Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Synthesia / Synthesia avatar models

Express-1

Fourth-generation expressive avatar model, with current stock-avatar access through the legacy video API.

availableClosed weightsVideo generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
5 of 17 specification fields collected
Output resolutionNot collectedAwaiting source review
Clip durationNot collectedAwaiting source review
Input billingNot collectedSynthesia
Output billingNot collectedNo inferred price

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected

No model-specific public value established in the reviewed sources.

Maximum output
Not collected

No model-specific public value established in the reviewed sources.

Context caching
Not collected

No model-specific public value established in the reviewed sources.

Reasoning
Not collected

No model-specific public value established in the reviewed sources.

Tool calling
Not collected

No model-specific public value established in the reviewed sources.

Structured output
Not collected

No model-specific public value established in the reviewed sources.

Streaming
Not collected

No model-specific public value established in the reviewed sources.

Batch processing
Not collected

No model-specific public value established in the reviewed sources.

Fine-tuning
Not collected

No model-specific public value established in the reviewed sources.

Parameters
Not collected

No model-specific public value established in the reviewed sources.

Architecture
Pretrained backbone with diffusion-based multimodal performance modelingSource for Architecture (opens in a new tab)

Parameter count and exact backbone names are not published in this source.

Knowledge cutoff
Not collected

No model-specific public value established in the reviewed sources.

Languages
Not collected

No model-specific public value established in the reviewed sources.

Release date
2024-04-22Source for Release date (opens in a new tab)

Official announcement of the fourth avatar generation.

Input modalities
AudioSource for Input modalities (opens in a new tab)

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.

Provider version
EXPRESS-1Source for Provider version (opens in a new tab)

Avatar catalog generation label, not an apiModelId or a pinned weight revision.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

API model ID
Not collected

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)
background
Transparent backgrounds supported by current stock-avatar guide. Hand gestures are not supported in that stock-avatar product.Source for background (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.

Read the service policy (opens in a new tab)
API model ID
Not collected

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
17 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)
Aspect ratios
16:9, 9:16, 1:1, 4:5, 5:4Source for Aspect ratios (opens in a new tab)
voiceSelection
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)
testMode
test=true produces a watermarked video without consuming the video quota.Source for testMode (opens in a new tab)
visibility
Private by default, with a time-limited download URL. Public videos can be viewed by anyone with their share URL.Source for visibility (opens in a new tab)
composition
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
CategoryUsageRateUnit
Video APIGenerated video1160 creditsminute of API video

Rate conditions

  1. 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.
Pricing source (opens in a new tab)

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.

Read the service policy (opens in a new tab)

Caching

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

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.

Classification evidence (opens in a new tab)

Lifecycle dates

Expressive Avatars / fourth generation announced22 Apr 2024Source (opens in a new tab)

Sources reviewed