",use:"Short films, audio drama, storyboarding",image:"/examples/seed-audio-scene-01.jpg",audio:"/audio/seed-audio-scene-01.wav",prompt:"Create a 20-second cinematic audio scene in English. Two investigators whisper in a rain-soaked alley at midnight. Add distant traffic, soft thunder, wet footsteps, a low suspense pad, and one metal door slam at the end. Keep the dialogue clear and natural.",notes:["Name the setting, delivery, ambience and ending cue.","Keep dialogue direction short so the scene has room to breathe.","Use one ordered effect instead of a long sound list."]},{title:"Podcast welcome segment",tag:"Narration + studio tone + intro bed",use:"Podcast intros, branded explainers, creator videos",image:"/examples/seed-audio-scene-02.jpg",audio:"/audio/seed-audio-scene-02.wav",prompt:"Create a 20-second podcast welcome for a calm technology show. Use one warm host voice, light studio room tone, a soft synth bed, and a clean broadcast-style ending. Keep the speech friendly, natural, and easy to understand.",notes:["Use one speaker when voice clarity matters.","Describe room tone and music separately.","Ask for a clean ending when the result will be edited."]},{title:"Night forest ambience",tag:"No speech + seamless ambience",use:"Games, XR scenes, background atmospheres",image:"/examples/seed-audio-scene-03.jpg",audio:"/audio/seed-audio-scene-03.wav",prompt:"Create a 20-second looping fantasy forest ambience with no speech. Use night insects, soft wind through leaves, distant owls, a faint magical shimmer, and one small branch snap near the middle. Keep the loop calm and usable in a game scene.",notes:["Say no speech when you want pure ambience.","Describe the loop purpose to avoid a dramatic ending.","Place one small event in the middle to test timing."]},{title:"Audiobook narration",tag:"Narration + subtle environment",use:"Audiobooks, story samples, voice direction tests",image:"/examples/seed-audio-scene-04.jpg",audio:"/audio/seed-audio-scene-04.wav",prompt:"Create a 20-second audiobook scene with one clear narrator. The setting is a quiet train at sunrise. Add very subtle carriage room tone and a soft rail rhythm, but keep the voice intimate, steady, and easy to hear.",notes:["Use subtle ambience when narration is the product.","Give one physical scene cue instead of a full plot.","Ask for steady delivery when you do not want dramatic acting."]},{title:"Educational sound explainer",tag:"Teacher voice + demonstration tones",use:"Learning content, classroom demos, micro-courses",image:"/examples/seed-audio-scene-05.jpg",audio:"/audio/seed-audio-scene-05.wav",prompt:"Create a 20-second educational explainer for students. A friendly teacher explains that sound is vibration moving through air, water, or solid objects. Add light classroom ambience and two gentle demonstration tones.",notes:["State the teaching role and intended audience.","Limit demonstration sounds to a small count.","Use gentle when you want to avoid harsh effects."]},{title:"Wellness breathing guide",tag:"Calm guide + warm pad + bell",use:"Meditation, breathing exercises, wellness prototypes",image:"/examples/seed-audio-scene-06.jpg",audio:"/audio/seed-audio-scene-06.wav",prompt:"Create a 20-second wellness audio scene. Use a calm guide voice, a soft breathing pace, quiet room tone, a warm ambient pad, and one gentle bell at the end. Keep the result relaxing, minimal, and clean.",notes:["Use minimal and clean for app-ready audio.","Add one ending marker such as a bell.","Avoid stacking too many music adjectives."]}],d=[["What is the best way to start with Seed Audio 2.0?","Begin with one short text-only scene. Define the speaker, setting, ambience, music direction, and one important ending event. Keep the first prompt focused so you can hear which part needs refinement."],["Can Seed Audio 2.0 generate more than speech?","Yes. A single prompt c

