Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Synthesia / Synthesia managed rendering

Interactive Avatar renderer

Hosted real-time avatar rendering service attached to a customer-controlled LiveKit speech agent; immutable model lineage is not exposed.

Video generation
availableClosed-source managed componentVideo generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
4 of 17 specification fields collected
Output resolutionNot collectedAwaiting source review
Clip durationNot collectedAwaiting source review
Input billingSee ratesSynthesia
Output billingSee ratesPublished units and conditions below

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
SupportedSource for Streaming (opens in a new tab)
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
Not collected

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

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
Not collected

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

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

Speech output supplied by the customer’s voice agent; conversation generation is external.

Output modalities
Video, AudioSource for Output modalities (opens in a new tab)

Publishes lip-synced video and the supplied audio. Audio passthrough does not establish native TTS.

Output transport
LiveKit onlySource for Output transport (opens in a new tab)

Access & pricing

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

Synthesia

Provider source (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://developers.synthesia.io/api/interactive-avatars/sessions with avatarIds, livekitUrl and a caller-minted livekitToken. Requires workspace API scope interactive_avatars:write and eligible account balance.
Regions
AWS public-cloud hosting; no model-specific regional processing guarantee established.
Streaming
SupportedSource for Streaming (opens in a new tab)
eligibleAvatars
Only synthetic and personal avatars; stock actor avatars cannot be used. Bust framing only, without hand, gesture or full-body controls.Source for eligibleAvatars (opens in a new tab)
enrollment
POST /api/interactive-avatars/avatars with sourceId from Studio. Repeated requests reuse ongoing/existing conversion unless regenerate=true. Credits are checked even when reusing an existing conversion.Source for enrollment (opens in a new tab)
Concurrent requests
Freemium: 1 running session; all paid plans: 100. Custom agreement possible. Separate minute quota exists but its threshold is unpublished.Source for Concurrent requests (opens in a new tab)
pipeline
Bring a LiveKit room, agent, speech generation and conversation logic. Synthesia hosts GPU rendering; customer-hosted transport does not make model inference self-hosted.Source for pipeline (opens in a new tab)
voiceService
Not supportedSource for voiceService (opens in a new tab)

Synthesia voices are not available through this BYO API.

sdk
Python 3.10+ and livekit-agents >=1.8.2. Attach AvatarSession before starting AgentSession; do not replace output.audio afterward.Source for sdk (opens in a new tab)
nodeAgents
Not supportedSource for nodeAgents (opens in a new tab)

Current integration explicitly does not support Node.js agents.

avatarSwitching
Plugin accepts 1–5 prepared avatar IDs; first starts active and swap_avatar selects another prepared avatar. This is not a public batch-generation API.Source for avatarSwitching (opens in a new tab)
timeouts
Worker join timeout defaults to 30 seconds; swap timeout defaults to 15 seconds. These are client timeouts, not model latency guarantees.Source for timeouts (opens in a new tab)
sessionTools
No session list, transcripts, recording or webhook/event system. Implement transcript capture and reconnect handling in the application.Source for sessionTools (opens in a new tab)
errors
402 for quota/plan issues, 429 for concurrent-session limit. A running session counts until it ends.Source for errors (opens in a new tab)
resolution
Hosted worker fixes output resolution; plugin has no quality setting and docs do not publish a numeric resolution. Subscribe at full client resolution.Source for resolution (opens in a new tab)
fullStack
Pricing page marks the managed voice + LLM + LiveKit option COMING SOON. It is not an available endpoint in this record.Source for fullStack (opens in a new tab)
Billing scope
Avatar-only USD $0.10/minute or 10 credits/minute in operational docs. India-rendered rate card shows INR ₹10/minute. These are distinct published billing displays, not a currency conversion. Shared account credit balance; external LLM, speech and transport costs are separate.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
Interactive avatar renderingAvatar layer only1$0.10minute of avatar usage
Interactive avatar renderingAvatar layer only110 creditsminute of avatar usage
Interactive avatar renderingAvatar layer only2₹10.00minute of avatar usage

Rate conditions

  1. Official operational tariff for the avatar renderer only. Connected STT, LLM, TTS and LiveKit are external. Shared account balance and concurrent-session quotas apply; no token-based estimate.
  2. India-localized rendered API pricing page. Not an exchange-rate conversion or a globally universal tariff. Bring your own voice, LLM and LiveKit; paid-plan and account entitlements apply.
Pricing source (opens in a new tab)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

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.

Classification evidence (opens in a new tab)

Sources reviewed