Seed Audio 1.0 features
From text to natural AI speech. Seed Audio 1.0 covers text-to-speech, voice cloning and multilingual output in one generator, with flexible controls for any use case.
Key features
Turn text into speech (TTS)
Type your script and Seed Audio 1.0 generates natural, expressive speech. Describe the tone in plain language to cover everything from narration to conversational delivery.
Model: Seed Audio 1.0
Voice cloning
Reproduce a voice from reference audio — up to 3 clips, 30 seconds each, referenced in the prompt as @Audio1–@Audio3. Keep one consistent brand voice across all of your content.
Model: Seed Audio 1.0
20 preset voices
Choose from 20 preset voices to fit your tone and use case — narration, character, news reading. The same script sounds very different across voices, so preview and compare.
Model: Seed Audio 1.0
Multilingual
Speaks English, Chinese, Japanese, Spanish, Indonesian and Portuguese, and reads text that mixes languages without extra setup.
Model: Seed Audio 1.0
Speed, pitch & volume control
Fine-tune speaking speed (0.5–2.0x), pitch (±12 semitones) and volume (0.5–2.0x). Slow down fast delivery or drop the pitch for a lower, calmer voice to fit each project.
Model: Seed Audio 1.0
Output formats & sample rate
Export as MP3, WAV, PCM or OGG Opus, with sample rates up to 48 kHz. Choose the format that fits video, podcast or app and download straight away.
Model: Seed Audio 1.0
Credit preview before you generate
Every generation shows its credit cost before you run it, based on length and settings. Start with free credits, and failed jobs are not charged.
Model: Seed Audio 1.0
Feature FAQ
Common questions about Seed Audio 1.0 features.
Generate voice now
Create natural speech from text with Seed Audio 1.0. Your first generation is covered by free credits.