Voice · ByteDance
Seed Audio 1.0
ByteDance's audio model: you describe the voice, the performance and the background in one prompt. Pick it for a voiced scene with ambience.
Anonymized Moderate costWhat sets it apart
Seed Audio 1.0 from ByteDance takes one prompt that describes the voice, the performance and the background sound together, instead of picking a preset voice. In Sub Rosa it is billed by the second, with 20 languages.
- One prompt: voice, acting, ambience
- No preset voices
- Speed 0.5x to 2x, MP3 or WAV
Strengths and limits
Where it shines
- Voice, effects and ambience from one description
- 20 languages, French included
- Billed by the second of audio
Think twice when
- No preset voices: the voice is described in the prompt
- Listed with the music models in Sub Rosa, not with the voices
- Speed 0.5x to 2x
- MP3 or WAV
Use cases
Voiced scene with ambience
A tired detective speaks softly in a rainy alley, distant traffic and dripping water behind him: It was always going to end here.
Voice and background come from one description.
Character voice test
A cheerful old woman with a warm voice greets customers in a busy market.
The voice is described, not picked from a list.
Against its rivals
- ElevenLabsElevenLabs gives you polished preset voices instead of a described one.#1 of 10 on Artificial Analysis Speech Arena (1,330 Elo)
- xAI TTSxAI uses preset voices with inline tags for delivery.
- Gemini 3.1 Flash TTSGemini steers delivery with tags and Director's Notes, with a voice chosen from a list.#3 of 10 on Artificial Analysis Speech Arena (1,209 Elo)
Version history
Each version, dated, with what it changed over the one before.
- Seed Audio 1.0Latest
- Release date not published by the maker; listed as current by ByteDance Seed
The model in this family
| Model | Use | Privacy | Price |
|---|---|---|---|
Seed Audio 1.0seed-audio-1-0 | Audio | Anonymized | $0.0129 per 10 seconds of sound |
Specifications
| Specification | Seed Audio 1.0 |
|---|---|
| Accepts | text |
| Produces | audio |
| Languages | 20 languages in Sub Rosa |
| Price | $0.0129 per 10 seconds of sound |
| Privacy | Anonymized |
Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.
Sources
Everything on this page comes from these pages, read on October 16, 2026 or as dated on each score.