Skip to main content
Vowen runs your dictation through a speech model of your choice. Some run entirely on your machine, some are cloud APIs you connect with your own key, and one lets you point Vowen at a server you run yourself. All of them live on the Speech models page in the left sidebar. That page has three sections: Cloud, Local (split into English Only and Multilingual), and, on Windows, GPU Acceleration.
Vowen's Speech models page showing a grid of cloud provider cards above the Local section

The Speech models page. Cloud providers come first, then the Local sections. The dark card with a tick is your active model.

​
Quick recommendations

​
Local models

Local models run entirely on your machine and need no internet connection. Nothing is bundled with the installer. You download every local model on demand from the Speech models page. See Model Download & Management. Sizes below are the download sizes as the app reports them.

​
Parakeet

NVIDIA’s Parakeet family. Vowen ships four separate Parakeet models, not one. Each is a different set of weights with its own language coverage and its own capabilities.
Parakeet Mandarin returns plain text only: no per-word timings, so no clickable timestamps and no subtitle export, no live preview, and no speaker labels. Everything else about it works normally.
Parakeet Japanese and Mandarin are macOS only. There is no Windows build, and on Windows the Speech models page simply does not list them.
On macOS, Parakeet V2 and V3 also pull down a small end-of-utterance streaming model in the background. It is what powers the live transcription preview. You never pick it or see it in the model list. See the download page for what it is and when it gets removed.

​
Nemotron (macOS, Apple Silicon)

NVIDIA Nemotron Speech models. Both stream natively, and unlike Parakeet their live preview arrives already punctuated and capitalized. It reads as finished text while you are still speaking, instead of arriving as a lowercase run-on that gets fixed at the end. Nemotron transcribes files with the same engine it uses for dictation, so its output carries no per-segment timings. See Languages for the full 31-language list.

​
Whisper

OpenAI’s Whisper, running locally on your own machine. 99 languages on the multilingual variants.
The (EN) models are English-only and slightly more accurate for English than their multilingual counterparts of the same size.
Tiny and Base ignore your Dictionary. Among the local Whisper sizes, only Small, Medium, Large v3 and Large v3 Turbo use your vocabulary. If you rely on custom vocabulary, use Small or larger. See Accuracy.

​
Start-up cost

Ordinary dictations pay no model load cost. On macOS and Windows alike, a local model is loaded once and stays ready between dictations. You do pay a one-time wait the first time a given model runs on your Mac, while it is optimized for your specific chip. That takes roughly 20 seconds, and noticeably longer the very first time. During that window the indicator shows “Optimizing Parakeet model”, and a dictation you start anyway is saved for retry rather than transcribed. See the download page for what to expect.

​
Cloud models

Cloud models send audio to a third-party API. They need an internet connection and an API key that you supply. Vowen never charges you for cloud transcription; you pay the provider directly, and most have a free tier. Counts below are the languages Vowen offers in the dictation language picker for that model. See Languages for the lists themselves.
There is no gpt-4o-transcribe in Vowen. Dictation uses either gpt-live-transcribe (streams while you speak) or gpt-transcribe (transcribes after you stop), depending on the toggle described in Per-model options. File transcription always uses gpt-transcribe, except when speaker identification is on, which switches to gpt-4o-transcribe-diarize. That is the only OpenAI model that emits speaker labels, and the only one that accepts no vocabulary hints at all.
Dictation streams over WebSocket in six languages: English, Spanish, French, German, Italian and Portuguese. File transcription uses Universal-3.5 Pro for the 18 languages it natively supports and falls back to Universal-2 for anything else.
Streaming uses Gemini Live, whose sessions are capped at 15 minutes each. File transcription uses Gemini Flash and handles audio up to about 9.5 hours. Custom vocabulary and speaker labels both work on Gemini file transcription, but more weakly than on providers built for them.
Listed in the app as Real-Time STT (Soniox). One entry covers both a real-time streaming model for dictation and an async model for file transcription, across 60+ languages. It is the strongest option in Vowen for switching languages mid-sentence.
Streaming-first, tuned for the lowest word error rate and the fastest live preview. English only. File transcription runs Cartesia’s batch model, which does not use your Dictionary.
Groq’s API returns text only. When you turn on speaker identification with a Groq model, Vowen runs its own on-device speaker pipeline over the audio afterwards, on macOS and Windows. See Diarization.

