wispa
Models and languages

Transcription models

wispa can transcribe with local models that run on your device or cloud models that use your own API key. Here is the full lineup.

3 min read

The model is what turns your voice into text. wispa gives you two kinds: models that run on your device, and cloud models you reach with your own API key. Each mode picks one.

On-device models

Whisper runs locally in sizes from Tiny to Large, plus a Turbo build, so you can trade speed for accuracy. Parakeet runs through Apple MLX and is very fast on Apple Silicon Macs. With any local model your audio is transcribed and discarded on your computer, offline if you want.

Cloud models

OpenAI offers whisper-1 and the newer gpt-4o-transcribe and gpt-4o-mini-transcribe. Groq runs whisper-large-v3-turbo very fast. Cloud models need an internet connection and your own API key, and your audio is sent to that provider.

ModelWhere it runsBest for
Whisper Tiny to BaseOn your deviceFast and light, low-resource machines
Whisper Small to LargeOn your deviceHigher accuracy, fully offline
ParakeetOn your device (Apple Silicon)Very fast transcription on a Mac
OpenAICloud, your keyTop accuracy without a download
GroqCloud, your keyVery low-latency cloud transcription

FAQ

Questions and answers

Which model is the default?

A local Whisper Base model is the recommended starting point. It downloads quickly and transcribes well on most machines without sending audio anywhere.

Can I use different models for different tasks?

Yes. Each mode sets its own model, so you might use a fast local model for quick notes and a cloud model for long, accuracy-critical dictation.

Is Parakeet available on Windows?

No. Parakeet runs through Apple MLX and is Apple Silicon only. On Windows you can use local Whisper models or a cloud provider.

Ready when you are

Start dictating in minutes

Download wispa, load a model or add a cloud key, and your voice becomes clean text in nearly any app. Free while in beta.

Download wispa