Avatar IDs, voice IDs and component labels are not public immutable model checkpoint selectors.
Access
POST https://api.synthesia.io/v2/videos. Select an eligible avatar ID, provide scriptText or uploaded scriptAudio plus scriptLanguage, and retrieve the asynchronous video result. API entitlement required.
Regions
AWS public-cloud hosting; no model-specific regional processing guarantee established.
catalog
38 avatar rows carry this version label in the reviewed catalog. Identities and camera/costume variants are not distinct models.Source for catalog (opens in a new tab)
Set input[].avatarSettings.voice explicitly for a reproducible voice choice. Uploaded audio requires scriptLanguage; the selected speech provider is separate from the avatar renderer.Source for voiceSelection (opens in a new tab)
Circular, rectangular and voiceOnly styles; horizontal alignment and scaling. Vertical alignment is fixed to bottom. Input clips form scenes, not a separate batch-inference discount.Source for composition (opens in a new tab)
seamless
Seamless rendering is limited to anna_costume1_cameraA and mia_costume1_cameraA, with a static background and lower quality. Do not assume all avatars support it.Source for seamless (opens in a new tab)
Billing scope
From October 1, 2026, API video generation is listed at 160 credits per minute, distinct from approximate studio video metering. Shared account credits and API entitlement apply.Source for Billing scope (opens in a new tab)
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Video API
Generated video1
160 credits
minute of API video
Rate conditions
Official plan-change tariff effective October 1, 2026. Applicable to video API usage, not the studio estimate or real-time renderer. Shared credit balance, enabled account access and plan conditions apply.
Hosted on AWS. Customer data deletion is described as taking up to 90 days, with residual backups subject to their lifecycle. Service-improvement terms permit usage analysis within specified customer-instruction and consent restrictions; this is not a universal no-training or zero-retention promise.
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUTProcess & retain
The system processes eligible input and retains reusable state.
02 / LATER REQUESTCheck available state
Reuse depends on matching input, session state and the cache policy.
03 / CACHE HITReuse & generate
Reusing state can reduce repeated work. Any charges follow the billing rules below.
Synthesia
Not verified
Saved avatars, reusable videos and enrollment reuse are not documented prompt caching or discounted input-token billing.
How it works
Not collected
Saved avatars, reusable videos and enrollment reuse are not documented prompt caching or discounted input-token billing.
Minimum reusable input
Not collected
Saved avatars, reusable videos and enrollment reuse are not documented prompt caching or discounted input-token billing.
Lifetime & refresh
Not collected
Saved avatars, reusable videos and enrollment reuse are not documented prompt caching or discounted input-token billing.
How to enable it
Not collected
Saved avatars, reusable videos and enrollment reuse are not documented prompt caching or discounted input-token billing.
Usage fields
Not collected
Saved avatars, reusable videos and enrollment reuse are not documented prompt caching or discounted input-token billing.
Billing rules
Not collected
Saved avatars, reusable videos and enrollment reuse are not documented prompt caching or discounted input-token billing.
Limits & data boundaries
Not collected
Saved avatars, reusable videos and enrollment reuse are not documented prompt caching or discounted input-token billing.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
What the measurements say
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
A documented proprietary hosted version family or rendering component. Exact weight identity is not exposed; this record is a managed component, not a claim of a separate foundation checkpoint.
