# Seed Audio 1.0

> Audio AI Model by ByteDance — available on Layer

Bytedance Seed Audio TTS with preset voices and zero-shot voice cloning.

Seed Audio 1.0 from ByteDance is a text-to-speech and audio generation model that produces natural, expressive speech from text prompts. It supports multilingual preset voices and voice cloning from a short audio sample, with control over speed, volume, pitch, and output format. Ideal for narration, character dialogue, localized voiceovers, and game audio where a consistent custom voice is required.

## Specifications

| Property | Value |
|----------|-------|
| Provider | ByteDance |
| Category | Audio |
| Price | 0.07 / second per second |

## Capabilities

- Text to Speech
- Auto Duration

---

[Try Seed Audio 1.0](https://next.app.layer.ai/me/session/new?baseModelId=SEED_AUDIO_1) | [All Audio Models](https://layer.ai/models/audio) | [All Models](https://layer.ai/models)