Avatar IDs, voice IDs and component labels are not public immutable model checkpoint selectors.
Access
POST https://api.synthesia.io/v2/dubbing with an uploaded sourceAssetId or signed S3 sourceVideoUrl and targetLanguages. Poll GET /v2/dubbing/{dubbing_project_id}; PATCH the same path to add locales. The API does not pin a Dubbing 2.0 checkpoint.
Regions
AWS public-cloud hosting; no model-specific regional processing guarantee established.
Exact target locale enum; plan entitlements can be narrower. Studio guide has a separate locale list and count.
inputUrl
Only signed S3 URLs accepted by the sourceVideoUrl route. Other URLs return 501. YouTube import in the studio does not establish YouTube support in this API.Source for inputUrl (opens in a new tab)
defaults
lipsyncEnabled=false; videoDuration=adaptive; visibility=private. If sourceLanguage is omitted it is detected automatically.Source for defaults (opens in a new tab)
completion
Asynchronous uploading, in_progress, complete or error states. Finished results expose expiring downloads and SRT/VTT captions. Inspect each language asset status.Source for completion (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
Dubbing
Voice only1
40 credits
minute of dubbed video
Dubbing
With lip sync1
80 credits
minute of dubbed video
Dubbing API · India rate card
Voice only2
₹40.00
minute of dubbed video
Dubbing API · India rate card
With lip sync2
₹80.00
minute of dubbed video
Rate conditions
October 1, 2026 published tariff, shared plan credit balance. Lip sync requires eligible plan access; Basic excludes it. Included allowances and enterprise agreements can affect billed usage. This is a managed pipeline rate, not a single internal model tariff.
India-localized rendered API rate card. Not a currency conversion or universal global price. Account plan and credit balance 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.
Avatar IDs, voice IDs and component labels are not public immutable model checkpoint selectors.
Access
Hosted Dubbing workflow with file upload or a YouTube link. Lip sync is excluded from Basic; Enterprise adds transcript/translation editing. Account and workspace enablement apply.
Regions
AWS public-cloud hosting; no model-specific regional processing guarantee established.
uploadLimits
MP4, WebM or MOV; up to 5 GB and 2.5 hours, 3840×2160 resolution, 23.98–60 fps, and audio sample rates 8–96 kHz. These are upload limits, not generated-output specifications.Source for uploadLimits (opens in a new tab)
bulkUpload
Up to 10 uploaded videos per batch with shared settings. YouTube links and existing Studio videos use a single-video flow; transcript review is unavailable in bulk.Source for bulkUpload (opens in a new tab)
timing
Adaptive changes video playback to fit the translated speech; Original keeps video speed and adjusts voiceover timing.Source for timing (opens in a new tab)
Enterprise transcript and translation editing supports speaker reassignment and replacement voices. Proofreading and retranslating consume no generation credits; generating changed output is billed.Source for editing (opens in a new tab)
Languages
Self-serve plans and Enterprise have distinct target-language lists; Enterprise guide names 135 languages and locales. This differs from the API enum and broad marketing counts.Source for Languages (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
Dubbing
Voice only1
40 credits
minute of dubbed video
Dubbing
With lip sync1
80 credits
minute of dubbed video
Rate conditions
October 1, 2026 published tariff, shared plan credit balance. Lip sync requires eligible plan access; Basic excludes it. Included allowances and enterprise agreements can affect billed usage. This is a managed pipeline rate, not a single internal model tariff.
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
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.
