Seed Audio 1.5
Experience SeedAudio 1.5, the next-gen AI audio scene generator for dialogue, music, and SFX.
Is this your product? Claim it to edit the listing, post updates and answer questions. Prove it with an email address at the product's domain (the listing becomes Claimed), or put the LotsDirectory badge on your website (the listing becomes Verified, and its link to your website is followed while the badge is live).
Description
Experience SeedAudio 1.5, the next-gen AI audio scene generator for dialogue, music, and SFX. Test Seed Audio 1.0 live and get early-bird launch pricing.
About Seed Audio 1.5
What is Seed Audio 1.5?
SeedAudio 1.5 is ByteDance Seed's audio model for complete scenes. It is built to generate dialogue, music, ambience, and sound effects together. The live generator on this site currently uses Seed Audio 1.0, while the published SeedAudio 1.5 length is 6 minutes, up from 2 minutes.
What Seed Audio 1.5 does
Published capabilities cover multi-speaker dialogue, reference voices, 30 languages with regional variants, video-aware dubbing, timestamps, and separate tracks. Four published input modes are text, text plus audio, text plus video, and text plus audio plus video. The live Seed Audio 1.0 generator accepts up to three audio references or one image.
Who Seed Audio 1.5 is for
Seed audio 1.5 is aimed at video dubbing, podcasts, audiobooks, game scenes, and ads. The page also lists short film sound design, marketing creatives, game and XR prototypes, and learning content.
How Seed Audio 1.5 works
Write a sound-scene prompt, add an optional audio or image reference, choose output settings, then generate. Settings include voice behavior, output format, sample rate, speed, volume, pitch, and a max credit cap. Paid audio tasks temporarily reserve 150 credits before generation, covering up to about 120 seconds. The final charge is 75 credits per generated minute, rounded up to a whole credit, with a 10-credit minimum.
Key features
- Dialogue, ambience, foley, and music can be generated in one pass, with separate stem tracks.
- Reference-guided voices can follow emotion, style, pace, and non-speech sounds. Published support is up to six audio references.
- Video-aware dubbing and timestamp control are in the published SeedAudio 1.5 specifications. The live workspace currently uses Seed Audio 1.0.
- 30 languages with regional variants, and four input modes for text, audio, and video.
- Scene ambience and BGM include environmental beds, background music, room tone, weather, crowds, or distant city texture.
- Commercial use depends on the terms of the access channel used to generate the audio.
Pricing
As listed on seedaudio15.org, checked 15 October 2026. Prices can change; see the site for current terms.
- Free is $0, with 10 free credits. The FAQ says free generations stay up to 8 seconds, and the card lists max 2 min audio per generation, API access, and priority support.
- Pro lists Save $39.98, $16.66, and $19.99/mo, with 30,000 credits per year, up to 400 total audio minutes, everything in Free, and reference voice uploads.
- Max lists Save $99.98, $41.66, and $49.99/mo, with 90,000 credits per year, up to 1,200 total audio minutes, and everything in Pro.
- The page says plan prices are unchanged. Credits work on one shared balance for the web app and API. A yearly option says 2 months free.
- Paid audio tasks temporarily reserve 150 credits, then charge 75 credits per generated minute, with a 10-credit minimum. Questions go to contact@seedaudio15.org.
Facts from seedaudio15.org, checked 15 October 2026
Written from Seed Audio 1.5's own website (Homepage, Pricing). The maker can claim this listing to edit it.
Categories
Frequently asked questions
Can SeedAudio 1.5 follow a video?
Published input modes include text plus video, and text plus audio plus video, for dubbing and sound design around existing footage. The generator accepts text, up to three audio references, or one image.
Why can a generation on the current generator fail?
On the current Seed Audio 1.0 generator, most failures come from input length or content policy, including reference audio longer than 30 seconds. Trim reference audio to 30 seconds or less and describe roles generically.
Why are 150 credits reserved?
Paid audio tasks temporarily reserve 150 credits before generation, covering up to about 120 seconds. The final charge is 75 credits per generated minute, rounded up to a whole credit, with a 10-credit minimum. Any clip up to 8 seconds costs 10 credits, and an 8-second result returns 140 credits.
Can output be used commercially?
Commercial use depends on the terms of the access channel used to generate the audio. Check license, content restrictions, and output rights before ads, games, podcasts, or paid media.
How long can SeedAudio audio be?
The published SeedAudio 1.5 limit is six minutes, up from two minutes in Seed Audio 1.0. On this site today, free generations stay up to 8 seconds and paid Seed Audio 1.0 generations stay up to 2 minutes.