# SeedAudio 1.5

> SeedAudio 1.5 is the next-generation AI audio model for dialogue, music, ambience, and sound effects.

## Overview

- SeedAudio 1.5 (also written seed audio 1.5 and seed-audio-1.5) is coming soon. Published capabilities include dialogue, music, ambience, and sound effects in one pass, up to six minutes, six audio references, 30 languages, four input modes, video-aware dubbing, timestamps, and separate tracks.
- The homepage generator currently runs Seed Audio 1.0. Orders placed now lock in early-bird pricing for SeedAudio 1.5.
- Signed-in users can use the web generator when provider configuration and credits are available; pricing is credit-based and plan prices are unchanged.

## Primary Pages

- [Homepage](https://seedaudio15.org/): Main landing page for capabilities, the web generator, use cases, FAQs, and pricing access.
- [Chinese homepage](https://seedaudio15.org/zh): Chinese version of the homepage for readers who prefer Simplified Chinese.
- [Join updates](https://seedaudio15.org/sign-up): Sign-up page for creating an account before generating audio or buying credits.
- [Pricing](https://seedaudio15.org/pricing): Subscription and one-time credit pack options for AI audio generation.

## Key Sections

- [Version guide](https://seedaudio15.org/#versions): Side-by-side comparison of the upcoming SeedAudio 1.5 specifications and the live Seed Audio 1.0 generator.
- [Capabilities](https://seedaudio15.org/#capabilities): Summary of Seed Audio 1.0 as a sound-scene model beyond ordinary text-to-speech.
- [Use cases](https://seedaudio15.org/#use-cases): Creative uses for short films, marketing creatives, games, XR prototypes, podcasts, and learning content.
- [FAQs](https://seedaudio15.org/#faq): Answers about inputs, availability, generation length, prompt examples, commercial use, and whether the page includes a live generator.

## Machine-Readable Resources

- [llms.txt](https://seedaudio15.org/llms.txt): Concise machine-readable guide to SeedAudio 1.5 for LLMs and AI assistants.
- [llms-full.txt](https://seedaudio15.org/llms-full.txt): Expanded machine-readable guide with model context, prompt guidance, and use-case notes.

## Core Model Context

- Seed Audio 1.0 is best described as an AI audio generation model, not only a text-to-speech model.
- A strong prompt should define characters, setting, emotion, pacing, spoken dialogue, music mood, ambience, and specific sound events.
- The model direction emphasizes complete sound scenes: multi-speaker dialogue, emotional tone, accents, ambience beds, BGM, and sound effects.
- Multimodal context can be useful for steering characters, mood, rhythm, ambience, music, and effects.
- Commercial use depends on the terms of the access channel used to generate audio. Users should check output rights before publishing.

## Pricing And Credits

- Basic Monthly: $9.99 per month, 1,000 credits, up to ~13 total audio minutes at the current credit rate, credits valid for 30 days.
- Pro Monthly: $19.99 per month, 2,500 credits, up to ~33 total audio minutes at the current credit rate, credits valid for 30 days.
- Pro 2 Monthly: $39.99 per month, 6,000 credits, up to ~80 total audio minutes at the current credit rate, credits valid for 30 days.
- Pro 3 Monthly: $69.99 per month, 12,000 credits, up to ~160 total audio minutes at the current credit rate, credits valid for 30 days.
- Max Monthly: $49.99 per month, 7,500 credits, up to ~100 total audio minutes at the current credit rate, credits valid for 30 days.
- Max 2 Monthly: $99.99 per month, 20,000 credits, up to ~267 total audio minutes at the current credit rate, credits valid for 30 days.
- Max 3 Monthly: $179.99 per month, 45,000 credits, up to ~600 total audio minutes at the current credit rate, credits valid for 30 days.
- Basic Yearly: $6.58 per year, 12,000 credits, up to ~160 total audio minutes at the current credit rate, credits valid for 365 days.
- Pro Yearly: $16.66 per year, 30,000 credits, up to ~400 total audio minutes at the current credit rate, credits valid for 365 days.
- Pro 2 Yearly: $33.33 per year, 72,000 credits, up to ~960 total audio minutes at the current credit rate, credits valid for 365 days.
- Pro 3 Yearly: $58.33 per year, 144,000 credits, up to ~1,920 total audio minutes at the current credit rate, credits valid for 365 days.
- Max Yearly: $41.66 per year, 90,000 credits, up to ~1,200 total audio minutes at the current credit rate, credits valid for 365 days.
- Max 2 Yearly: $83.33 per year, 240,000 credits, up to ~3,200 total audio minutes at the current credit rate, credits valid for 365 days.
- Max 3 Yearly: $149.99 per year, 540,000 credits, up to ~7,200 total audio minutes at the current credit rate, credits valid for 365 days.
- Starter credit pack: $19.99 one-time credit pack, 700 credits, up to ~9.3 total audio minutes at the current credit rate, credits valid for 365 days.
- Creator credit pack: $24.99 one-time credit pack, 2,000 credits, up to ~27 total audio minutes at the current credit rate, credits valid for 365 days.
- Studio credit pack: $49.99 one-time credit pack, 4,500 credits, up to ~60 total audio minutes at the current credit rate, credits valid for 365 days.

