Audio generation

Seed Audio 1.0

by ByteDance

ByteDance's next‑generation audio model.
Speech, effects, and music in one pass.

Seed Audio 1.0

Key features

These are the expected features that will be available on Seed Audio 1.0.

Hear the range

Speech, sound effects, and music, generated together in one pass.

Documentary narrationSpeech

A warm, measured documentary voice-over.

0:00
0:12
Thriller voice-overSpeech

A hushed, tense line read, close and intimate.

0:00
0:12
Spice-market ambienceSound effects

A layered open-air market sound bed.

0:00
0:12
ThunderstormSound effects

A rolling storm building to a distant thunderclap.

0:00
0:12
Orchestral cueMusic

A short rising cue for strings and brass.

0:00
0:12
Lo-fi beatMusic

A relaxed beat with soft keys and vinyl crackle.

0:00
0:12

Technical specifications

Upcoming

Announced and expected soon, not yet released.

Beta in 2026

Early beta expected in 2026.

All-in-one

Speech, effects, and music together in one pass.

Beyond TTS

Past text-to-speech, toward full scene audio.

Seed line

Built on Seed-Music and Seed Speech 2.

Step change

A leap beyond routine voice tools.

Use cases

One-pass video audio

One generation gives a clip its narration, effects, and score, with no separate mixing step.

Narrated explainers

Speech plus light ambience and music in one output suits explainers and how-to clips where the voice carries it.

Ads and promos

A spoken line, a few effects, and a music bed as one soundscape, made for short ads and promos.

Podcast and audio drama

Dialogue with matching ambience and stings helps audio drama and scripted podcast segments feel placed in a scene.

Game and UI sketches

Quick combined audio roughs in a game moment or interface before bespoke sound design, voice, effect, and tone.

Social shorts

Creators making lots of short video generate fitting audio in one step instead of hunting for clips and tracks.

Prompt examples

Narrated explainer

Calm narrator over soft room tone, explaining a simple recipe step by step

Edit prompt

Ad soundscape

Upbeat voice line, a whoosh, and a short bright music bed for a sneaker ad

Edit prompt

Audio drama beat

Two characters argue in a busy cafe, clatter and chatter underneath

Edit prompt

Game moment

A heavy door creaks open into a cavern, low drone, a single dripping echo

Edit prompt

Social short

Punchy voiceover with a snappy transition sound and light background beat

Edit prompt

Scene ambience

Quiet forest at dawn, birdsong building, a gentle strings pad beneath

Edit prompt

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$0/ month
billed as $0 per year

900 monthly credits

1 user only

All models

Workflows

Standard

$0/ month
billed as $0 per year

3200 monthly credits

1 user only

All models

Workflows

Pro

$0/ month
billed as $0 per year

6200 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Pro Max

$0/ month
billed as $0 per year

24000 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

Unlimited credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows
Compare plan details

FAQs

What is Seed Audio 1.0?
Seed Audio 1.0 is ByteDance's upcoming all-in-one audio model. It goes beyond traditional text-to-speech to generate speech, sound effects, and background music together in a single output, built on ByteDance's Seed-Music and Seed Speech work. An early beta is expected in 2026.
When does Seed Audio 1.0 come out?
An early beta of Seed Audio 1.0 is expected in 2026. As an upcoming model, the timing may shift until ByteDance ships it.
How is Seed Audio 1.0 different from text-to-speech?
Plain text-to-speech turns words into a spoken voice. Seed Audio 1.0 produces the whole soundscape, the spoken line plus sound effects and background music, in one generation. The difference is scope: a finished scene of sound rather than only the voice.
What is Seed Audio 1.0 built on?
Seed Audio 1.0 builds on ByteDance's existing audio work: the Seed-Music generation system and the Seed Speech 2 line for natural, multilingual, emotion-controllable speech, plus the native audio in Seedance video, brought together into one model.
What is Seed Audio 1.0 good for?
The clearest fit is audio for video: a single pass that gives a clip its narration, effects, and music together. That suits ads, explainers, social shorts, and audio drama, where sourcing and mixing separate tracks is the slow part.

Other models

Seedance 2.0 4K

ByteDance

ByteDance's Seedance 2.0, now in native 4K. Big-screen detail that stays crisp in motion.

Seedance 2.5

ByteDance

ByteDance's next-generation video model. Up to 30s native clips, 50 references, 4K.

Seedream 5.0 Pro

ByteDance

ByteDance's next-generation image model. Precise layer editing and online search.

Happy Horse 1.1

Alibaba

Alibaba's video model. Synchronized audio and native lip-sync, generated in a single pass.