The visual model is driven by speech. Text-to-speech, script drafting and voice choice are separate pipeline stages; this does not establish native language reasoning.
Avatar IDs, voice IDs and component labels are not public immutable model checkpoint selectors.
Access
Hosted Synthesia video creation. Select an eligible avatar in the account; available identities and features depend on plan and rollout. No public immutable checkpoint selector.
Regions
AWS public-cloud hosting; no model-specific regional processing guarantee established.
Billing scope
Video creation consumes credits for new avatar footage. Provider estimates about 100 credits for a typical finished minute, varying with avatar screen time and generated assets. This is not a fixed model-specific per-minute tariff.Source for Billing scope (opens in a new tab)
regeneration
Editing and previewing do not consume generation credits. Only newly generated footage is charged on regeneration; this is not a token-cache contract.Source for regeneration (opens in a new tab)
rollout
Assistant launch page says every plan at no additional feature charge; stock-avatar help still describes staged rollout across avatars and workspaces. Check the actual avatar selection in the account.Source for rollout (opens in a new tab)
planScope
Express-3 is advertised on every plan at no extra feature charge; generation allowances and other usage charges still apply.Source for planScope (opens in a new tab)
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
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
Synthesia identifies this named model in its proprietary research or product materials. No public model weights or permissive weight license are established; open client code does not expose the serving model.
