Quick setup
Open the kRouter dashboard at http://localhost:20128
Go to Providers → click AssemblyAI
Paste your API key, click Save
Test the connection
Use in your IDE
Point any OpenAI-compatible client at kRouter using your local API key.
# Endpoint
http://localhost:20128/v1
# API key (from Dashboard → API Keys)
sk-krouter-XXXX
# Model
aai/<model-id>How AssemblyAI billing works with kRouter
AssemblyAI is pay-per-token. You bring your own API key and kRouter routes to it, so you keep your own rate limits and billing relationship. kRouter authenticates it via apikey. 2 models are routable as assemblyai/<model>.
Through kRouter, AssemblyAI serves speech-to-text, exposed on /v1/audio/transcriptions. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from AssemblyAI is a one-line model change in your client rather than a rewrite.
AssemblyAI models & pricing
These are the model ids kRouter routes to. This provider does not publish per-token rates.
| Model | Route as |
|---|---|
| Universal 3 Pro | assemblyai/universal-3-pro |
| Universal 2 | assemblyai/universal-2 |
AssemblyAI links
AssemblyAI FAQ
Is AssemblyAI free through kRouter?
AssemblyAI is pay-per-token: you bring your own API key and are billed by AssemblyAI at their rates. kRouter adds nothing on top and is free and MIT-licensed.
How do I use AssemblyAI with Claude Code or Cursor?
Connect AssemblyAI in the kRouter dashboard, then point your tool at kRouter's local endpoint (http://localhost:20128/v1) with a kRouter API key. Any OpenAI-compatible client works, and models are addressed as assemblyai/<model>.
Which AssemblyAI models can kRouter route to?
2 models, including Universal 3 Pro, Universal 2. Every one is addressed as assemblyai/<model> from any client.
What happens when AssemblyAI is rate limited?
kRouter detects the limit, parks that account until its real reset time, and fails over to your next connected account or provider — so the request still completes instead of erroring.