by ByteDanceAudio
Seed Audio 1.0
Multi-voice audio scenes with music and effects
From 54 credits per run≈ $0.54
What it's like to use
Seed Audio 1.0 is ByteDance's all-in-one audio model: describe the speakers, put their lines in quotes, add music, ambience and sound effects, and get one finished scene of up to about two minutes back as an MP3. Each character gets a distinct voice in the same clip, so you don't need a separate voice model per role.
Good for
- Short audio dramas with two or more characters
- Sound-designed scenes: dialogue, music and effects in one track
- Voice tracks for a talking avatar or a lip-sync video
What Seed Audio 1.0 can do
Each mode opens in the studio with Seed Audio 1.0 already picked. The price shows before you generate.
How to prompt Seed Audio 1.0
- Write it like a radio script: who is speaking, how they sound, then their line in quotes.
- Add the room around them in the same prompt: rain on a window, a café murmur, a distant train.
- To reuse a voice, upload up to three reference clips and refer to them in the prompt as @Audio1, @Audio2 and @Audio3.
Settings worth knowing
Everything else has a sensible default, so you can type a prompt and go.
image_url- The picture to start from.
reference_audio_urls≤ 3- Audio to match: a voice, music or a rhythm.
speed0.5–2- Speaking pace.
output_formatmp3 · wav · opus · pcm- File type of the result.
How it compares
Same kind of job, different strengths and prices.
MiniMax Speech 2.8 HD is the better pick for a single narrator reading a long script. Seed Audio is built for whole scenes with several voices and sound.
Good to know
One flat price per request, whatever the length. The whole scene, voices included, has to fit in a 2,000-character prompt.
Questions about Seed Audio 1.0
How much does Seed Audio 1.0 cost?
On PopNow, the cheapest run of Seed Audio 1.0 costs 54 credits ($0.54) per run. You pay with credits (1 credit = $0.01), the exact cost shows on the Generate button before you start, and failed generations are refunded automatically.
What can Seed Audio 1.0 do?
On PopNow, Seed Audio 1.0 works in these modes: Sound Effects. Pick one in the studio and add a prompt or an upload.
How should I write prompts for Seed Audio 1.0?
Write it like a radio script: who is speaking, how they sound, then their line in quotes. Add the room around them in the same prompt: rain on a window, a café murmur, a distant train. To reuse a voice, upload up to three reference clips and refer to them in the prompt as @Audio1, @Audio2 and @Audio3.
Seed Audio 1.0 or MiniMax Speech 2.8 HD?
MiniMax Speech 2.8 HD is the better pick for a single narrator reading a long script. Seed Audio is built for whole scenes with several voices and sound.
Do I need to install anything to use Seed Audio 1.0?
No. Seed Audio 1.0 runs in your browser on PopNow: write a prompt or add a file, choose the settings and download the result. Sign up and you can generate straight away.
Make something with Seed Audio 1.0
Type an idea, pick your settings and see the price before you hit Generate.