SeedAudio 1.0 Audio Model

Explore SeedAudio 1.0 for complete sound scenes: expressive dialogue, music, ambience and effects shaped by one creative brief. Plan a reunion, a natural soundscape or a cinematic moment with the examples below, then bring your audio and visual ideas into your creative workflow.

SeedAudio 1.0 examples

Use these as scene-level sound briefs, rather than ordinary text-to-speech scripts. Identify dialogue, background sound and music separately. These illustrations show creative contexts, not playable model outputs. The optional “Use in a video” links open a video workflow; keep delivery notes separate from spoken text.

  • A quiet reunion at the station

    Create a short English audio scene at a quiet train station after rain. Two original adult voices speak naturally: A, warmly: "I thought I had missed you." B, relieved: "You are right on time." Begin with soft approaching footsteps and distant station ambience, leave space for each reply, then bring in a restrained warm piano phrase. Keep dialogue clearly audible above the background. No announcements with intelligible words, extra voices or abrupt ending.

    Use in a video
  • A layered woodland atmosphere

    Create a peaceful woodland soundscape at sunrise. Establish a close flowing stream, light leaves moving in a breeze and a few birds at different distances. Introduce delicate acoustic guitar gradually, keeping the natural ambience in front. Let the scene breathe with subtle variation rather than repeating an identical sound. No speech, loud percussion, sudden animal calls or dramatic volume changes.

    Use in a video
  • Footsteps through a rainy market

    Create a cinematic sound scene of an original adult walking through a nearly closed street market after rain. Begin with soft footsteps on wet stone, awnings shifting gently and distant muffled activity. Add one quiet original voice saying, "There is still a light ahead," then return to the street ambience. Use a low restrained musical texture only near the end. No busy overlapping dialogue, intelligible shop announcements or abrupt cuts.

    Use in a video

What SeedAudio 1.0 creates

Think in complete sound scenes, with a clear foreground, supporting ambience and a deliberate musical role.

SeedAudio 1.0 illustrative script or music brief context 1

Build dialogue, music and effects as one scene

A reunion scene needs more than two clean voices: footsteps establish distance, station ambience locates the action and a restrained musical phrase can change its emotional meaning. SeedAudio 1.0 is an audio-creation model for this broader sound-scene task, rather than just reading a text field aloud. Write the scene in layers and make the dialogue the foreground when the words matter. Specify when an effect enters and whether music should support or lead. Listen for balance and continuity across the full result instead of assessing each sound only in isolation.

SeedAudio 1.0 illustrative script or music brief context 1

Describe performance and speaker turns clearly

Multiple characters need distinct turns, a believable relationship and enough space for the listener to understand each line. Give every speaker a concise identity and describe the intended delivery around the spoken words. SeedAudio 1.0 supports Chinese and English in the provider’s current specification, with accent performance distinguished from unrestricted dialect output. Keep the script compact and avoid several characters speaking at once in an initial test. Review pronunciation, turn-taking and whether emotion fits the scene, then simplify any instruction that makes the exchange difficult to follow.

SeedAudio 1.0 illustrative script or music brief context 2

Use references for a specific creative purpose

An image can establish the setting, while an authorized audio reference can communicate a voice or sound character more directly than a long adjective list. The provider documents one image and up to three reference-audio clips for SeedAudio 1.0, alongside a text brief. These limits describe that provider workflow, not a verified upload menu in Dreamina. Choose clean references and state what each should contribute. Keep the requested scene original and check whether the result follows the intended voice, atmosphere and sound hierarchy rather than assuming every source detail will transfer exactly.

SeedAudio 1.0 illustrative script or music brief context 3

Plan duration and delivery as audio decisions

A sound scene needs time to establish its environment, deliver its lines and reach a natural ending. The provider lists output up to two minutes, several audio formats and sample-rate options, while marking SSML unsupported for this model. That makes a concise scene description more appropriate than borrowing a tag syntax from an unrelated TTS engine. Test a short passage before expanding the scene, and listen for rushed speech when the script becomes dense. Choose the actual export options offered by your service and review the file in the intended listening context.

Give the listener a clear scene

Use one organized brief to decide what the audience should hear first, what supports it and how the moment ends.

SeedAudio 1.0 illustrative script or music brief context 1

Make dialogue easier to place

Describe the room, distance and background before adding the lines. A clear sound environment gives you a practical way to judge whether the voices belong in the scene.