​
Setting up a cloud model

1

Open Speech models

Click Speech models in the left sidebar. Cloud models are the first section.
2

Pick a provider

Click its card. A configuration panel opens showing the model’s languages and capabilities.This is true only for a provider you have not set up yet. Once a provider is configured, clicking its card switches to that model instead. Use the gear on the card to reopen its settings.
The Cloud section of the Speech models page with one provider card highlighted

Click any card in the Cloud section to open its configuration panel.

3

Paste an API key

Use the “Get your API key here” link to open the provider’s dashboard, generate a key, and paste it in.
The Speech models page with a provider's configuration panel open inline, showing an API Key field with Cancel, Save and Disconnect buttons

The panel opens inline, underneath the card. Paste the key and click Save.

4

Save

The model becomes your active model immediately. You can connect as many providers as you like and switch between them at any time, including from the tray menu.
The Cloud section with a configured provider card highlighted, showing the gear that reopens its settings

A provider you have set up keeps a gear on its card. The gear reopens the key panel; clicking the card itself switches to that model.

Groq is the most popular choice among Vowen users. It is fast, accurate, and its free tier covers most daily use.

​
Per-model options

Two providers expose extra controls in the same panel where you paste the API key. For OpenAI, Dictation model is a two-way toggle: This affects dictation only. File transcription always uses gpt-transcribe.
The OpenAI configuration panel with the Dictation model toggle highlighted, offering gpt-live-transcribe and gpt-transcribe

OpenAI's Dictation model toggle, in the same panel as the API key.

ElevenLabs Scribe v2 has two toggles, both off by default:
The ElevenLabs Scribe v2 configuration panel with its two option toggles highlighted

ElevenLabs adds its two toggles below the key field. Both are off unless you turn them on.

​
Custom speech servers

Point Vowen at any OpenAI-compatible transcription endpoint: a local whisper.cpp server, LocalAI, Ollama, FastFlowLM, a vLLM Whisper deployment, or a hosted service that speaks the same API. A custom server needs a Server URL. A Model Name and an API Key are both optional; leave them blank when your server does not require them. Vowen checks that the URL is reachable before saving, so a typo fails immediately instead of surfacing at your next dictation. Once saved, a custom server behaves like any other cloud model: it renders as its own card on the Speech models page, appears in every model picker, and can be selected from the tray.
The Add Custom API form filled in with a name, a server URL, a model name, and an empty optional API key field

The form: a name, the server URL, and optionally a model name and key.

The end of the Cloud section on the Speech models page, with the dotted Add Custom API card highlighted

Add Custom API sits at the end of the Cloud section, beside the built-in Local / Self-hosted card.

Adding a second and further custom server is a Pro feature. Use Add Custom API at the end of the cloud section. Free users keep the single original slot.
Custom servers receive your Dictionary terms the same way Groq does, as a hint. It helps, but less than an engine that uses your Dictionary directly.

​
Speaker identification

Not every model can label who said what. These can, for pre-recorded audio and meeting notes: Cloud: Nova 2 and Nova 3 (Deepgram), Scribe v2 (ElevenLabs), Universal-3.5 Pro (AssemblyAI), Voxtral Mini (Mistral), Aurora (xAI), Speechmatics, OpenAI, Gemini. Local, on macOS and Windows: Parakeet V2, Parakeet V3, and every Whisper model. Groq’s two Whisper models also qualify, because Vowen runs the same on-device speaker pipeline over their output. Nemotron, Parakeet Japanese, Parakeet Mandarin, Cartesia Ink 2, Saaras v3 and custom servers do not offer speaker labels. Speaker identification is a Pro feature. Full detail in Diarization.

​
Real-time preview

Live text under the recording indicator needs a streaming-capable model. Every cloud model in the table above except the two Groq entries and custom servers can stream. Locally, Parakeet V2, Parakeet V3, Nemotron EN and Nemotron Multilingual stream on macOS; Parakeet streaming is not available on Windows. Turn it on in Settings > Recording > Real-time transcription preview. The row is greyed out until your active model can stream.

​
GPU acceleration (Windows)

If you have an NVIDIA GPU, Vowen can download a CUDA acceleration module that dramatically speeds up local Whisper transcription.
  • Windows only. macOS is already accelerated and needs nothing extra; Linux is not supported.
  • Requires an RTX 2000 series or newer NVIDIA GPU.
  • The download is about 631 MB. No separate CUDA toolkit install is needed.
The card only appears on the Speech models page when Vowen detects a supported GPU. Download it, restart Vowen, and even Large v3 responds in a couple of seconds.

​
Local or cloud