Meetings & Voice · Integration
Retell AI
Add Retell AI to your product for your customers, and give your AI agents governed access to it.
Retell AI builds voice agents that hold real phone conversations, so the objects are the agent configuration, the phone number it answers on, and the call it produced. Calls are the interesting record because each carries a transcript and a recording, and those arrive after the call ends rather than during it, so a product reading immediately gets metadata and has to return for the content. Agents are configured with a prompt and a voice, which makes agent configuration something your product can offer as a feature rather than a setup step. Numbers are provisioned per account. fastn scopes each customer's key so their agents and call records stay theirs.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer connect their own Retell AI account so voice agents run on their number and their bill.
Create or update an agent's prompt and voice from inside your product.
Place an outbound call or handle an inbound one, driven by events in your product.
Read the transcript once a call completes and attach it to the right record.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent reads a call transcript and extracts what the caller actually wanted.
An agent updates a voice agent's prompt within governed permissions, with the change audited.
An agent triggers an outbound call in response to a product event, with the action logged.
Example prompt
Summarise the calls this agent handled today and flag any that ended badly.
Set up Retell AI in 4 steps
- 01Enable the Retell AI connector from your fastn dashboard.
- 02Have each customer authorise their own Retell AI account, so calls run under their credentials rather than a shared key.
- 03Decide which meetings, calls and participants your product needs, map those fields, then enable the actions and triggers you want.
- 04Call it from your product and expose it to your agents through the same governed connection.
Why teams use the Retell AI integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Retell AI integration without building it. Your customers connect their own Retell AI account inside your product and work their meetings, calls and participants there, with no per-customer code on your side.
- Handle the part that actually costs time: a call or a meeting is a real-time event, so a missed join or a dropped recording cannot be retried later. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a Retell AI update is not your on-call problem.
- One integration serves your product and your agents. The same governed Retell AI connection powers in-product features and gives AI agents scoped, audited access, so you let your product act on the conversations that happen by voice and video, not just the written ones without wiring it twice.
Used by these teams
Compare with
Bland AI
DialpadWorks well with
TwilioOften used alongside
Tools the same teams tend to run next to Retell AI, across other categories.
Slack
Microsoft Teams
Calendly
Google CalendarRetell AI integration FAQ
How do I add a Retell AI integration to my product?
Enable the Retell AI connector in your fastn dashboard, then let each customer authenticate their own Retell AI account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Retell AI client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Retell AI account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Retell AI account and only ever sees their own meetings, calls and participants. 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 Retell AI 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 reads a call transcript and extracts what the caller actually wanted.
Who maintains the Retell AI integration?
fastn does. When Retell AI 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.
Can my product schedule or act on Retell AI conversations automatically?
Yes. Within the permissions each customer grants, your product can create a meeting, place or route a call, add participants, or react when one ends, all inside their own Retell AI account rather than through a shared one.
Can I get recordings, transcripts and outcomes back from Retell AI?
Yes, scoped per tenant and audited. This matters more here than in most integrations, because the substance of a call usually exists only in its recording or transcript, so a read that fails silently loses the thing you wanted.
What can I build with the Retell AI integration?
A common starting point: let a customer connect their own Retell AI account so voice agents run on their number and their bill. 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 Retell AI integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Retell AI does not change your per-connector cost. You can start free with 3 connected accounts.
Add Retell AI to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.