Back to models

Seed Audio 1.0

AudioText to audio
bytedance/seed-audio-1.0View on fal.ai

Parameters

Dictation ready.

Prompt or text to synthesize. Reference audio inputs by order with @Audio1, @Audio2, @Audio3.

Up to 3 reference audio URLs, referenced in prompt as @Audio1, @Audio2, @Audio3. Each clip: up to 30s, 10MB, wav/mp3/pcm/ogg_opus.

A single reference image URL (jpeg/png/webp, up to 10MB). Cannot be combined with audio references.

Result

Run the model to see the result here.