AI & Models · Integration
AssemblyAI
Add AssemblyAI to your product for your customers, and give your AI agents governed access to it.
AssemblyAI's speech API at api.assemblyai.com returns 401 without an API key in the authorization header, and transcription is a two-step, asynchronous flow: you POST an audio URL to create a transcript, get an id back with status queued, then poll or receive a webhook when it becomes completed or error. Audio must be reachable by AssemblyAI, so private files are either uploaded to their upload endpoint first or exposed by a signed URL, and a URL that expires before processing starts fails after the job was accepted. Optional features such as speaker diarisation, chapters, sentiment and entity detection are flags set at creation, not afterwards, so adding one to an existing transcript means paying to run the audio again. The response returns both a flat text field and word-level timings, and with diarisation on the useful structure is utterances rather than words, which is what most products actually render. Streaming real-time transcription uses a separate websocket endpoint with its own limits. fastn holds each customer's AssemblyAI key on their own connection and keeps the submit, poll and webhook cycle wired up.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer connect their own AssemblyAI key so transcription is billed to them and their retention rules apply
Transcribe recorded calls and show speaker-separated utterances with timestamps in your product
Detect entities and topics in transcripts to tag records automatically instead of asking users to
Give admins a view of transcripts stuck in error status with the reason returned by the API
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
Ask an agent to summarise a completed transcript and list the action items with their timestamps
Have an agent submit a recording for transcription with diarisation enabled and report the job id, audited per tenant
Let an agent report how many minutes of audio a tenant transcribed in a period
Example prompt
Can you summarise yesterday's client call transcript and list who said what about pricing?
Set up AssemblyAI in 4 steps
- 01Enable the AssemblyAI connector from your fastn dashboard.
- 02Have each customer authorise their own AssemblyAI account, so calls run under their credentials rather than a shared key.
- 03Decide which models, requests and outputs 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 AssemblyAI integration
What you get by embedding it with fastn instead of building it yourself.
- Ship an AssemblyAI integration without building it. Your customers connect their own AssemblyAI 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 an AssemblyAI update is not your on-call problem.
- One integration serves your product and your agents. The same governed AssemblyAI 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
Anthropic Claude
OpenAI
Azure OpenAIOften used alongside
Tools the same teams tend to run next to AssemblyAI, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeAssemblyAI integration FAQ
How do I add an AssemblyAI integration to my product?
Enable the AssemblyAI connector in your fastn dashboard, then let each customer authenticate their own AssemblyAI account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no AssemblyAI client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own AssemblyAI account?
Yes. Every connection is scoped to the individual customer, so each authorises their own AssemblyAI 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 AssemblyAI integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. Ask an agent to summarise a completed transcript and list the action items with their timestamps
Who maintains the AssemblyAI integration?
fastn does. When AssemblyAI 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 AssemblyAI API key and quota does each call use?
Each customer authorises their own AssemblyAI 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 AssemblyAI integration?
A common starting point: let a customer connect their own AssemblyAI key so transcription is billed to them and their retention rules apply. 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 AssemblyAI integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding AssemblyAI does not change your per-connector cost. You can start free with 3 connected accounts.
Add AssemblyAI to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.