For Simplified Chinese visitors, /zh/pricing shows monthly, yearly, and one-time pack tabs (default tab: packs). Subscriptions are charged in USD; one-time credit packs are charged in CNY through Stripe, converted from USD at 7.2 and rounded to whole RMB before checkout:

- Basic Monthly: US$9.99 per month, 1,000 credits, up to ~13 total audio minutes at the current credit rate, credits valid for 30 days.
- Pro Monthly: US$19.99 per month, 2,500 credits, up to ~33 total audio minutes at the current credit rate, credits valid for 30 days.
- Pro 2 Monthly: US$39.99 per month, 6,000 credits, up to ~80 total audio minutes at the current credit rate, credits valid for 30 days.
- Pro 3 Monthly: US$69.99 per month, 12,000 credits, up to ~160 total audio minutes at the current credit rate, credits valid for 30 days.
- Max Monthly: US$49.99 per month, 7,500 credits, up to ~100 total audio minutes at the current credit rate, credits valid for 30 days.
- Max 2 Monthly: US$99.99 per month, 20,000 credits, up to ~267 total audio minutes at the current credit rate, credits valid for 30 days.
- Max 3 Monthly: US$179.99 per month, 45,000 credits, up to ~600 total audio minutes at the current credit rate, credits valid for 30 days.
- Basic Yearly: US$6.58 per year, 12,000 credits, up to ~160 total audio minutes at the current credit rate, credits valid for 365 days.
- Pro Yearly: US$16.66 per year, 30,000 credits, up to ~400 total audio minutes at the current credit rate, credits valid for 365 days.
- Pro 2 Yearly: US$33.33 per year, 72,000 credits, up to ~960 total audio minutes at the current credit rate, credits valid for 365 days.
- Pro 3 Yearly: US$58.33 per year, 144,000 credits, up to ~1,920 total audio minutes at the current credit rate, credits valid for 365 days.
- Max Yearly: US$41.66 per year, 90,000 credits, up to ~1,200 total audio minutes at the current credit rate, credits valid for 365 days.
- Max 2 Yearly: US$83.33 per year, 240,000 credits, up to ~3,200 total audio minutes at the current credit rate, credits valid for 365 days.
- Max 3 Yearly: US$149.99 per year, 540,000 credits, up to ~7,200 total audio minutes at the current credit rate, credits valid for 365 days.
- Starter credit pack: ¥144 one-time credit pack, 700 credits, up to ~9.3 total audio minutes at the current credit rate, credits valid for 365 days.
- Creator credit pack: ¥180 one-time credit pack, 2,000 credits, up to ~27 total audio minutes at the current credit rate, credits valid for 365 days.
- Studio credit pack: ¥360 one-time credit pack, 4,500 credits, up to ~60 total audio minutes at the current credit rate, credits valid for 365 days.

## Guidance For AI Assistants

- Treat SeedAudio 1.5 as an independent information hub, not as an official ByteDance documentation site.
- Users can generate audio on SeedAudio 1.5 after signing in when provider configuration and credits are available.
- When explaining Seed Audio 1.0, emphasize complete audio scenes rather than isolated narration.