SeedAudio 1.0 illustrative script or music brief context 2

Keep atmosphere from burying the words

Specify a foreground voice and a restrained musical role. Review the mix at ordinary listening volume so an attractive ambience does not hide the important line.

SeedAudio 1.0 illustrative script or music brief context 3

Develop a scene with a natural ending

Leave a pause after the last line and describe how ambience or music should settle. That ending gives an audio edit a more useful place to finish or transition.

From brief to finished audio

Choose the model and workflow

Choose a service that explicitly offers SeedAudio 1.0. Confirm its supported inputs, duration and output settings. The Dreamina button here opens its general workspace rather than a verified standalone audio generator.

SeedAudio 1.0 illustrative script or music brief context 1

Prepare the script or sound brief

Copy a sound brief above and replace the setting or dialogue. Add permitted references only when the chosen service supports them. Separate foreground speech, ambience, effects and music in the instructions.

SeedAudio 1.0 illustrative script or music brief context 2

Listen, refine and use the result

Generate a short version and listen through headphones and ordinary speakers. Review dialogue clarity, speaker turns and the ending before refining the brief. Save the audio in an available format and use it in your chosen audio or audiovisual workflow.

SeedAudio 1.0 illustrative script or music brief context 3

Explore Dreamina plans

Compare plans for the creative tools available in Dreamina. These prices do not establish access to a particular standalone audio model or replace the model provider’s current pricing.

Basic

USD0.29/monthUSD15
USD 0.29 for the first month, then USD 15.00/month. Cancel anytime.The subscription will automatically renew.
1575 credits/month
USD1 = 5431 credits
Unlimited generationsSeedance 2.5No unlimited generationsSeedance 2.0No unlimited generationsSeedance 2.0 FastNo unlimited generations
  • Remove the Dreamina watermark in downloads
  • Extend video length
  • Increase video resolution
  • Make videos smoother (frame rate to up to 60 FPS)
  • Lip sync audio generations
  • Fast queue
  • One-year free unlimited 2K generation with Seedream 4.1 for users subscribe before Dec 15, 2025
  • One-year free unlimited 2K generation with Seedream 4.5 for users subscribe before Dec 15, 2025
  • Free Image 5.0 (2K) for 1 year
  • Free Image 4.6 (2K) for 1 year

Standard

USD21.60/monthUSD36
USD 21.60 for the first month, then USD 36.00/month. Cancel anytime.The subscription will automatically renew.
3885 credits/month
USD1 = 180 credits
Unlimited generations1K7-day unlimited1K7-day unlimited2K180-day unlimited
  • Remove the Dreamina watermark in downloads
  • Extend video length
  • Increase video resolution
  • Make videos smoother (frame rate to up to 60 FPS)
  • Lip sync audio generations
  • Fast queue
  • One-year free unlimited 2K generation with Seedream 4.1 for users subscribe before Dec 15, 2025
  • One-year free unlimited 2K generation with Seedream 4.5 for users subscribe before Dec 15, 2025
  • Free Image 5.0 (2K) for 1 year
  • Free Image 4.6 (2K) for 1 year

Advanced

USD31.60/monthUSD79
USD 31.60 for the first month, then USD 79.00/month. Cancel anytime.The subscription will automatically renew.
8645 credits/month
USD1 = 274 credits
Unlimited generations720p7-day unlimited2K30-day unlimited1K30-day unlimited
  • Remove the Dreamina watermark in downloads
  • Extend video length
  • Increase video resolution
  • Make videos smoother (frame rate to up to 60 FPS)
  • Lip sync audio generations
  • Fast queue (highest priority)
  • One-year free unlimited 4K generation with Seedream 4.1 for users subscribe before Dec 15, 2025
  • One-year free unlimited 4K generation with Seedream 4.5 for users subscribe before Dec 15, 2025
  • Free Image 5.0 (4K) for 1 year
  • Free Image 4.6 (4K) for 1 year

Ultra

USD208/monthUSD520
USD 208.00 for the first month, then USD 520.00/month. Cancel anytime.The subscription will automatically renew.
59000 credits/month
USD1 = 284 credits
Unlimited generations720p7-day unlimited720p7-day unlimited720p30-day unlimited
  • Remove the Dreamina watermark in downloads
  • Extend video length
  • Increase video resolution
  • Make videos smoother (frame rate to up to 60 FPS)
  • Lip sync audio generations
  • Fast queue (highest priority)
  • One-year free unlimited 4K generation with Seedream 4.1 for users subscribe before Dec 15, 2025
  • One-year free unlimited 4K generation with Seedream 4.5 for users subscribe before Dec 15, 2025
  • Free Image 5.0 (4K) for 1 year
  • Free Image 4.6 (4K) for 1 year

What users say about Dreamina's SeedAudio 1.0 workflow

Vera Drew

Illustrative creator brief: I would give the station scene a quiet background and two short lines, then listen for whether the piano supports the reunion without covering the words.

