Supported engines

whisper.cpp on Inpherio.

Earn from the whisper.cpp you already run. The Inpherio connector finds it automatically and offers the speech-to-text models you choose to developers through one OpenAI-compatible API — at prices you set.

What it is.

whisper.cpp is a fast C/C++ implementation of OpenAI's Whisper speech recognition, with a built-in transcription server.

whisper.cpp at a glance
ServesSpeech-to-text
Detected on127.0.0.1, port 8080, 8081 or 9090
Speech-to-text/v1/audio/transcriptions
Setup changes neededNone — the connector wraps it

Set it up in three steps.

  1. Run whisper.cpp

    Start whisper.cpp's server with a Whisper model.

  2. Install the connector

    Run the Inpherio install command from your dashboard on the same machine. The connector finds whisper.cpp on port 8080, 8081 or 9090 by itself.

  3. Set your prices

    Each model is benchmarked on your hardware, then goes live on the marketplace at the platform's default prices. Change any price, or switch a model off, from your dashboard.

The install command is one line on Linux, macOS, Windows, Raspberry Pi or Docker — see the connector guide.

Control it from your dashboard.

What the Inpherio dashboard can do with whisper.cpp on your machine, remotely and securely:

Model management for this engine happens in the engine itself — the Inpherio dashboard shows its models, prices and benchmarks, and you can still disable any model so it isn't offered.

Questions.

Does Inpherio work with whisper.cpp?

Yes. The Inpherio connector detects whisper.cpp running on the same machine automatically and lists its speech-to-text models in your dashboard — the ones you leave switched on are offered on the marketplace, at prices you set. You don't change your whisper.cpp setup.

Do all my whisper.cpp models go on the marketplace?

Only the ones you choose. Every model the connector finds appears in your dashboard, switched on by default; switch any model off (or the whole engine) and it is never routed to, rented or listed — the change applies straight away, no restart. A newly found model also has to pass a benchmark on your machine before anyone can use it.

Which port does Inpherio look for whisper.cpp on?

Port 8080, 8081 or 9090 on 127.0.0.1. If yours runs elsewhere, add a port override for whisper.cpp in your connector settings.

Can people reach my whisper.cpp server directly?

No. The connector only talks to your engine on 127.0.0.1 and dials out to Inpherio over an encrypted link — nothing on your machine listens for outside connections.

How are whisper.cpp models priced?

You set the price for each model in pounds — per million tokens for text and embeddings, per hour of audio for speech. Inpherio takes a flat 15% from what you earn, and each payout carries a payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country. New providers pay no platform fee for their first 12 months or until they have earned £250 fee-free, whichever comes first; the payout fee still applies.

Other engines.