1an direct narration, dialogue, ambience, music beds, Foley-style effects, and timed sound events as parts of one audio scene."],["How long should my first generation be?","Start with a short target, such as 15 to 25 seconds. Short scenes are easier to evaluate, revise, and compare before you create a longer version."],["Does the requested duration always match exactly?","Treat the requested duration as guidance rather than frame-accurate timing. If an edit needs an exact length, generate the strongest version first and trim the final audio in your editing workflow."],["When should I use an image reference?","Use an image reference when the visual setting helps define the sound world, such as a rainy street, crowded station, quiet studio, or fantasy landscape. Describe the audio outcome in text as well, rather than relying on the image alone."],["When should I use reference audio?","Start text-only when possible. Add a short, authorized reference after you know which voice quality, pacing, emotion, or texture you want to preserve in the next generation."],["Why can a Seed Audio 2.0 generation fail?","Failures can happen when a prompt contains too many competing instructions, when a reference file exceeds supported limits, or when the request includes restricted names or protected characters. Simplify the prompt and check every uploaded file before trying again."],["What should I do if the output sounds too busy?","Reduce the number of active layers. Keep one main voice, one ambience bed, one music direction, and one or two important sound effects. Then add complexity only after the core scene sounds clear."],["How can I make dialogue easier to understand?","Name each speaker’s role, tone, pacing, and emotional direction. State that dialogue should remain clear, then keep background music and effects subtle when important lines are being spoken."],["Can I download and edit the generated audio?","Yes. Download the version you want to keep, then trim, mix, or place it in your video, game, lesson, advertisement, or other production workflow. Make sure you have the necessary rights for any references or material you provide."]];function c({text:e}){let[s,a]=(0,i.useState)(!1);async function t(){await navigator.clipboard.writeText(e),a(!0),window.setTimeout(()=>a(!1),1400)}return(0,n.jsx)("button",{className:"copy-prompt",onClick:t,children:s?"Copied ✓":"Copy prompt"})}function l(){return(0,n.jsxs)("main",{className:"how-page",children:[(0,n.jsx)(t.default,{className:"how-shared-nav"}),(0,n.jsxs)("section",{className:"how-hero",children:[(0,n.jsx)("img",{src:"/seed-audio-how-to-hero.png",alt:"Seed Audio 2.0 production studio with headphones and luminous sound waves"}),(0,n.jsx)("div",{className:"how-hero-shade"}),(0,n.jsxs)("div",{className:"how-shell how-hero-content",children:[(0,n.jsx)("span",{className:"how-pill",children:"A hands-on guide to Seed Audio 2.0"}),(0,n.jsx)("h1",{children:"How to get a usable first take—and fix the misses."}),(0,n.jsx)("p",{children:"Hear six examples, see the prompts behind them, and learn when to use text, an image, or reference audio. We also cover the mistakes that most often lead to muddy or awkward results."