Emily R. •March 3
Alice

Illustrative creator brief: I would describe the stream as close and the birds as distant, so the woodland brief contains a useful sound hierarchy instead of a list of nature effects.

Jason T.•May 7
Bob

Illustrative creator brief: I would start with one spoken line in the rainy-market scene and check the pause afterward before adding more characters or a stronger musical layer.

Sophia L •May 9
Cathy

Illustrative creator brief: I would assign each reference a purpose, such as environment or authorized voice character, then compare the result with that specific intention.

Daniel K.•March 18
Vera Drew

Illustrative creator brief: I would give the station scene a quiet background and two short lines, then listen for whether the piano supports the reunion without covering the words.

Emily R. •March 3
Alice

Illustrative creator brief: I would describe the stream as close and the birds as distant, so the woodland brief contains a useful sound hierarchy instead of a list of nature effects.

Jason T.•May 7
Bob

Illustrative creator brief: I would start with one spoken line in the rainy-market scene and check the pause afterward before adding more characters or a stronger musical layer.

Sophia L •May 9
Cathy

Illustrative creator brief: I would assign each reference a purpose, such as environment or authorized voice character, then compare the result with that specific intention.

Daniel K.•March 18
David

Illustrative creator brief: I would test a short conversation first because rushed delivery is easier to notice when the script is compact and the speaker turns are clear.

Mia C. •May 14
Emma

Illustrative creator brief: I would listen at normal speaker volume as well as on headphones, checking that quiet dialogue remains understandable when the ambience becomes more detailed.

Ryan P •May 17
David

Illustrative creator brief: I would write the ending into the brief so the last line has time to land and the sound scene does not stop in the middle of a musical phrase.

Olivia N. • May 29
Emma

Illustrative creator brief: I would keep the model’s scene-generation workflow separate from ordinary TTS, using a layered brief when I need voices, atmosphere and effects together.

Chris A.• June 2
David

Illustrative creator brief: I would test a short conversation first because rushed delivery is easier to notice when the script is compact and the speaker turns are clear.

Mia C. •May 14
Emma

Illustrative creator brief: I would listen at normal speaker volume as well as on headphones, checking that quiet dialogue remains understandable when the ambience becomes more detailed.

Ryan P •May 17
David

Illustrative creator brief: I would write the ending into the brief so the last line has time to land and the sound scene does not stop in the middle of a musical phrase.

Olivia N. • May 29
Emma

Illustrative creator brief: I would keep the model’s scene-generation workflow separate from ordinary TTS, using a layered brief when I need voices, atmosphere and effects together.

Chris A.• June 2

SeedAudio 1.0 FAQs

What is SeedAudio 1.0?

SeedAudio 1.0, also described as Seed-Audio 1.0 or the Doubao audio-generation model, creates sound scenes from a prompt and supported references. Its scope includes dialogue, music, ambience and sound effects, which is broader than ordinary text-to-speech.

What inputs and languages does it support?

The provider lists text, one image and up to three audio references, with Chinese and English support. Accent performance does not mean unrestricted pure-dialect output. Check the chosen service’s exact input controls and use references you are permitted to use.

How long can the generated audio be?

The provider lists output up to two minutes. Actual usable duration depends on the selected service and request, and dense spoken text may sound rushed. Start with a short scene and leave room for pauses, ambience and a natural ending.

Should I use SSML or an ElevenLabs tag format?

Do not assume those syntaxes apply. The current SeedAudio 1.0 specification marks SSML unsupported. Use a clear scene brief with speaker turns and sound direction, then follow the syntax documented by the service you actually use.

Can I start with free Dreamina credits?

Dreamina offers free trial credits for supported creative tools. Access to a named standalone speech or music model has not been established by the workspace link on this page. Check the available tools and current pricing in the service you choose; trial credits do not imply unlimited audio generation or a provider subscription.

Build your next creative project

Keep your script, sound brief and visual direction together. Open Dreamina to explore its available creative tools, and use the selected audio service for model-specific speech or music generation.

Dreamina Unlimited is live!

Dreamina Unlimited is live!

Unlock 10 top AI image and video models in one plan with unlimited generations.

Try now