Avatar IDs, voice IDs and component labels are not public immutable model checkpoint selectors.
Access
Select the Synthesia Express-Voice variant for remastered voices in the studio script editor. No standalone public TTS checkpoint selector is established.
Regions
AWS public-cloud hosting; no model-specific regional processing guarantee established.
voiceVariants
Remastered voices default to Synthesia Express-Voice. Switching to ElevenLabs Turbo v2 selects a different provider model and disables the remastered pronunciation controls.Source for voiceVariants (opens in a new tab)
Pronunciation controls
Studio controls accept phonetic spelling or a recorded pronunciation reference, with IPA/respelling choices and glossary reuse. Reliability varies by voice and language.Source for Pronunciation controls (opens in a new tab)
speed
Paragraph or whole-video speed adjustment from 0.8× to 1.2×. Numeric ratios are approximate, not guaranteed precise time stretching.Source for speed (opens in a new tab)
Current BYO Interactive Avatar API explicitly does not provide Synthesia voices. External TTS is supplied by the integrator.
Billing scope
No separately published Express-Voice per-character, per-token or per-minute tariff verified. Video creation is billed through the studio plan; avoid inferring a speech price from video bundles.Source for Billing scope (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
WavLM speaker similarity
Synthesia · provider-reported
0.977943cosine similarity
Provider study described in June 2025: 17 English-speaking identities with diverse accents, 13 target sentences each, separate 20–30-second cloning references. Chart values matched to EXPRESS-Voice in the published JavaScript. No independent replication or universal ranking claimed.
Provider study described in June 2025: 17 English-speaking identities with diverse accents, 13 target sentences each, separate 20–30-second cloning references. Chart values matched to EXPRESS-Voice in the published JavaScript. No independent replication or universal ranking claimed.
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.
