Seed Audio Multilingual
Seed Audio · Audio · Text → Speech
Synthesize natural speech in 20 languages — pick a named voice or clone one from a reference audio.
Model ID:
seed-audio-1.0-multilingualWorkflow: bytedance/text-to-speech20 LanguagesVoice CloningReference Audio
Model rates
What this model costs per generation, billed in Picsart credits.
| Tier | Rate | Approx. cost |
|---|---|---|
| Standard | 5 credits / min | ≈ $0.025 / min |
Approx. cost at ~$0.005/credit; your effective rate depends on your plan.
Credit plans
Credits are shared across every Picsart API and model. Buy them once or on a monthly plan — larger packs cost less per credit.
| Credits | One-time | Monthly | Per credit |
|---|---|---|---|
| 1,000 | $7.50 | $5.00/mo | $0.005 |
| 10,000 | $65.00 | $47.50/mo | $0.005 |
| 20,000 | $100.00 | $90.00/mo | $0.004 |
Snapshot of picsart.io/pricing — see the live page for current plans.
How credits work
- Credits are the universal unit for all Picsart APIs and models — each call deducts a fixed amount (this model's rate is above).
- 200 free credits on signup, so you can start building right away.
- Utility endpoints — uploads, listing, balance and result lookups — cost 0 credits.
- Larger credit packs lower your per-credit price; unused monthly credits don't roll over.
- High volume? Enterprise offers custom rates and support — [email protected].