AI & Models · Integration
Synthesia
Add Synthesia to your product for your customers, and give your AI agents governed access to it.
Synthesia turns a script into a video of a presenter, so what an embedded Synthesia integration exposes is generation rather than a record store: your product submits a script with an avatar, a voice and a template, Synthesia renders it, and the result is a video file with a status you have to wait for. That asynchrony is the design constraint. A render takes minutes, so the call returns an id and your product either polls or takes a callback, and it has to handle a render that fails because the script was rejected. Each customer authorises their own Synthesia account, so the minutes and credits a render consumes are billed to whoever asked for it rather than metered from a shared key of yours, and every request is logged with the script behind it, because a finished video cannot be reconstructed from the request afterwards.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let each customer connect their own Synthesia account so the minutes their videos consume are billed to them.
Generate a video from a template your customer already branded, filling its variables with data from your product.
Treat the render as asynchronous: submit, hold the id, then fetch the file once the status says it is ready.
Handle a rejected or failed render as an expected outcome, showing the reason rather than a generic error.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent writes a script from a summary and submits it for rendering, with the script it used recorded.
An agent reports which renders are still in progress and which failed, and why.
An agent fetches a finished video and attaches it where the customer asked, within scoped permissions.
Example prompt
Turn this release summary into a two minute avatar video using our branded template and tell me when it has rendered.
Set up Synthesia in 4 steps
- 01Enable the Synthesia connector in your fastn dashboard.
- 02Have each customer authorise their own Synthesia account, so renders draw on their credits rather than a key you share.
- 03Map the templates, avatars and script variables your product uses, then decide whether you poll for status or take a callback.
- 04Call it from your product and expose the same connection to your agents through the MCP gateway.
Why teams use the Synthesia integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Synthesia integration without building it. Your customers connect their own Synthesia account inside your product and work their models, requests and outputs there, with no per-customer code on your side.
- Handle the part that actually costs time: per-customer keys, quotas and cost attribution matter more than schema here, because every call is billed. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a Synthesia update is not your on-call problem.
- One integration serves your product and your agents. The same governed Synthesia connection powers in-product features and gives AI agents scoped, audited access, so you give your product and your agents a model call each customer pays for themselves without wiring it twice.
Used by these teams
Compare with
ElevenLabs
OpenAI
ReplicateOften used alongside
Tools the same teams tend to run next to Synthesia, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeSynthesia integration FAQ
How do I add a Synthesia integration to my product?
Enable the Synthesia connector in your fastn dashboard, then let each customer authenticate their own Synthesia account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Synthesia client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Synthesia account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Synthesia account and only ever sees their own models, requests and outputs. That per-tenant isolation is the point of an embedded integration: you support the long tail of customer setups without maintaining an integration per customer.
Can AI agents use this Synthesia integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. An agent writes a script from a summary and submits it for rendering, with the script it used recorded.
Who maintains the Synthesia integration?
fastn does. When Synthesia changes an endpoint, deprecates a field or alters its auth, the fix lands in the connector rather than in your backlog, and your customers' connections keep working.
Whose Synthesia API key and quota does each call use?
Each customer authorises their own Synthesia account, so usage, rate limits and cost land on the customer that caused them. You are not metering a shared key and re-billing it, and one heavy customer cannot exhaust another's quota.
Are inputs and outputs auditable?
Yes. Every call is logged per tenant with the call, the input and the result, so an output can be traced back to what produced it. That matters more here than in most integrations, because a generated answer or an extracted field cannot be reconstructed from the request alone.
What can I build with the Synthesia integration?
A common starting point: let each customer connect their own Synthesia account so the minutes their videos consume are billed to them. Teams also use it for the other use cases listed above, and expose it to agents for governed reads and writes.
How much does the Synthesia integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Synthesia does not change your per-connector cost. You can start free with 3 connected accounts.
Add Synthesia to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.