BYOK

Bring your own API key for AI dictation.

Verenu doesn't run its own transcription or cleanup servers. You add an API key from a provider you already trust, and Verenu sends requests straight from your machine to that provider, with no Verenu backend in between.

Why bring your own key

You pay the provider directly, at their price, instead of paying Verenu a markup on top. You can see exactly which model handled your audio and text, since you picked it. And your API key lives in Windows Credential Manager or macOS Keychain on your own machine, not in a Verenu account.

Groq's transcription tier and Google's tier are both free at the time of writing, so BYOK doesn't have to cost anything.

Supported providers

Transcription and cleanup are picked separately. AssemblyAI is transcription-only, so pair it with Groq, OpenAI, or Google for the cleanup pass.

Groq
whisper-large-v3-turbo for transcription, llama-3.3-70b-versatile for cleanup
Free tier available
OpenAI
gpt-4o-transcribe for transcription, gpt-4o-mini for cleanup
Usage-based
Google
gemini-3.5-flash for transcription, gemini-3.5-flash for cleanup
Free tier available
AssemblyAI
AssemblyAI API for transcription only
Transcription only

Don't want to use a cloud provider at all?

Verenu also supports fully on-device transcription and cleanup models on Windows and Apple Silicon Macs, no API key or connection required after the model files download. See local AI dictation.