}),(0,n.jsxs)("div",{className:"how-actions",children:[(0,n.jsxs)("a",{href:"#examples",children:["Hear the examples ",(0,n.jsx)("b",{children:"▶"})]}),(0,n.jsxs)("a",{href:"/#studio",children:["Open generator ",(0,n.jsx)("b",{children:"↗"})]})]}),(0,n.jsxs)("div",{className:"how-stats",children:[(0,n.jsxs)("div",{children:[(0,n.jsx)("strong",{children:"6"}),(0,n.jsx)("span",{children:"Playable scenes"})]}),(0,n.jsxs)("div",{children:[(0,n.jsx)("strong",{children:"20s"}),(0,n.jsx)("span",{children:"Focused examples"})]}),(0,n.jsxs)("div",{children:[(0,n.jsx)("strong",{children:"2 min"}),(0,n.jsx)("span",{children:"Maximum generation"})]}),(0,n.jsxs)("div",{children:[(0,n.jsx)("strong",{children:"4"}),(0,n.jsx)("span",{children:"Prompt layers"})]})]})]})]}),(0,n.jsx)("section",{className:"how-answer",children:(0,n.jsxs)("div",{className:"how-shell",children:[(0,n.jsxs)("div",{children:[(0,n.jsx)("span",{children:"WHAT IS SEED AUDIO 2.0?"}),(0,n.jsx)("h2",{children:"How Seed Audio 2.0 Builds Voice and Scene Audio Together"})]}),(0,n.jsxs)("div",{children:[(0,n.jsx)("p",{children:"Text-to-speech usually gives you a voice track. Here, the same prompt c

1an also place that voice in a room, add background sound, and cue events at specific moments."}),(0,n.jsx)("p",{children:"It works best for drafts: podcast openings, rough film scenes, product demos, game concepts, and lessons you want to hear before producing properly."})]})]})}),(0,n.jsxs)("div",{className:"how-shell how-guide-layout",children:[(0,n.jsxs)("aside",{className:"how-toc",children:[(0,n.jsx)("b",{children:"ON THIS PAGE"}),(0,n.jsx)("a",{href:"#examples",children:"Example results"}),(0,n.jsx)("a",{href:"#pattern",children:"Prompt pattern"}),(0,n.jsx)("a",{href:"#workflow",children:"Workflow"}),(0,n.jsx)("a",{href:"#checks",children:"Failure checks"}),(0,n.jsx)("a",{href:"#questions",children:"FAQ"})]}),(0,n.jsxs)("div",{className:"how-content",children:[(0,n.jsxs)("section",{id:"examples",className:"how-examples",children:[(0,n.jsx)("span",{className:"how-kicker",children:"PROMPT EXAMPLES"}),(0,n.jsx)("h2",{children:"Listen to 6 Seed Audio 2.0 Scene Examples"}),(0,n.jsx)("p",{className:"how-lead",children:"Every card pairs a playable result with a reusable production brief and the decisions worth carrying into your own prompt."}),(0,n.jsx)("div",{className:"how-example-list",children:r.map((e,s)=>(0,n.jsxs)("article",{className:"how-example",children:[(0,n.jsxs)("div",{className:"example-summary",children:[(0,n.jsx)("img",{src:e.image,alt:`${e.title} scene`}),(0,n.jsxs)("div",{className:"example-main",children:[(0,n.jsxs)("span",{className:"example-tag",children:["Example ",s+1,": ",e.tag]}),(0,n.jsx)("h3",{children:e.title}),(0,n.jsx)("p",{children:e.use}),(0,n.jsxs)("div",{className:"audio-box",children:[(0,n.jsx)("b",{children:"Audio preview"}),(0,n.jsx)("audio",{controls:!0,preload:"metadata",src:e.audio,children:"Your browser does not support audio playback."})]})]}),(0,n.jsxs)("div",{className:"example-time",children:[(0,n.jsx)("span",{children:"Audio"}),(0,n.jsx)("strong",{children:"20s"})]})]}),(0,n.jsxs)("div",{className:"example-details",children:[(0,n.jsxs)("div",{children:[(0,n.jsxs)("div",{className:"detail-title",children:[(0,n.jsx)("b",{children:"Prompt"}),(0,n.jsx)(c,{text:e.prompt})]}),(0,n.jsx)("pre",{children:e.prompt})]}),(0,n.jsxs)("div",{children:[(0,n.jsx)("b",{children:"What this example shows"}),(0,n.jsx)("ul",{children:e.notes.map(e=>(0,n.jsx)("li",{children:e},e))})]})]})]},e.title))})]}),(0,n.jsxs)("section",{id:"pattern",className:"how-section",children:[(0,n.jsx)("span",{className:"how-kicker",children:"PROMPT STRUCTURE"}),(0,n.jsx)("h2",{children:"Build the Scene in Four Connected Layers"}),(0,n.jsx)("p",{className:"how-lead",children:"The strongest Seed Audio 2.0 prompts read like compact production briefs instead of disconnected keywords."}),(0,n.jsxs)("div",{className:"pattern-grid",children:[(0,n.jsxs)("article",{children:[(0,n.jsx)("b",{children:"1. Scene and output"}),(0,n.jsx)("p",{children:"Name the format, location, duration target, audience, and intended emotional effect."