AI & Models · Integration

Deepgram

Add Deepgram to your product for your customers, and give your AI agents governed access to it.

Deepgram transcribes speech through api.deepgram.com, and its authorisation header is Authorization: Token <key> rather than Bearer, which is the first thing that breaks a copied HTTP client. Pre-recorded audio goes to POST /v1/listen either as a JSON body holding a url or as raw audio bytes with the right content type, while live audio uses a WebSocket to the same path; behaviour is driven by query parameters such as model, smart_format, diarize, punctuate and language rather than by a request body schema. Long files are better sent with a callback URL so the result is posted back instead of holding a connection open. Keys are scoped to a project and the secret is only shown once at creation, so rotation means creating a new key under /v1/projects/{id}/keys before revoking the old one. Usage and balance endpoints report per-project consumption, which is what per-customer billing should be reconciled against. fastn stores each customer's key and project, keeps the connection current and governs which agents may transcribe.

Start freeBook a demo

In your product

Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.

Let a customer connect their own Deepgram project so transcription is billed to their account and their key.

Transcribe uploaded call recordings with diarisation and store speaker-labelled text against the record.

Stream live meeting or call audio over the WebSocket and show captions inside your product.

Report per-project usage back to a customer so they can see transcription minutes consumed.

For your AI agents

Governed, audited access for the agents you build, through the MCP server.

Let an agent transcribe a named recording and return a summary with speaker labels, with minutes consumed audited per tenant.

Have an agent check project usage and balance before starting a large backlog transcription.

Allow an agent to create and read transcriptions while blocking API key creation or revocation.

Example prompt

Transcribe yesterday's support call and tell me who said what about the refund.

Set up Deepgram in 4 steps

  1. 01Enable the Deepgram connector from your fastn dashboard.
  2. 02Have each customer authorise their own Deepgram account, so calls run under their credentials rather than a shared key.
  3. 03Decide which models, requests and outputs your product needs, map those fields, then enable the actions and triggers you want.
  4. 04Call it from your product and expose it to your agents through the same governed connection.

Why teams use the Deepgram integration

What you get by embedding it with fastn instead of building it yourself.

  • Ship a Deepgram integration without building it. Your customers connect their own Deepgram 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 Deepgram update is not your on-call problem.
  • One integration serves your product and your agents. The same governed Deepgram 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

EngineeringData & Analytics

Compare with

Anthropic ClaudeOpenAIAzure OpenAI

Often used alongside

Tools the same teams tend to run next to Deepgram, across other categories.

SnowflakeAirtablePostgreSQLAmplitude

Deepgram integration FAQ

How do I add a Deepgram integration to my product?

Enable the Deepgram connector in your fastn dashboard, then let each customer authenticate their own Deepgram account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Deepgram client code in your app and no per-customer branch in your codebase. Setup is 4 steps.

Do my customers each connect their own Deepgram account?

Yes. Every connection is scoped to the individual customer, so each authorises their own Deepgram 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 Deepgram integration?

Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. Let an agent transcribe a named recording and return a summary with speaker labels, with minutes consumed audited per tenant.

Who maintains the Deepgram integration?

fastn does. When Deepgram 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 Deepgram API key and quota does each call use?

Each customer authorises their own Deepgram 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 Deepgram integration?

A common starting point: let a customer connect their own Deepgram project so transcription is billed to their account and their key. 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 Deepgram integration cost?

It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Deepgram does not change your per-connector cost. You can start free with 3 connected accounts.

Add Deepgram to your product

Start free with 3 connected accounts. No sales call required, and no per-customer integration code.

Start freeRead the docs
← All integrations