Create a talking avatar job
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Headers
Unique key for safe retries of job creation requests.
8 - 128Body
- Option 1
- Option 2
Talking-avatar request. Lip-syncs a still portrait to either a generated script (TTS) or an existing audio file.
Pricing: 3 credits per second, minimum 5 seconds. +5 credits when
product_placement=true. For script mode, duration ≈ len(script) / 10
seconds, and script must be at least 100 characters (enforced server-side).
Hosted portrait image (png/jpg/jpeg/webp, ≤ 50 MB).
Script for mode=script. Min 100 chars (server-enforced).
100 - 8192• script — generate speech from script (default).
• audio — lip-sync to the provided audio_url.
script, audio Hosted audio URL for mode=audio (mp3/wav/m4a, ≤ 50 MB).
Optional library or custom voice ID. If omitted in mode=script,
the first voice in your library catalog is used.
When true (with product_image_url), fuses a product into the shot. Adds 5 credits.
Required when product_placement=true.
Optional hosted background image URL.
Response
Talking avatar job accepted.
image_generation_job, video_generation_job, talking_avatar_job queued, processing, completed, failed, canceled 0 <= x <= 100