})]}),(0,n.jsxs)("article",{children:[(0,n.jsx)("b",{children:"2. Speakers and delivery"}),(0,n.jsx)("p",{children:"Define speaker count, role, tone, pacing, emotion, language, and how clearly each voice should be heard."})]}),(0,n.jsxs)("article",{children:[(0,n.jsx)("b",{children:"3. Acoustic setting"}),(0,n.jsx)("p",{children:"Describe room tone, weather, crowd, vehicle, classroom, or outdoor ambience that should surround the voices."})]}),(0,n.jsxs)("article",{children:[(0,n.jsx)("b",{children:"4. Music and events"}),(0,n.jsx)("p",{children:"Add one music direction and one to three ordered sound events, including when the final cue should happen."})]})]})]}),(0,n.jsxs)("section",{id:"workflow",className:"how-section workflow-section",children:[(0,n.jsxs)("div",{children:[(0,n.jsx)("span",{className:"how-kicker",children:"WORKFLOW"}),(0,n.jsx)("h2",{children:"Start with a Focused Seed Audio 2.0 Test"}),(0,n.jsx)("p",{children:"Use the first generation as a diagnostic pass, then revise one layer at a time."})]}),(0,n.jsx)("div",{className:"workflow-list",children:[["Start text-only","Use a 15 to 25 second target before adding reference files."],["Listen for the biggest issue","Check voice clarity, ambience, music intensity, and event timing separately."],["Rewrite one layer","Change only the speaker, ambience, music, or effects before rerunning."],["Prepare the final clip","Download the best draft, trim exact timing, and save the prompt."]].map((e,s)=>(0,n.jsxs)("article",{children:[(0,n.jsx)("b",{children:s+1}),(0,n.jsxs)("div",{children:[(0,n.jsx)("h3",{children:e[0]}),(0,n.jsx)("p",{children:e[1]})]})]},e[0]))})]}),(0,n.jsxs)("section",{id:"checks",className:"how-section",children:[(0,n.jsx)("span",{className:"how-kicker",children:"GENERATION FAILURE CHECKS"}),(0,n.jsx)("h2",{children:"Why Seed Audio 2.0 Generations Can Fail"}),(0,n.jsx)("p",{className:"how-lead",children:"Check the input before changing the whole creative direction."}),(0,n.jsxs)("div",{className:"check-grid",children:[(0,n.jsxs)("article",{children:[(0,n.jsx)("i",{children:"✓"}),(0,n.jsx)("h3",{children:"Reference audio is too long"}),(0,n.jsx)("p",{children:"Keep each uploaded reference at 30 seconds or shorter."})]}),(0,n.jsxs)("article",{children:[(0,n.jsx)("i",{children:"✓"}),(0,n.jsx)("h3",{children:"The prompt is overloaded"}),(0,n.jsx)("p",{children:"Reduce competing voices, music moods, and effect lists."})]}),(0,n.jsxs)("article",{children:[(0,n.jsx)("i",{children:"✓"}),(0,n.jsx)("h3",{children:"Named people or protected characters"}

1),(0,n.jsx)("p",{children:"Describe the role and vocal qualities generically instead."})]})]})]}),(0,n.jsxs)("section",{id:"questions",className:"how-section how-faq",children:[(0,n.jsx)("span",{className:"how-kicker",children:"FAQs"}),(0,n.jsx)("h2",{children:"Seed Audio 2.0 Usage FAQ"}),(0,n.jsx)("div",{children:d.map(([e,s],a)=>(0,n.jsxs)("details",{open:0===a,children:[(0,n.jsxs)("summary",{children:[e,(0,n.jsx)("span",{children:"+"})]}),(0,n.jsx)("p",{children:s})]},e))})]})]})]}),(0,n.jsx)("section",{className:"how-cta",children:(0,n.jsxs)("div",{className:"how-shell",children:[(0,n.jsxs)("div",{children:[(0,n.jsx)("span",{children:"READY TO CREATE?"}),(0,n.jsx)("h2",{children:"Start with one tested prompt, then adapt the scene."}),(0,n.jsx)("p",{children:"Change the setting and voice direction first. Add references only when the core result works."})]}),(0,n.jsx)("a",{href:"/#studio",children:"Try Seed Audio 2.0 →"})]})}),(0,n.jsx)(o.A,{})]})}}},e=>{e.O(0,[5445,1235,5760,4308,8500,2697,3960,8441,3794,7358],()=>e(e.s=2673)),_N_E=e.O()}]);