AI & Models · Integration
Plaud
Add Plaud to your product for your customers, and give your AI agents governed access to it.
Plaud makes recorders and the platform behind them, and the developer side of it is a transcription pipeline you can point your own audio at. The flow is deliberately staged rather than a single call: exchange a client id and secret for a partner token, mint a user token from it so work is attributable to the person it belongs to, request presigned URLs and upload the audio in parts, then submit the file for transcription and poll the task until it finishes. What comes back is a speaker-labelled transcript across a long list of languages, and the asynchronous shape is the point, since a one-hour recording is not a request you hold open. Each customer registering their own credentials is what keeps the minutes billed to the tenant whose conversation was captured, and it is also what makes the audit trail worth having, because a transcript cannot be reconstructed from the request that produced it.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Have each customer register their own Plaud credentials, so transcription minutes are billed to the tenant whose conversation was recorded.
Upload long recordings in parts through presigned URLs, so a one-hour file never has to survive a single request.
Submit audio and poll the transcription task, so your product can show progress instead of blocking on a call that runs for minutes.
Keep the speaker-labelled transcript next to the recording it came from, since the substance of an in-person conversation exists nowhere else.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent reads a finished transcript and pulls out what each speaker committed to.
An agent submits a recording for transcription under the tenant's own credentials, and the task id is logged.
An agent reports which recordings are still processing and which failed, rather than reporting silence.
Example prompt
Transcribe this recording and tell me which speaker agreed to the delivery date.
Set up Plaud in 4 steps
- 01Enable the Plaud connector in your fastn dashboard.
- 02Have each customer register their own client id and secret, so transcription minutes are billed to them rather than to a key you hold.
- 03Decide where audio is uploaded from, mint a user token per person so work stays attributable, and choose how the task is polled.
- 04Call it from your product and expose the same connection to your agents through the MCP gateway.
Why teams use the Plaud integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Plaud integration without building it. Your customers connect their own Plaud 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 Plaud update is not your on-call problem.
- One integration serves your product and your agents. The same governed Plaud 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
Google Cloud Speech-to-TextWorks well with
Fathom
GongOften used alongside
Tools the same teams tend to run next to Plaud, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudePlaud integration FAQ
How do I add a Plaud integration to my product?
Enable the Plaud connector in your fastn dashboard, then let each customer authenticate their own Plaud account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Plaud client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Plaud account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Plaud 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 Plaud 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 finished transcript and pulls out what each speaker committed to.
Who maintains the Plaud integration?
fastn does. When Plaud 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 Plaud API key and quota does each call use?
Each customer authorises their own Plaud 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 Plaud integration?
A common starting point: have each customer register their own Plaud credentials, so transcription minutes are billed to the tenant whose conversation was recorded. 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 Plaud integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Plaud does not change your per-connector cost. You can start free with 3 connected accounts.
Add Plaud to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.