Speech and sound for business teams
Seed Audio API
Call Seed Audio 1.0 through JMovie API for speech and sound from text, audio references or one image. The enabled model ID is seed-audio-1.0.
Updated ยท JMovie API integration guide
What the Seed Audio API can do
Seed Audio 1.0 generates natural speech and sound. You may send audio references or one image reference, plus sound configuration and subtitles. Audio and image references cannot be mixed.
Public and cloned speaker IDs remain unavailable until their exact supplier catalog or authorization can be verified. Do not use a Seedance portrait-library asset as a substitute for voice authorization.
How to integrate Seed Audio
POST /api/v3/tts/create with a Bearer Key and a unique Idempotency-Key, then poll GET /api/v3/tasks/:id. Generated PCM can be downloaded in its original raw format; without a trusted audio profile, raw PCM cannot be reused as a reference.
Seed Audio API pricing
Audio bills $0.0025 per actual original_duration second. Playback duration after changing speech rate is not the billing unit. Reservations can hold up to 120 original seconds until verified usage is known.
Frequently asked questions
What is the Seed Audio API?
Seed Audio 1.0 generates speech and sound from text, audio references or one image. JMovie API serves the fixed ID seed-audio-1.0.
Can Seed Audio mix audio and image references?
No. Seed Audio accepts audio references or a single image reference, not both together.
How do I call the Seed Audio API?
POST /api/v3/tts/create, then poll GET /api/v3/tasks/:id. Public and cloned speaker IDs remain unavailable until their exact supplier catalog or authorization can be verified.